View Details

This morning Wired published This Ad-Tech Company Is Powering Surveillance of US Military Personnel. It’s a good piece, which is typical of Wired lately. But what caught my eye was “Ad-Tech” in the headline. Some writers say “ad tech.” Others say “adtech” or “AdTech.”

I’m highly leveraged in “adtech,” since I’ve now posted 160 pieces (including this one) using that expression since 2008.

So I did a Google Trends search on the three uses, and saw that “adtech” still wins, by a hair, though “ad tech” is close, and was ahead for much of the ‘teens.

The more interesting thing is that interest in the topic itself dropped by 75% between 2004 and th e mid-teens, and has kinda flattened since then.

But it’s still an issue.

At least I am relieved of the need to go back and change all those posts.

View Details

Looks right, works wrong.Every so often a product shows up that is so bad somebody needs to sound a warning.

So I’m sounding one for the Ion Retro Glow. For the last month or so, it’s been on display and selling at the Sams Club here in Bloomington, Indiana. That’s where I shot the photo above.

At first I thought it was just an interesting goof: an old-fashioned boom box with Bluetooth and a rechargeable battery. But then I remembered that I have about a hundred cassette tapes I want to go through, and no way to play them. I also thought the thing wouldn’t be a bad Bluetooth speaker system for my phone. The sound, while not great, wasn’t bad when I pressed the buttons on the display. I also still listen to some radio, so I thought that might be a nice bonus, if the radio was at least okay. And the price was right: $69.

So I bought one.

OMG. Quelle merde.

First, all the buttons and knobs are crap plastic, and the Stop/Eject button wouldn’t open the cassette door, making that function useless. Right there I needed to take it back. But to exchange it?

Not after checking out the radio.

The dial knob was so stiff I thought something was surely wrong with it. And there was. The dial pointer leaned one way or the other as one tuned up and down. And the radio was so bad on both bands that it would be a total turn-off to anyone wanting to give radio a try for the first time. (And there are now large demographics in that category.) Noise rejection on AM was completely absent, and the radio only got one station. There wasn’t even a tiny hint that there might be other signals out there. (And there are many here.) On FM, strong local signals splattered all over the dial, and the tuner made strange pulsing sounds as I (with lots of torque) turned the dial pointer slowly (there was no other way) up and down. And the sound kinda sucked too.

The only thing that worked as advertised was the Bluetooth. My phone found the thing instantly.

As for the sound, I’m much better served by the Bluetooth speakers I already have. There are good ones in the same price range.

The glowing rings around the speakers are just eye candy.

I suppose the rechargeable battery is okay. It worked for the few minutes I bothered checking it out.

The lesson: If you want a good boom box, check out your neighborhood or online thrift stores. Here’s Facebook Marketplace for my region here.

I suspect at least one of these is still good.

A final word to Sam’s Club: please stop selling this piece of crap. It makes victims of your customers.

View Details

Somebody just gave the 31st upvote to my answer to the Quora question “What do you regret as you get older?” So I thought it might be worth repeating.

Here’s a short list:

1. Not learning at least one other language.
2. Not learning a musical instrument (or to sing) well enough to play in a group.
3. Not getting fit physically and staying that way. (Related: not working hard to succeed in at least one varsity sport—especially one requiring teamwork.)
4. Not spending more time in other countries and cultures when I was young.
5. Getting married too early and often. (Since you’re asking, twice before a great marriage now going on 27 years.)

For a full perspective on those, here’s a list of things I don’t regret:

1. Staying curious about everything, all my life. (“Learn as if you’ll live forever, live as if you’ll die tomorrow,” Gandhi is said to have said.)
2. Learning to ski (in my 40s) and at learning to play soccer and basketball well enough not to be chosen last in pickup games.
3. Sucking in school, which forced me to learn in other ways—and to learn well enough to at least play a decent academic later in life.
4. Never taking up smoking, drugs or drinking heavily.
5. Watching so little TV that I miss most cultural references to various stars and shows.

There are many more possibilities for both lists, but that’s a start.

That was seven years ago. My wife and I have now been married for almost 34 years.

View Details

Twenty-fifth in the News Commons series

This is etched in limestone over an entrance to a building at the University of Wyoming. It gave John McPhee the title for perhaps its most useful book.Southern California has two seasons: Fire and Rain.

Rain didn’t begin this year until a few days after Fire ended apocalyptically, incinerating much of Altadena and Pacific Palisades. Now Rain is here, with the occasional atmospheric river flowing across the faces of hills and mountains whose beards were just burned off.

Much is being written about what geologists call debris flows and Muggles call mudslides. These tend to happen when mountains of poorly bound slopes of loose rock and soil get drenched in rain after the vegetation holding everything in place has been burned away. Many of the big slopes above Los Angeles are mile-wide dump trucks waiting to hoist their beds and open their tailgates. The Los Angeles County Flood Control District (aka “Flood”) has been on this case for a century and stands ready with debris basins and other risk abatements. But the San Gabriel Mountains are much bigger, and resemble volcanoes in their tectonic youth and tendency to erode downward and outward almost as fast as earthquakes push them up.

For describing all this, no writing is more useful than John McPhee‘s Los Angeles Against The Mountains, which ran first as a pair of long essays in September and October 1988 editions of The New Yorker, and later as a chapter in The Control of Nature, which came out in 1990. (Another chapter in that book is “The Army Corps of Engineers vs. the Mississippi,” which first appeared as Achafalya in a 1987 issue of The New Yorker. The magazine published it again after Hurricane Katrina as if it were a live report on what happened when the levees failed in New Orleans—though it had been written, prophetically, seventeen years earlier.)

McPhee is the Beethoven, the Rembrandt, the Shakespeare of nonfiction: inimitable and without equal. At ninety-three he is still writing and teaching other writers at Princeton. Though I’ve never set foot in Princeton, McPhee has been teaching me how to write for many decades. I have read all his books, some many times. A few have so many page flags I could brush off a table with them. Some of those flags now aid my compression of “Los Angeles Against the Mountains.”

Here he frames the battle:

…in the confrontation of the urban and the wild. Los Angeles is overmatched on one side by the Pacific Ocean and on the other by very high mountains. With respect to these principal boundaries, Los Angeles is done sprawling. The San Gabriels, in their state of tectonic youth, are rising as rapidly as any range on earth. Their loose inimical slopes flout the tolerance of the angle of repose. Rising straight up out of the megalopolis, they stand ten thousand feet above the nearby sea, and they are not kidding with this city. Shedding, spalling, self-destructing, they are disintegrating at a rate that is also among the fastest in the world…

The slopes average sixty-five to seventy per cent. In numerous places, they are vertical…The term “oversteepened” is often used to describe them. At the giddy extreme of oversteepening is the angle of maximum slope. Very large sections of the San Gabriels closely approach that angle. In such terrain, there is not much to hold the loose material except the plants that grow there…

And here he’s describing the experience of hanging with geologists on the steep face of one slope:

Evergreen oaks were fingering up the creases in the mountainsides, pointing toward the ridgeline forests of big-cone Douglas fir, of knobcone and Coulter pine. The forests had an odd sort of timberline. They went down to it rather than up. Down from the ridges the conifers descended through nine thousand, seven thousand, six thousand feet, stopping roughly at five. The forests abruptly ended—the country below being too dry in summer to sustain tall trees. On down the slopes and all the way to the canyons was a thicket of varied shrubs that changed in character as altitude fell but was everywhere dense enough to stop an army. On its lower levels, it was all green, white, and yellow with buckwheat, burroweed, lotus and sage, deerweed, bindweed, yerba santa… The thicket’s resistance to trespass, while everywhere formidable, stiffened considerably as it evolved upward…Whatever and wherever they were, these plants were prickly, thick, and dry, and a good deal tougher than tundra. Those evergreen oaks fingering up the creases in the mountains were known to the Spaniards as chaparros. Riders who worked in the related landscape wore leather overalls open at the back, and called them chaparajos. By extension, this all but impenetrable brush was known as chaparral.

The low stuff, at the buckwheat level, is often called soft chaparral. Up in the tough chamise, closer to the lofty timber, is high chaparral, which is also called hard chaparral. High or low—hard, soft, or mixed—all chaparral has in common an always developing, relentlessly intensifying, vital necessity to burst into flame. In a sense, chaparral consumes fire no less than fire consumes chaparral. Fire nourishes and rejuvenates the plants. There are seeds that fall into the soil, stay there indefinitely, and will not germinate except in the aftermath of fire. There are basal buds that sprout only after fire. Droughts are so long, rains so brief, that dead bits of wood and leaves scarcely decay. Instead, they accumulate, thicken, until the plant community is all but strangling in its own duff. The nutrients in the dead material are being withheld from the soil. When fire comes, it puts the nutrients back in the ground. It clears the terrain for fresh growth. When chaparral has not been burned for thirty years, about half the thicket will be dry dead stuff—twenty-five thousand tons of it in one square mile. The living plants are no less flammable. The chamise, the manzanita—in fact, most chaparral plants—are full of solvent extractives that burn intensely and ignite easily. Their leaves are glossy with oils and resins that seal in moisture during hot dry periods and serve the dual purpose of responding explosively to flame. In the long dry season, and particularly in the fall, air flows southwest toward Los Angeles from the Colorado Plateau and the Basin and Range. Extremely low in moisture, it comes out of the canyon lands and crosses the Mojave Desert. As it drops in altitude, it compresses, becoming even dryer and hotter. It advances in gusts. This is the wind that is sometimes called the foehn. The fire wind. The devil wind. In Los Angeles, it is known as Santa Ana. When chamise and other chaparral plants sense the presence of Santa Ana winds, their level of moisture drops, and they become even more flammable than they were before. The Santa Anas bring what has been described as “instant critical fire weather.” Temperatures rise above a hundred degrees. Humidity drops very close to zero. According to Charles Colver, of the United States Forest Service, “moisture evaporates off your eyeballs so fast you have to keep blinking.”

About fires, when they happen, he says this:

…Where the Santa Anas collide with local mountain winds, they become so erratic that they can scatter a fire in big flying brands for a long distance in any direction. The frequency and the intensity of the forest fires in the Southern California chaparral are the greatest in the United States, with the possible exception of the wildfires of the New Jersey Pine Barrens.

McPhee’s writing is always wrapped around characters, most of which I’m leaving out of this compression. The first exception for our purpose here is Wade Wells, a hydrologist with the United States Forest Service.

The chaparral fires are considerably more potent than the forest fires Wade Wells saw when he was an undergraduate at the University of Idaho or when he worked as a firefighter in the Pacific Northwest. “Fires in the Pacific Northwest are nothing compared with these chaparral fires,” he remarked. “Chaparral fires are almost vicious by comparison. They’re so intense. Chaparral is one of the most flammable vegetation complexes there are.”

It burns as if it were soaked with gasoline. Chaparral plants typically have multiple stems emerging from a single root crown, and this contributes not only to the density of the thickets but, ultimately, to the surface area of combustible material that stands prepared for flame. Hundreds of acres can be burned clean in minutes. In thick black smoke there is wild orange flame, rising through the canyons like explosion crowns. The canyons serve as chimneys, and in minutes whole mountains are aflame, resembling volcanoes, emitting high columns of fire and smoke…

In millennia before Los Angeles settled its plain, the chaparral burned every thirty years or so, as the chaparral does now. The burns of prehistory, in their natural mosaic, were smaller than the ones today. With cleared fire lanes, chemical retardants, and other means of suppressing what is not beyond control, people have conserved fuel in large acreages. When the inevitable fires come, they burn hotter, higher, faster than they ever did in a state of unhindered nature. When the fires end, there is nothing much left on the mountainsides but a thin blanket of ash. The burns are vast and bare. On the sheer declivities where the surface soils were held by chaparral, there is no chaparral.

Fine material tumbles downslope and collects in the waterless beds of streams. It forms large and bulky cones there, to some extent filling the canyons. Under green chaparral, the gravitational movement of bits of soil, particles of sand, and other loose debris goes on month after month, year after year, especially in oversteepened environments, where it can represent more than half of all erosion. After a burn, though, it increases exponentially. It may increase twentyfold, fortyfold, even sixtyfold. This steady tumbling descent of unconsolidated mountain crumbs is known as dry ravel. After a burn, so much dry ravel and other debris becomes piled up and ready to go that to live under one of those canyons is (as many have said) to look up the barrel of a gun.

One would imagine that the first rain would set the whole thing off, but it doesn’t. The early-winter rains—and sometimes the rains of a whole season—are not enough to make the great bulk move. Actually, they add to it…

In the slow progression of normal decay, chaparral litter seems to give up to the soil what have been vaguely described as “waxlike complexes of long-chain aliphatic hydrocarbons.” These waxy substances are what make unburned chaparral soil somewhat resistant to water, or “slightly nonwettable,” as Wells and his colleagues are wont to describe it. When the wildfires burn, and temperatures at the surface of the ground are six or seven hundred centigrade degrees, the soil is so effective as an insulator that the temperature one centimetre below the surface may not be hot enough to boil water. The heavy waxlike substances vaporize at the surface and recondense in the cooler temperatures below. Acting like oil, they coat soil particles and establish the hydrophobic layer—one to six centimetres down. Above that layer, where the waxlike substances are gone, the veneer of burned soil is “wettable.” When Wells drips water on a dishful of that, the water soaks in as if the dish were full of Kleenex. When rain falls on burned and denuded ground, it soaks the very thin upper layer but can penetrate no farther. Hiking boots strike hard enough to break through into the dust, but the rain is repelled and goes down the slope. Of all the assembling factors that eventually send debris flows rumbling down the canyons, none is more detonative than the waterproof soil.

In the first rains after a fire, water quickly saturates the thin permeable layer, and liquefied soil drips downhill like runs of excess paint. These miniature debris flows stripe the mountainsides with miniature streambeds—countless scarlike rills that are soon the predominant characteristic of the burned terrain. As more rain comes, each rill is going to deliver a little more debris to the accumulating load in the canyon below. But, more to the point, each rill—its natural levees framing its impermeable bed—will increase the speed of the surface water. As rain sheds off a mountainside like water off a tin roof, the rill network, as it is called, may actually cube the speed, and therefore the power, of the runoff. The transport capacity of the watershed—how much bulk it can move—may increase a thousandfold. The rill network is prepared to deliver water with enough force and volume to mobilize the deposits lying in the canyons below. With the appearance of the rills, almost all prerequisites have now sequentially occurred. The muzzle-loader is charged. For a full-scale flat-out debris flow to burst forth from the mountains, the final requirement is a special-intensity storm.

Some of the most concentrated rainfall in the history of the United States has occurred in the San Gabriel Mountains. The oddity of this is about as intense as the rain. Months—seasons—go by in Los Angeles without a fallen drop. Los Angeles is one of the least-rained-upon places in the Western Hemisphere. The mountains are so dry they hum. Erosion by dry ravel greatly exceeds erosion by water. The celebrated Mediterranean climate of Los Angeles owes itself to aridity. While Seattle is receiving its average rainfall of thirty-nine inches a year, Chicago thirty-three, the District of Columbia thirty-nine, and New York City forty-four, Los Angeles is doing well if it gets fifteen. In one year out of every four over the past century, rainfall in Los Angeles has been under ten inches, and once or twice it was around five. That is pure Gobi. When certain storm systems approach Los Angeles, though—storms that come in on a very long reach from far out in the Pacific—they will pick up huge quantities of water from the ocean and just pump it into the mountains…

Here begins a story about one debris flow, in a setting high and dry:

Five miles into the mountains from the edge of the city is a small, obscure, steep-sided watershed of twenty-five hundred acres which is drained by the Middle Fork of Mill Creek, a tributary of the Big Tujunga. The place is so still you can hear the dry ravel…

Then came Fire:

It was a textbook situation—a bowl in the mountains filled with hard chaparral that had not been touched by fire in ninety-nine years. The older chaparral becomes, the hotter it burns. In its first ten years of new growth, it is all but incombustible. After twenty years, its renewed flammability curves sharply upward. It burns, usually, before it is forty years old. The hotter the fire, the more likely a debris flow—and the greater the volume when it comes. The century-old fuel of the Middle Fork was so combustible that afterward there were not even stumps. The slopes looked sandpapered. The streambed, already loaded, piled even higher with dry ravel. The Middle Fire, as the burn was known, was cause for particular alarm, because a small settlement was a mile downstream. Its name—Hidden Springs—contained more prophecy than its residents seemed prepared to imagine. Three hundred and ninety thousand cubic yards of loose debris was gathered just above them, awaiting mobilization.

Then, Rain:

Toward midnight February 9th, an accidental fire broke out in a small building of Gabe Hinterberg’s. A fire truck eventually came. Half a dozen people fought the fire, assisted by the heavy rain. One of them was George Scribner. The five-minute spike of greatest downpour occurred at about one-thirty. Half an hour later, George said, “Hey, we got the fire put out.”

Gabe said, “Good deal.”

And then Gabe and George were dead.

Amos Lewis, nearby, was holding a fire hose in his hand and was attempting to prevent it from kinking. In his concentration, he did not see danger coming. He heard nothing ominous. He only felt the hose draw taut. Through his peripheral vision he became aware that the fire truck—with the hose connected to it—was somehow moving sideways. Seconds later, Amos Lewis, too, was swept away.

The snout of the debris flow was twenty feet high, tapering behind. Debris flows sometimes ooze along, and sometimes move as fast as the fastest river rapids. The huge dark snout was moving nearly five hundred feet a minute and the rest of the flow behind was coming twice as fast, making roll waves as it piled forward against itself—this great slug, as geologists would describe it, this discrete slug, this heaving violence of wet cement. Already included in the debris were propane tanks, outbuildings, picnic tables, canyon live oaks, alders, sycamores, cottonwoods, a Lincoln Continental, an Oldsmobile, and countless boulders five feet thick. All this was spread wide a couple of hundred feet, and as the debris flow went through Hidden Springs it tore out more trees, picked up house trailers and more cars and more boulders, and knocked Gabe Hinterberg’s lodge completely off its foundation. Mary and Cal Drake were standing in their living room when a wall came off. “We got outside somehow,” he said later. “I just got away. She was trying to follow me. Evidently, her feet slipped out from under her. She slid right down into the main channel.” The family next door were picked up and pushed against their own ceiling. Two were carried away. Whole houses were torn loose with people inside them. A house was ripped in half. A bridge was obliterated. A large part of town was carried a mile downstream and buried in the reservoir behind Big Tujunga Dam. Thirteen people were part of the debris. Most of the bodies were never found.

As Amos Lewis suddenly found himself struggling in the viscous flow, he more or less bumped into a whirling pickup, coming down in the debris from who knows where upstream. One of the roll waves picked him up and threw him into the back of the truck. As the vehicle spun around and around, it neared one bank. Lewis saw an overhanging limb. He reached for it, caught it, and pulled himself above the rocky flow. Years later, just about where this had happened, he told Wade Wells and me the story. “I got pushed to one side,” he said as he finished. “I lucked out.” Lewis is a prematurely white-haired man with a white beard and dark-brown eyes. On this day in late spring, his muscular build and deeply tanned skin were amply displayed by a general absence of clothing. He wore bluejean shorts, white socks, mountain boots, and nothing else. When people began to discover human remains in the reservoir, he had gone in his patrol car to investigate the fate of his neighbors. “I had to go roll on them calls,” he said. “A deputy sheriff has to roll on any type of body being found. I carried out at least four, maybe five, skulls.”

These are all things to bear in mind when we visit how news ought to work in a digital environment where facts mostly don’t matter—until they do.

View Details

The image above answered this prompt to ChatGPT: “Give me an image of a personal AI: one belonging to the individual and in control of the individual.” I added the text. It’s not perfect, or even close. But I’m rushed and not sure iterating this will get us anything better.The unintended risks of handing over our lives to Personal AI is the headline of the opening segment of Jamie Smith‘s newsletter today. In it he shares a post by Liz Gerber about an autonomous choice made by the AI in her self-parking car:

Last night, my car automatically parked in the grocery store parking lot. The car beautifully maneuvered itself into a parking spot avoiding colliding with other cars and people walking through the lot.

However the car prioritized performance, fine tuning its movement in the parking spot as my fellow shoppers waited in below freezing temperatures for the car to do a perfect job.

The car failed to register that one shopper was a mom with a crying child in her arms and a toddler tugging at her leg. And it failed to take into account the several cars that were waiting to turn into the parking lot, causing a backup on the street.

While the experience was delightful for me, the car was inconsiderate of others. Even worse, I didn’t notice the others until after the car had parked itself.

I didn’t stop my car from prioritizing my needs over others. I not only handed over steering to my car, I handed over my humanity.

Jamie then asks, What happens when we hand over our experiences – often very human experiences – to an AI agent? and added in summary, Digital wallets and Personal AI are going to have a transformative effect on our lives and society. But let’s make sure we don’t hand over our humanity with it.

Here’s another question: Is the AI in Liz’s car personal?

If we want truly personal AI—the kind under our control, working for us, enlarging our agency in the world—the answer to that question has to be no.

The AI in Liz’s car is not hers. It belongs to the car’s maker. It does not contain or express her humanity or extend her agency. It may be personalized, but it is not personal. (About the difference.)

We don’t have personal AI yet. (One bit of evidence is the image ChatGPT generated for me, above.) Yes, there is plentiful personalized AI, but nothing as personal as your pants, your PC, or the car you operate entirely on your own. Nothing that makes you more independent, not less.

We’re working at Kwaai on an open-source personal AI operating system (pAI-OS). There are other projects as well. But we don’t yet have a personal AI that does all the things this image suggests—

—much less an AI of our own that can express our ethical preferences.

Meanwhile, we need to be careful not to call the AIs in our things (especially big dangerous ones, such as cars) personal. They are not.

Personal AI is a greenfield. And there is a risk nothing will grow in it if we keep calling stuff like a car’s autonomous parking “personal AI.”

Oh, and you won’t find a better voice for personal empowerment in the digital world than Jamie Smith‘s. Please subscribe to his newsletter.

View Details

The location of just one United Club at O’Hare (ORD), one of United’s main hubs, through which I have transited countless times.United Airlines details 6 big inflight entertainment updates, including all-new Control Tower map, by Zach Griff in The Points Guy, is thick with welcome news for frequent United fliers, of which my wife and I are two. (So far I have clocked 1,533,214 miles with United, and she has about double that. We are also both lifetime members of the United Club, thanks to her wise investment in a sweet deal offered by United decades ago—and withdrawn quickly after that.)

We are also both T-Mobile customers, which is why seeing this on my phone’s United app is always welcome:

It mostly works. Yes, it’s slow, but it is possible to get work done at altitude at no extra cost. Very nice.

Here’s the rundown of new stuff from United, according to Zach:

• New 4K seatback screens
• “Bluetooth connectivity at every seat, making it possible to pair wireless headphones, including AirPods, with the entertainment systems.”
• Control Tower View: “This view allows you to pull up a map of the airfield that’s overlaid with all the aircraft around you. Clicking on each little plane brings up its call sign and operating airline… powered by the flight deck’s navigation systems and a live feed of planes from FlightAware.”
• Starlink is coming. This will be a huge boost in bandwidth for passengers connecting to the Net on flights.
• Channel 9 (now called “From the Flight Deck”) is still there.

Here is what that last item looked like, the last time I saw the option and shot it on a plane:

Two problems with this. First, it’s buried deep among entertainment options (Zach says it’s under the Audio tab). Second, most, if not all, pilots don’t bother with it. Back in the primitive Channel 9 days, more than half of United pilots turned it on (or left it on, if it was there by default). Or at least that was my experience. Zach:

That said, in recent years, United’s aviation enthusiast customers have complained that Channel 9 hasn’t been working. According to Green, the functionality is still very much available — it’s just that more and more pilots are choosing not to enable the feed.

“Pilots can turn it off if they don’t want people to hear whatever chatter is going on,” Green explained. All hope isn’t lost, though. “We know it’s a cool feature,” Green added. “We have it enabled as much as we can.” (That’s Dominic Green, United’s director of inflight entertainment.)

I suggest that United urge their pilots a bit more forcefully to turn the feature on. Fellow pilots and aviation buffs love having it there. And people afraid of flying also find it comforting to hear pilots sounding totally calm while flying through turbulence.

One more thing. While it would be nice to screen-share the seat-back screen from your own device, there’s this:

Extended displays aren’t coming soon

As more travelers bring their own tablets and laptops on board, I’ve always wondered why airlines don’t offer a screencasting feature on the entertainment screens. After all, it’s a lot easier to get work done with some additional screen real estate.

Turns out, United can already technically enable screencasting today, Green said, but a major issue will likely mean that flyers will never see this functionality.

“We’ve had a lot of pushback from our corporate partners that say they don’t necessarily want their staff using publicly available screens,” Green said.

It’s not that United would have access to any data; it’s that they don’t want nosy passengers snooping in on their neighbors.

Makes sense. But I think United could partner with Apple and Google to create Apple PlanePlay and Google Plane (or whatever names they want to come up with), so at least some personal apps could extend onto the seatback.

Anyway, progress.

View Details

When Hurricane Helene hit Western North Carolina, the Swannanoa River rose three storys above its shores, all but erasing the town named after the river, and leaving hundreds homeless.But the challenge for Swannanoa was not just recovery. It was regeneration. For that, Swannanoa’s residents formed new kinds of partnerships and problem solutions that could prove a model of what to do after disasters hit communities anywhere—such as Altadena and Pacific Palisades, on which I’ve been reporting lately in my News Commons series.

Kevin Jones, one of the founders of SOCAP and curator of Neighborhood Economics, is a Swannanoa resident reporting on what is working in real time. This next Wednesday, January 29 at Noon EST, Kevin will be doing exactly that in our Salon Series at Indiana University—and live on the Web.

If you care about recovery and regeneration for your neighborhood—or anybody’s—after disaster strikes, this is a one-hour required course. As a salon, it is participatory. Come with questions, answers, or helpful stories of your own. Let’s teach and learn together, for the sake of a world larger than each of our own.

Go here for more information and the Zoom link for the salon.

Photo by Bill McMannis.

View Details

Twenty-fourth in the News Commons series
Eigth on the #LAfires

7:35 am January 23, 2024—It’s morning now. The Hughes Fire is 17% contained but no longer interesting. The Sepulveda Fire broke out last night along the 405 freeway. It stopped at forty acres, and doesn’t matter much now. Here’s the path of one fire helicopter shuttling between the two fire sites:

So reporting is now off the fires themselves. Let’s look at these six screen grabs—

—and put them where they go on this table:

The rows are requirements of story-telling. The columns are stages of disaster news coverage.

In these screen grabs—

• Channel 4 is doing a mix of live reporting and human interest, focusing on how some characters (school kids) are doing nice things for firefighters.
• Channel 5 is doing live reporting from the Sepulveda Fire, which is pretty much out.
• Channel 7 has a weather forecast, for rain, which is long overdue and will put a damper on the fires. (An aside: my wife observes that “weather people on TV are either crusty old dudes or hot young women.”)
• KCAL/9 has an interview with a fire official working toward coming to an understanding while earlier footage (recalling live coverage) shows to his right.
• KTTV/11 (the Fox channel) is showing some public service stuff mixed with promotional jive. It’s between news segments and regular programming, so not news at all.
• Telemundo (Channel 52) is reporting on a church recovering from the Eaton Fire. That’s a mix of live reporting and human interest.
• Blame is not in any of these. If you want some of that, here’s the latest from the LA Times.

What I’m trying to do with this table is show how the requirements of a story (character, problem, movement) are met by the four stages of story-telling by journalists. Every story you see, hear, or read will play across that grid. Of course, none matter more than #4, which is more complicated and less interesting than the other three stages. But, that is where most facts will go. For more on that, see How Facts Matter.

8:10 pm—The LA Times reports that the I-5 is open again. (That link goes to their ongoing coverage.) Here is what CAL FIRE says about current fires and their containment:

Note that the Palisades and Eaton Fires are still not fully contained, though we haven’t been worried about them in a while. The same will happen with the Hughes Fire. While it is currently 0% contained, that does not mean it hasn’t been slowed or halted along stretches of its perimeter. Full containment means firefighters are sure the fire will not spread beyond control lines. And they are very cautious about the numbers they share. The winds later tonight and tomorrow are still a concern, and thousands of people remain evacuated.

5:40 pm—I just heard on one of the TV channels that The I-Five, aka The Grapevine, is likely to be opened again soon. All the channels sound more optimistic about the paths of the fire. Smoke is also flowing upwards rather than sideways, so that’s less of a concern as well.

Night has also fallen, meaning the flames are far more dramatic:

Great TV, but not more to worry about.

3:45 pm—Watching the Los Angeles TV stations (each with a tab in my browser) cover the Hughes Fire. I have them arranged by channel number. (Note that NBC’s 4 and Telemundo’s 52 are co-teamed. One reporter’s mike says NBC4 on two sides and T—for Telemundo—52 on two sides.) Including the above, here are all the media we’re watching, reading, and listening to:* KNBC/4 * KTLA/5 * KABC/7 * KCAL/9 * KTTV/11 * KVEA/52 * LA Times * LAist * #HughesFire on Bluesky * #HughesFire on Facebook * #hughesfire on Instagram * #HughesFire on Threads * #HughesFire on X

I’m also watching aerial fire fighting (aircraft, paths) on adsbexchange.com and FlightRadar24. Linked images from each:

On the plus side, the concerns here are for outer suburbs and exurbs on a landscape of hilly grassland and chaparral. Compared to the steeper San Gabriels (such as those above Pasadena and Altadena), the civilized stuff is relatively defensible, with fire breaks on the ridges and bare spaces around at least some of the housing developments and other collections of structures. Winds are not too strong for aircraft, which have been able to drop water and lines of retardant. It helps that Castaic Lake itself is an enormous fire break, as well as a convenient source of water to scoop up and drop on the fire.

So, while there is lots of danger here, especially if the winds get too high for aircraft to keep flying, I expect the fight against the HughesFire to succeed.

If we can back off the edges of our seats a bit, it should be interesting to look at coverage of the #HughesFire through the prism of story. Again, the three requirements are:

• Character(s)
• Problem(s)
• Movement

And the four stages of coverage are:

1. Live reporting
2. Human interest
3. Blame
4. Coming to an understanding

At this stage, the main character is the Hughes Fire, which is also the problem. And it’s moving. Of course all the media like to bring the human characters in: a resident, a fire captain, a county official, a store owner. Not long ago one of the TV stations interviewed an insurance guy holding a book full of checks he was ready to write to policyholders. That’s also what we get with the mix of the first and second kinds of coverage. No blame yet, but (as they say in social media reels) wait for it. Understanding, of course, will take the longest. Here’s a screen grab from Google Maps that will tell at least some of what isn’t much of a story yet (not much character or movement), but there is an expression for it what you see: the Wildland-Urban Interface (WUI). Read about it at that link. See it here, in the path of the Hughes Fire if it isn’t stopped:

And here is a wider view of the whole region:

With the exception of the Chiquita Canyon Landfill, all of the bare areas are housing developments. All of the housing and industrial developments used to be bare areas. And all of both used to be desert mountain grasslands and chaparral. Throughout the natural history of the area, at least since the end of the Pleistocene, burns from natural causes cleared off the land about every twenty-five years or so. And all the mountains were produced by earthquakes. I’ll write more about all of this in my next post.

View Details

Twenty-third in the News Commons series
Seventh on the #LAfires

Images from a Google image search for “LA fires aftermath.” Sources listed below.†Disaster coverage tends to go through four stages:

1. Live reporting. TV stations stop all advertising and go into round-the-clock coverage. Radio stations drop the feeds from elsewhere and go wall-to-wall with live reports. Newspapers drop their paywalls. Coverage by the best of them ranges from good to heroic. As stories go, they are all about the problem.
2. Human interest. The worst is over, so the stories go to human loss, resourcefulness, forbearing, kindness, and mendacity. Reporters on TV stand in front of some hellscape and talk to victims, heroes, or anyone they can find. This leverages the need for characters and their problems, with stories about how they survived, who or what they lost, always at least with hints toward movement forward.
3. Blame. This is all about character. Reporters are taught to seek the five W’s: Who, What, Where, When, and Why, sometimes appending an H for How. But since stories always require characters, Who is what matters most.
4. Coming to an understanding. While that’s the goal, and something nearly everyone wants, it’s provisional while the story continues. Also, full understanding, if it ever comes, will be at the end. And stories like the LA fires may never end, because there are contexts for them that may never change.

But that’s where we are now. In Stage 4. Here’s a Google search I just did:

Note that all of these stories are one to three days old. All of them are provisionally conclusive (meaning they still keep the story going). And all of them are less interesting than Stage 3: Blame.

I want to focus on that because blame makes story-telling—and story-generating—easy. Too easy.

That’s why Donald Trump—the best story-generator (and blame-placer) the world has ever known (and I mean this seriously)—wasted no time fingering Gavin Newsom:

Politifact spent 942 words explaining, among other things, that there was plenty of water, that a “water restoration declaration” never existed, that the smelt thing concerned water for elsewhere, and that what Trump said was wrong in other ways. But, as Ronald Reagan said, If you’re explaining, you’re losing. And Trump never loses, because that’s out of character. (Again, I mean this seriously. We’re talking stories here. The man is all-character, all the time.) And it is impossible for the media, which now includes everybody, not to participate in his story processes.

Of course, stories being what they are, Trump has hardly been alone in playing the blame game. Scott Galloway:

LAFD Chief Kristin Crowley took time out from fighting the fires to blame Mayor Karen Bass for cutting $17.6 million from the department’s budget. The department’s $895 million budget actually increased by $58 million as a result of the latest union contract. To get that higher pay to firefighters, the department reduced spending on equipment and training. The mayor’s response added to the drama, fueling rumors that the chief had been fired. Right-wing podcasters blame Fire Chief Crowley’s gayness, saying she was a DEI hire. Note: She has outstanding qualifications.

For all the good work being done at Stage 4, the urge to blame will never cease.

And we need some. Justice demands it.

What kind of justice? Well, there are many: retributive, distributive, restorative, procedural, social, environmental, economic, and so on. Of all those, retributive justice is what people want most and best understand. Perpetrators must be found, punished, and made to pay.

But starting with blame is too easy, too simple, often wrong, and always incomplete. Other factors matter. Conditions. Contexts. Black swans.

That’s why coming to an understanding is far more important, especially if we want to minimize or avoid the same kinds of disasters in the future. That’s what I’ll visit in my next series of posts.

Meanwhile, some of my open tabs:

• LA Times: How to help those affected by fires raging across Los Angeles County.
• KNBC/4: Asher Bingham, an LA artist, is drawing pictures of houses lost in the fire. “What I’m fascinated with is taking something from a picture and building a story to it,” she tells “So Asher picked up a pen and shared the artwork to Instagram with a simple offer to anyone that has lost a home in the LA fires. ‘I will draw your home for free… Three million views on that video later, there is now a waiting list of hundreds of requests.”
• Wired: Los Angeles Needs to Fireproof Communities, Not Just Houses.
• Business Insider via MSN: I’m a pilot flying a DC-10 fire bomber to battle the LA fires. This is what I’ve seen — and this is what needs to stop.
• Kwaai Events: Fire Resilience & Beyond with Personal AI Hackathon 2025 – $30K in Prizes.
• Washington Post: A key ‘weakness’ in L.A.’s wildfire strategy went unaddressed for years, Post probe shows.

† Sources via Google Image search: Reuters, NBC News, Marketwatch, ABC News, Hindustan Times, ABC, NPR, USA Today, The Indian Express, Nevada Appeal, YouTube, Commercial Observer, East Bay times, CBC, India TV News, Urban Land Magazine, Hope Standard, TMZ, Yahoo, Bloomberg, Instagram, and iObserve.

View Details

Twenty-second in the News Commons series
Sixth on the #LAfires

Facts don’t matter, or they matter much less than people think—Daniel Kahnemann

Facts don’t matter. What matters is how much we hate the person talking—Scott Adams

But facts do matter when life and death are on the line. Or when one is recovering from a life-changing situation. To help make the case for that, here are two collections of facts about the #LAfires:

A useful visualization of the CAL FIRE Damage Inspection (DINS) database for the Eaton Fire.A useful visualization of the CAL FIRE Damage Inspection (DINS) database for the Palisades fire.These are being updated on an ASAP basis by CAL FIRE (the The Department of Forestry and Fire Protection) as they inspect damage across the those two fires’ burned neighborhoods.

Here is a close-up of one section of the Eaton Fire map, with one moused-over pop-out:

The photo link in the pop-out goes here:

The house next door appears undamaged. That’s the green one on the map. By looking at Google Maps, I can see those houses are 3305 and 3310 North Marengo Avenue in Altadena. Note that the map has a search field in the top left corner. When one looks for an address (such as the first of those two), a pop-out appears with this:

“Show more results” and “Zoom to” lead to additional information. Would it help to have a list of all the affected structures, their addresses and conditions? Sure. Exactly seven years ago, after a massive debris flow destroyed much of Montecito, California (one zip code away from our house in Santa Barbara), I posted a list like that in this blog post. My source map was this one (now at the Santa Barbara County Fire Department):

Mousing over those dots popped up an address for each one, and I used those to hand-produce a master list with the addresses for all the structures that had been lost or damaged. The idea was to have a Web page where people could quickly see what may have happened to their house—or the house of somebody they knew, using a simple text search of a Web page. Maybe somebody will do the same thing here.

I bring this up in obedience to my mother’s prime command to my sister and me when we were kids: Make yourself useful.

And that’s what I hope I’m also doing with this post. It’s not just about sharing some maps. It’s about pulling facts away from stories, which I wrote about in my last post. To spare you a click, I said stories are the base format of human interest, and the main product of journalism—and that they have just three requirements: character, problem, and movement.

Stories serve many purposes, of course. One is persuasion. For more on that, check out Win Bigly: Persuasion in a World Where Facts Don’t Matter, by Scott Adams, of Dilbert fame:

The world where facts don’t matter is the digital one we live in now, alongside the physical one where all those homes were lost. In the digital world, the three requirements of stories can be used against journalism as well as by it. Toward both of those uses, I wrote Where Journalism Fails during the first Trump administration, and some of it bears repeating:

We have never seen Donald Trump’s like before, and may never again. His genius at working all three elements is without equal in our time—or perhaps any time. So please, if you can, set your politics aside and just look at the dude through the prism of Story.

Donald Trump spins up stories at least four ways:

1. Through constant characterization of others, for example with nicknames (“Little Mario,” “Low Energy Jeb,” “Crooked Hillary,” “Sleepy Joe,” “Failing New York Times”)
2. By finding or creating problems, and characterizing those too: “witch hunt,” “fake news,” “illegal ballots,” “Dominion-izing the Vote.”
3. By creating movement via the Roy Cohn and Roger Stone playbook: always attack and counter-attack, sue constantly, and claim victory no matter what. (Roy Cohn was a lawyer Frank Rich felicitously called “The worst human being who ever lived … the most evil, twisted, vicious bastard ever to snort coke at Studio 54.” Talk about character: Cohn was absolutely interesting. As Politico puts it here, “Cohn imparted an M.O. that’s been on searing display throughout Trump’s ascent, his divisive, captivating campaign, and his fraught, unprecedented presidency. Deflect and distract, never give in, never admit fault, lie and attack, lie and attack, publicity no matter what, win no matter what, all underpinned by a deep, prove-me-wrong belief in the power of chaos and fear.”)
4. By playing the ultimate alpha. That’s why he constantly calls himself the winner, and “loser” is one of his favorite epithets.
5. By de-legitimizing facts, truths, norms, and those who traffic in them. Key to this is accusing others of wrongs he commits himself. This is why he labels CNN and other news organizations “fake news” while raising falsity to an art form. Often, his accusations against others are a reliable tell of his guilt for doing the same thing.
6. As for movement, every new problem Trump creates or intensifies is meant to generate an emotional response, which is movement in itself.

Look closely: Trump’s news is deliberate, theatrical, and constant. All of it is staged and re-staged, so every unavoidably interesting thing he says or does pushes the last thing he said or did off the stage and into irrelevance, because whatever he’s saying or doing now demands full attention, no matter what he said or did yesterday.

There is genius to this, and it requires understanding and respect—especially by those who report on it.

You can call this trolling, or earned media coverage, meaning the free kind. Both are true. Comparing Trump to The Mule in Isaac Asimov’s Foundation and Empire also makes sense. (The Mule was a mutant with exceptional influence over the emotions of whole populations. It was by noting this resemblance that I, along with Scott Adams, expected Trump to win in 2016.)

This speaks of two big fails for journalism:

1. Its appetite for stories proves a weakness when it’s fed by a genius at hogging the stage.
2. It avoids reporting what doesn’t fit the story format. This includes most of reality.

My favorite priest says “Some truths are so deep only stories can tell them,” and I’m sure this is true. But stories by themselves are also inadequate ways to present essential facts people need to know because they exclude what doesn’t fit “the narrative,” which is the modern way to talk about story—and to spin journalists. (My hairs of suspicion stand on end every time I hear the word “narrative.”)

So here’s the paradox: We need to know more than stories can tell, yet stories are pretty much all people are interested in. Character, problem, and movement give shape and purpose to every human life. We can’t correct for it.

That’s why my topic here—a deep and abiding flaw (also a feature) of both journalism and human nature—is one most journalists won’t touch. The flawed nature of The Story itself is not a story. Same goes for “earned media coverage.” Both are features rather than bugs because they cause much of journalism’s success and debugging them has proven impossible.

Ah, but we can debug the context of journalism, which is the world of facts—especially facts in the physical world. That’s why I’m sharing these CAL FIRE maps. Besides being extremely useful, they highlight how much more needs to be compiled and put in useful forms, so the stories journalism tells can be as fact-based as possible. In an upcoming post, I’ll talk about a new time and history-based way to gather, compile, and archive facts that can maximize their usefulness to journalism in the present, when deadlines rule. If you want to learn a bit about this approach, I outline it in The Future, Present, and Past of News (eleventh in the News Commons series).

Next post: The Blame Game.

Bonus links:

• 2 Bay Area climate tech startups seek to help first responders in LA County wildfire fight features is a good story on its own, and features old friend Jackson Yip and the work his new company is doing. (NBC Bay Area)
• As Los Angeles burned, Latino immigrants rushed in to put out fires (LAist)
• Home Losses From the LA Fires Hasten ‘An Uninsurable Future’ (Time)
• Los Angeles Needs to Fireproof Communities, Not Just Houses (Wired)
• Santa Barbara Talks: LA Journalist Tony Pierce on Fires, Media, Uber Column (Noozhawk)

View Details

Two of these are not like the others. Just two. And one of those faces calls himself a “raging moderate.”Rush Limbaugh started it. Dozens of wannabes filled the rest of talk radio with it. Fox News took it to cable. And now Rushians rule the News Commentary roost on Apple Podcasts, and score well overall.

It’s not much different on Spotify:

Six out of the top ten.As Michael Tomasky puts it in The New Republic,

Once upon a time, the mainstream media was a beachball, and the right-wing media was a golf ball. Today, the mainstream media (what with layoffs and closures and the near death of serious local news reporting) is the size of a volleyball, and the right-wing media is the size of a basketball, which, in case you’re wondering, is bigger.

In case that doesn’t hammer the point home hard enough, he adds this:

Today, the right-wing media—Fox News (and the entire News Corp.), Newsmax, One America News Network, the Sinclair network of radio and TV stations and newspapers, iHeart Media (formerly Clear Channel), the Bott Radio Network (Christian radio), Elon Musk’s X, the huge podcasts like Joe Rogan’s, and much more—sets the news agenda in this country. And they fed their audiences a diet of slanted and distorted information that made it possible for Trump to win.

Let me say that again, in case it got lost: Today, the right-wing media sets the news agenda in this country. Not The New York Times. Not The Washington Post (which bent over backwards to exert no influence when Jeff Bezos pulled the paper’s Harris endorsement). Not CBS, NBC, and ABC. The agenda is set by all the outlets I listed in the above paragraph. Even the mighty New York Times follows in its wake, aping the tone they set disturbingly often.

And he barely mentions podcasting.

According to Newsweek, Joe Rogan‘s interview with Donald Trump was viewed over 26 million times in the 24 hours after it went up. And that was just the video. Rogan has 14.5 million followers on Spotify alone for his all-audio podcast.

We can see the reason why Spotify paid $200 million for Joe Rogan back in 2022. Hell, you could buy the whole AM band in New York for less than that today. Wait a few years and the FM band will be on the bargain shelf as well, because radio is being eaten alive on the talk side by podcasting and on the music side by streaming. (EMarketer has lots of numbers here.)

Fox News owns what’s left of news on cable. Also, since Trump won the presidency, viewing of MSNBC has tanked, while Fox News continues to grow—while stars of its shows are named to Trump’s new cabinet positions.

This is a very big thing: so big that we need a good label for the sum of all these popular right-wing new news and commentary outlets: one we can pose against what’s still called “mainstream,” but isn’t.

I suggest redstream media.

Spread the words.

View Details

If you’re tired of moaning (or celebrating) the after-effects of the U.S. election, or how all of us seem trapped inside the captive markets of Amazon, Apple, Alphabet, Microsoft, Meta, and other feudal powers, take in a talk about something constructive that’s nowhere near any of that, but serves as a model for economies and cultures everywhere: India’s Open Network for Digital Commerce, or ONDC.

Shwetha RaoThat’s what Shwetha Rao will be talking about next Tuesday, 19 November, at Indiana University and on Zoom wherever else you happen to be, noon Eastern Time.

The title is How Open Networks Impact Local Economies: Lessons from India, and here is how she puts it at that link:

In today’s digital commerce landscape, where major platforms hold significant influence, small businesses and local communities often face substantial barriers. Open networks are helping to shift this landscape by creating a more inclusive and accessible digital economy. A leading example is India’s Open Network for Digital Commerce (ONDC), which demonstrates how decentralized systems can boost digital access and economic opportunity. Unlike traditional platform-centric models, ONDC enables buyers and sellers to transact across various applications, breaking down barriers and fostering inclusivity. This government-backed initiative now connects over a million sellers with shoppers in 600+ cities, supporting small businesses and rural entrepreneurs.

This talk provides insights into the challenges and successes of scaling such open networks, underscoring the role of community engagement and sustainable growth models in driving equitable access and paving the way for a more decentralized digital future.

ONDC is a happening thing:

And, as far as I know, it isn’t happening anywhere outside of India. But it should. And, being open, it could.

The theme for our Beyond the Web salons this academic year is Think Globally, Eat Here: Local Solutions for Big Tech Problems. This solution might be the biggest so far.

As a salon, this will be short on lecture and long on conversation. So bring your curiosity and your questions. We’ll see you there.

View Details

In a vote for “Senior Superlatives” among his 36 classmates at Concordia Prep, Paul Marshall won in several categories. The yearbook staff, however, limited the Superlative distinction to one per student, and Paul chose to be recognized for his wit, which was boundless. He was also the editor-in-chief of The Prepster, our student paper, because he was the best writer. He was the best musician, playing the organ in our twice-daily chapel services, and sousaphone in the school band. He even taught sophomore biology when the teacher was sick for a few weeks.

Concordia Prep was a Lutheran seminary for high school boys and an academic correctional facility for lousy students like me. In his autobiography, AJ Ontko said I would have been voted Least Likely to Achieve, had that been an option. Yet, after an academically and socially miserable year as a sophomore, Paul recruited me to be his roommate for the following year, and we stayed together until Graduation. During that whole time, my life improved in every way.

Take music. Paul taught me volumes about Bach, Purcell, Händel, and other composers, such as Peter Schickele (P.D.Q. Bach) and Tom Lehrer. He tutored through performance, which involved runs by train to New York City, an hour train ride away. One especially memorable one involved Clarke & Purcell’s Trumpet Voluntary, performed on the massive pipe trumpets in the Cathedral of St. John the Devine. (A sample.)

Paul also taught me to believe in myself. From a post a couple of months back:

I remember a day when a bunch of us were hanging in our dorm room, talking about SAT scores. Mine was the lowest of the bunch. (If you must know, the total was 1001: a 482 in verbal and a 519 in math. Those numbers will remain burned in my brain until I die.) Others, including Paul, had scores that verged on perfection—or so I recall. (Whatever, they were all better than mine.). But Paul defended me from potential accusations of relative stupidity by saying this: “But David has insight.” (I wasn’t Doc yet.) Then he gave examples, which I’ve forgotten. By saying I had insight, Paul kindly and forever removed another obstacle from my path forward in life. From that moment on, insight became my stock in trade. Is it measurable? Thankfully, no.

After high school, Paul went on to distinguished careers as a liturgical historian, a parish pastor, a professor at the Yale Divinity School, Bishop of the Episcopal Church’s Bethlehem Diocese in Pennsylvania, and an activist for progressive causes (notably in his church). Our contacts through all of that were infrequent but always interesting and fun.

Of no importance but some interest is a moment we shared walking on a New York street at night with our young sons. One of the boys, looking at the moon, asked if was full. In unison and without thinking, Paul and I both replied, “No, it’s empty.”

In a likewise manner, we agreed to speak at each others’ funerals. Alas, we both missed that chance. Paul died of cancer on October 21, and his funeral was last Friday when I was in France.

Four days older than me, we were both 77. Here is the Church’s obituary.

My joke about mortality is that I know I’m in line for the exit, but I let others cut in. I wish Paul hadn’t.

Requiescat in pace, old friend. And forgive me for putting off our next meeting.

View Details

It used to be When.

But that was yesterday: election day in the U.S.

In California, where I voted (by mail), it’s still 10:30 PM., and the Blue folk are especially blue, because the whole thing is over. Trump hasn’t won yet, but he will.

I correctly predicted a Trump win in 2016, a loss in 2020, and a win again in 2024. That was, until Biden dropped out. Harris was a much stronger candidate than I—and nearly everyone—expected.

Here in Paris, I went to bed last night expecting a Harris win. When I got up at 4 AM, it was clear that she would lose. Badly. And now, at 7:45 AM, it looks like the GOP will take the Senate and perhaps also the House

I have always avoided politics on this blog, and even more on social media. But I have always had a lot to say. It is not, however, what others are saying, so don’t guess at it.

What I will say for now is that Democrats need a new story. Or a collection of them.

I’ve talked about stories before. This TEDx talk is one place. This blog post is another.

I’ll be expanding on points made in both. Meanwhile, coffee and croissants await.

View Details

While I am extremely pleased and grateful that 26 years of writing on Linux Journal survive online without being 404’d, I also realize that this condition probably won’t last forever. Also, some pieces are now missing their images and other graces. This is one of them. It is also one of my best, I think, Or at least one of the most important. This is a late draft, rather than the published final text, but it’s still good. Read on and enjoy—Doc

It starts here, in the heart of Long Island, a couple dozen exits east of Queens. I saw it with my own eyes in Mineola’s Public Schools, where kids, led by a nonprofit called kidOYO (“Kid-oy-yo”), are learning to program in different languages on different computers and operating systems, creating and re-creating software and hardware, with fun and at speed. Their esteem in themselves and in the eyes of their peers derives from their actual work and their helpfulness to others. What I saw was also sure to strip the gears of any system meant to contain them. Mineola’s schools were not among those.

OYO means Own Your Own, and that’s what these kids are learning to do. In geekier terms, they are rooting their own lives online. They’re doing it by learning to program in languages that start with Scratch and move up through Python, Java, C# and beyond. They’re doing it on every hardware and software platform they can, while staying anchored to Linux, because Linux is where the roots of personal freedom and agency go deepest. And they’re doing in all in the spirit of Linus’ book title: Just for fun.

With kidOYO, the heuristics go both ways: kidOYO teaches the kids, and the kids teach kidOYO. Iteration is constant. What works gets improved, and what doesn’t gets tossed or replaced. The measures of success are how enthused the kids stay, how much they give and get energy from each other, and how much they learn and teach. Nowhere are they sorted into bell curves, given caste-producing labels such as “gifted” or “challenged.” Nor are they captive to the old report card system. When they do take standardized tests, for example the college AP (advanced placement) ones for computer science, they tend to kick ass. (At that link we see how nearly all the 6th-9th graders who took the test passed, meaning they were ready for AP college work.)

kidOYO is the creation of the Loffreto family: Devon, Melora, and their son Zhen, who is now 12. What started as a way to teach computing to Zhen turned into ways to teach computer science to every kid. Their methods resemble how the Linux kernel constantly improves, stamping out bugs and iterating toward ever-expanding completeness, guided by an equal mix of purpose and fun.

Before we met, I had assumed, from Devon’s writing style and deep knowledge of stuff, that he was a gentleman perhaps of my own age, or even older. So I was surprised to find that he was not only a youngish guy, but a New York state high school champion baseball and basketball player who went to college on a sports scholarship. Also that he looked a stunt double for George Clooney.

I also knew what he and kidOYO were doing was important. But my mind wasn’t blown until I finally obeyed Devon’s invitation to see their approach at work. That happened on Groundhog Day in February. (An album of pictures I took on that visit is on the Linux Journal Flickr site here.)

Mineola is about as prototypical as a middle class New York suburban town can get: a 2-square mile village of about 20,000 in the center of Nassau County, which lays between Long Island’s north and south shore and is home to about 1.5 million people. The Mineola Free Union School District, however, is anything but typical. I’ve never seen a public—or any—school system with its feet equally planted in the digital and the physical worlds, or as eager to run forward in both. For example, all three schools I visited had created social and hacker spaces within their libraries. The books and the stacks still mattered, but so did the ability of kids to research, learn and teach together using computing and related gear, such as 3-D printers and programmable robots.

Standing in the Coding Center at the Mineola Middle School, surrounded by kids doing amazing stuff on their Chromebooks, Dr. Michael Nagler (@naglersnotions), superintendent for the district, gave me the backstory on how kidOYO got involved.

“Three years ago my wife signed our son up for a coding class these guys were putting on,” he said. “So I drive my son out there, and I’m watching what they’re doing, and I’m impressed. I ask Dev, ‘Why aren’t you in schools?’ He says, ‘The schools won’t talk to us.’ So I say, ‘Well you’re in luck, because I know a guy.’ We worked to help adapt their platform for schools, starting with ours. And I mean all of ours. We jumped in the deep end, starting with the little kids first and pushing it up through high school. And now we’re on this three year journey, so far, during which everything changes. Constantly. The little ones get the skills, and they roll up. Now I have to adjust my next level, and do it waaay faster than I have to with any other curriculum. Right now, for example, for the AP Computer Principles course in high school, they’re doing the learning path for (hatchcoding‘s) Hatch 1 and Hatch 2. Meanwhile, my sixth graders are already finished with it. So by the time these sixth and seventh graders get to ninth grade, my expectation is that every student in the district is taking AP Computer Principles. That’s going to replace our Exploring Computer Science class. And then we build in connections. So we’re doing Arduinos here in the Middle School’s sixth grade, and simultaneously in ninth grade in the high school. Then, as the younger kids move forward, we’ll change the ninth grade setup.”

Since Maker Faire New York is a great place for kids from everywhere to show off their maker chops, I asked Dr. Nagler if they had plans for that.

“We merge CS and computational thinking with making. We have a whole design and creative thinking framework tied to our mascot, the mustang. We make ways for the kids to conceptualize, design, iterate, prototype, test, refine, go, back, and build things.”

I asked, “How do you deal with the combination of kids who are already on this path, kids who want to come in and need to catch up, and eventually everybody in the school doing AP level work on computers? And beyond that, how does this whole thing catch fire?”

“A couple of ways. First, it’s not an elective. Here in Mineola, every kid has to do it. They also have to do it in their subject classes. So we tie a coding project to a curriculum project. Every grade has to do three a year. So we teach a language that way. We teach it independently the OYO way. And we teach it the formal way, cycling kids through CS classes, for example here in this room. As for catching fire, we’re Ground Zero. We succeed here and it spreads to other districts.”

“How do you all scale? I mean both what you’re doing and what kidOYO is doing?”

“I think we’re unique in that I don’t want it to be a formal class. I want CS to be ingrained in everything we do. In the process we’ll refine it and share it in ways that can be adopted by other districts. I’m a big open source guy. Sharing is key. So I’m taking the kidOYO platform and building an open computer science curriculum in social space. The beauty of their platform is that it lets me build an OER—Open Educational Resources—using their concept of learning paths, which we also work on together. Dev also built me a website that I can send to an organization I belong to called the League of Innovative Schools, which is a national organization. We can crowd-source content there. For example I built a sample curriculum unit. I can push that out to various states. By crowdsourcing we already have a ton of content on there.”

At this point Devon joined the conversation. “Tell Doc about MC².”

“Right. It stands for Mineola Creative Content, and it’s a video production studio, where we do fun learning videos, which are a basis for the learning pathway here.”

The opening text on the site (https://mc2oer.oyoclass.com/) explains, “This community showcases open educational content and other materials from the Mineola School District. Mineola is a suburban district located about 30 miles outside of New York City. Our school district is dedicated to the #GoOpen movement which supports sharing educational resources.

“It’s all about #OER—Open Educational Resources—and open source,” Dr. Nagler explained. “We use the videos here in the district, and also throw them out to the world where everybody can use them.”

Look up “Dr. Nagler” on YouTube, and you’ll find lots of them. He’s the star, as both a mentor and an animated character. There’s even one video where talks with his animated brain, bearing his signature goatee.

“An important context is that there is no central repository of educational materials in this country, because they’re all locked up by proprietary publishers. What we’re doing here is a way to get around that. And I have a lot of flexibility. I can market MC² as a school district entity, and not worry about all the copyright crap. It’s all made to share.”

I asked, “What happens to the world when these kids graduate into it?”

“They’re going to change the world. That’s clear. We’re also all dealing with astronomical change in the technical environment along the way. Constantly. This makes everything very hard to predict. Look at my 2019 high school graduates. They started Kindergarten in 2006. Even from just 2006 to 2009, the technology advances were astronomical. And then look what happened in the next ten years. Huge. So if I start planning now for where Kindergarten kids will come out at the end of the next twelve years, I’m already lost. But if I trust the process we have in place already, I’ll be fine. We’re driving it, and the kids are driving it too. It’s a constant cycle.”

I replied, “We also live in a world where giant companies are also working to contain those kids’ agency inside corporate silos. Some of those silos also spy on everyone constantly. How do you deal with that?”

“The common denominator is CS, and the flexibility within it. There’s freedom in that. I’m not going to force you to master, say, just one language. I’m going to get you on a platform where you can play with any and all of them, learn quickly and well, and apply whatever language you like toward building something. And because we’re merging the making and the coding, your next question will be, ‘What will this code do?’ The answer is, computational thinking will always push you toward solving problems. If you look at the big picture, content already is readily available to every kid. And content has always been our specialty, as a school. But with CS, the kids learn to master that content, in many ways. That’s key. Kids need to know and feel that they’re on top of things. That they Own their Own.

“What about curricular necessities: mandates that come down from the federal and state level?” I asked.

We’re still a public school, and we do have formalities. For example, here in New York every kid has to pass the state Regents Exam. We teach to that, but we also make sure there’s no way a kid graduates without exposure to computer science.”

“And you trust that’s going to equip them, once they’re out.”

“It’s more than that. Working with kidOYO, we’ve developed something that not only should be replicated everywhere, but needs to be. Here’s the important thing: there aren’t enough people who know computer science who can also teach it. So when you figure out a way to virtually do it, to scale the knowledge outward for everybody, it’s a big deal. The investment I make here probably cost me one teacher’s salary. But it scales to the whole district. To scale evenly, you can’t beat it. In fact it’s the only way to scale up computer science through schools, because the current credentialing system is too slow, and too top-down, and formal training is too slow, too far behind the curve. The kids and their mentors are moving too fast for that.

The biggest absence I saw that day was anything that looked like a bell curve. the system here clearly

What I saw here was a system that doesn’t have a bell curve, with A+ stars at one end and failures at the other. The system is made so every kid progresses, and every kid succeeds. A few minutes earlier, Melora explained, “We have no lowest common denominator, because everyone succeeds. There are twelve-year olds in this program that a 7th grade teacher wouldn’t look twice at in an ordinary classroom, but proves into her future as a profound programmer. And choice is key. When Dr. Nagler brought in this program, it wasn’t just for a select few kids. He wanted it to be open to everybody. And everybody has the ability to chose anything they want. It’s a totally different ecosystem than you’ll find anywhere else. And he’s gracious enough to reach out to other school systems to help them break down their own classroom walls. One of the things he preaches is that you have to believe. That’s a requirement of being on the cutting edge. The failing forward principle works for everybody too. It’s a model that works.”

The spirit of helpfulness and failing forward also fosters kids’ confidence that they can weigh in with solutions of all kinds. To show me how that works, Devon took me over to a table where Jordan Chaver and Connor Scott, a sixth and seventh grader, were working together on something.

“These two guys,” he said, “are your app builders. They came with us out to Stony Brook University for some of our software program there. Jordan pitched them on building an app on iOS, which he already knew how to do. But there was not a single mentor in the room that knew what he was trying to do—. legitimately, because in university CS they don’t want to work in a closed environment. So we transitioned the challenge over to the Web: to instead make a Web based app with database functionality. And that’s what these guys are building. And there isn’t just one app. There’s one they call social-emotional. And another called Class Dash. Asked to demo one, Connor pulled up a Chromebook, angled it toward me and said, “Let’s say you have a research paper. One that’s big and complicated. And you press Submit. Behind this you have something kind of like Dropbox, where you can share documents.”

Devon jumped in to explain, “They’re sharing all their class assignments in a firewalled white spaced environment where they don’t have access to their emails. So this is a simple way of sharing inside that environment.”

Connor continued, “You also have this five-character ID code. Jordan can type in the code, and he gets the same exact document. So can anyone else with the code. The idea is to share something with the class in a way that avoids complications. We’re also in a class play, Once Upon a Mattress, which is based on the Princess and the Pea. I’m the Price and Jordan is the Wizard. So Jordan made this schedule for all the performances, where you can buy tickets, and so on.” On his Chromebook, Jordan showed me his page with the schedule next to a graphic of the play’s title. He then gave Connor the five-digit code for access to the schedule, and it came up on the Connor’s Chromebook. (A picture of that is here.)

Connor again: “Right now I’m adding a way to lock a document. Let’s say that Jordan is the teacher and he finds a spelling error in my document. I’ll add a button you can click on and see if anybody has updated the document.”

Jordan said, “Let me tell you more about Class Dash, which I did for Stony Brook. It’s a student-teacher companion app. It has multiple uses, but the one that’s currently available is called Schedule. It covers notes, teacher, room, and supplies. I play drums, so drumsticks are an example of supplies. I also have Instant Messaging Teacher. The idea is, if you have a homework question, instead of emailing the teacher and getting a response the morning after, the teacher gets a push notification on their phone.” Class Dash will first hit the market in April as an iOS app. Other versions will come after that.

Joseph Malone, also twelve, is at the same table, hacking AI algorithms. Devon said, “Joseph here is spinning up his own virtual machine and generating algorithms to train his AI to run his scripts. He’s going into OpenAI, playing with AI algorithms, modifying them, and putting them to use. It’s neat stuff, and it’s also huge.” Melora told me Joseph is also helping out by volunteering a stream of challenges, solutions and badges for kidOYO courseware. “He does all the work himself, and makes it open and available to everybody.”

“We’re fully networked here,” Devon adds. “No need for back-end support.” Meaning no external corporate dependencies. kidOYO and its participants—learners (they aren’t called students), mentors (they aren’t called teachers), parents, schools—all work together, and for each other, as a “community of communities.” They’re also not moving at the speed of anybody’s clock, or anybody’s class. Though they’re sure to change the world, that’s not the goal. In fact, there is no long-term goal. The journey is truly the reward, and the journey is called the learning path. That’s what matters, and its not seen, or built, as a way to plow through the status quo. Even though that’s one of the things it does. Neither Mineola nor kidOYO want to burden kids with anything at all, other than the need to master their digital worlds, and to constantly advance their mastery.

The Middle School was the second one we visited in Mineola. The first was Hampton Street School, which is Pre-K to 6th grade. There we saw clusters of five and six year old girls and boys in the library’s Coding Center, hacking away on on school-issued tablets using Scratch, which is free (as in both liberty and cost), open source and runs on anything. They were also doing this both by themselves and collaboratively.

The way kidOYO works, all the kids know they are working both to expand their own skills and those of other kids as well. There are also rewards along the way, such as on-screen fireworks and badges. After a bit of working on their own, the kids’ work is shown on a screen for review by each other and Melora, their mentor. (The learner/mentor relationship is central to the kidOYO system, and practiced in the Mineola school system as well.) Devon later explained what was going on: “Melora was reviewing the process of getting challenge submission feedback from mentors, as well as introducing them to a new app called Sprite Editor that we recently released for kids to create art they may want add to their Scratch, Python or Web-based projects. Often it’s their own video game character art.”

When one boy failed a particular challenge, he embraced it, knowing that FAIL means “first attempt at learning.” Three girls came over to help the boy out. It was interesting to watch how they knew their job wasn’t to jump in with the right answer, but to help the boy learn what he didn’t know yet, so he would have the satisfaction of succeeding for himself. This was a far more sophisticated and mature than I would normally expect of kids so young. Instead I would have expected kids that age to show off what they knew, or to one-up each other. But that’s not how the kidOYO approach works.

Have you ever played the red/black game? I remember it as an exercise the human potential movement used to teach in weekend retreats and workshops to show there’s more to be gained from cooperation than from competition. The idea behind the game is to reprogram adults so they value cooperation at as well as competition. My point in bringing it up is that it’s hard to teach adults how to deal with each other in ways that are as empathetic, helpful and vanity-free as what I saw as normal behavior among these little kids.

At Hampton Street, Devon spent most of his time working with a second grader named William Ponce, who was clearly grooving on what he was doing. Later, Devon wrote to explain what was going on:

Here is William Ponce’s portfolio. Every kid has one. You can see badges he has earned. If you click on one of his “Mastery Badges” you will see the “Learning Pathway” that he navigated in earning it, displayed as evidence in the badge. Clicking on the micro badges in evidence will show you the badges earned on way to mastery badge.

Here was helping William earn his first Mastery Badge. Since we left that class, you can see he has earned two more already!!

Our third stop was Mineola High School, which has a fab lab and manufacturing facility. “We actually source product from them,” Devon told us on the way over. “For our store. Coding is the underlying infrastructure, but it’s applied everywhere.”

The Fab Lab is beyond impressive. It’s as big as a lumber yard and has lots of machinery, materials, and students making stuff. Ken Coy, who runs the lab, explained, “We do it all. Welding, electronics, coding, Arduino, hand tools, computer tools. We bring it all together here. We have all the old traditional tools you’d have in wood shop days—drill press, band saw, lathe, tools for sanding—plus all the new stuff that’s both manual and computer controlled. Large format printers, laser cutters…”

When I asked him about Linux, he brought me over to the shop’s Linux CNC (Computer Numerical Control) computer, running on Ubuntu and attached to a Probotix controller and a router. (Not a network router, but a powered workworking tool that cuts with bits or blades.) In the design class space, Andrew Woolsey (@WoolseyDesigns) showed me a CNC controlled laser cutter where the students were tracing, carving and printing out parts for art projects, signs and much more (which occupied students on adjacent tables). He also showed me a printer as wide as a piano churning out student portraits and posters of amazing quality, including ones for the Mineola Robotics Team (@mineolarobotics), which is apparently (judging from the awards and posters) always competitive. I don’t often see stuff that makes me wish I was fourteen again, but Mineola High School did the job. Walking around the fab lab, the library and the halls, I didn’t see a kid who wasn’t upbeat and engaged, or a teacher who wasn’t the same.

My mind blown, I followed up that one-day tour by asking Devon and Melora a lot of questions that amounted to an interview. Here it is.

DS: How much about Linux, including, eventually, operating in command line mode, do kids pick up, and at what stage? I also want to know how kids learn to be masters across platforms: from Linux to Mac, Windows, Android and iOS, because I saw and heard all of those discussed in the schools we visited.

DL: It varies by program type and mentor interaction. In schools, its limited. While schools are using Chromebook computers which can be dual booted into a Linux Ubuntu environment, this is generally disabled. Some schools will use Raspberry Pi’s that will allow for introduction to Linux OS, but its still rare. To some degree they are limited by the gear they get, and the familiarity with Linux of the mentors. But we support Linux with curriculum whenever it’s possible. And we do our best to push schools in the Linux direction.

In kidOYO programs we run in our own community, outside of school classrooms, Linux engagement is higher. Here it scales with complexity of lessons and the skills of students and mentors. This past semester, our program was hosted at Stony Brook University, and we had ten to sixteen year old students learning to create projects within Linux Ubuntu and GNU Linux OS, as well as Mac plus Windows by installing Windows sub-systems for Linux. They can set up their dev environment with basic shell commands, using Vim, gradle, flask, etc. Skills and proclivities on this path vary widely, but I will say that outside of game development skills specifically, most high level learners tend to be Linux proficient as well. It’s just a corollary I’ve observed over many years. For his Demo Day project to show parents, one kid built Ia multi-player version of Space Invaders in Java using libgdx on his machine running Linux Ubuntu. He did this at age eleven.

Since our platform runs on Linux, and my core team also serves as mentors to kids in these programs, we always enable students to see behind the scenes, and learn why we use certain tools, such as Linux and Vim. To a kid at first this stuff is not obvious, or necessarily relevant. Still, as they advance we show them how Vim works and how it is used, then create challenges for them to try it out. Some kids are tuned to this innately and once they touch Linux and root dev methods via command line, they never go back to the GUI. Others fight it, as you might expect, and prefer GUI computing. Once kids self-identify as interested/proficient in an area like this one, I try to support them sharing their knowledge and interests as they think others should also like learn. Here is one such example, created by 12 year old student who only uses Linux machines.

DS: What is it that makes kidOYO’s approach so different?

DL: Our main goal, which is to influence the way learners—not students—approach learning. This affects both students and teachers, as we create opportunities several ways: one in the context of indie classrooms that our organization leads, another in K-12 classrooms our mentors support, and another in the context of professional development, or PD, allowing teachers to self-provision their needs as a peer-group and as a school district. Our platform serves as foundation for STEAM (science, technology, engineering, art, math) learning across a diverse landscape of tools, methods, toys and concepts, all of which are about self-led learning, which goes beyond pedagogy.

Its not without a fight. There are plenty of pedagogy-centric thinkers in the ranks of teachers and administrators, and plenty of methods to support their priorities. For example, pedagogy-oriented thinkers tend to complain when we give kids real world tools like their own DNS (domain name) + hosting + editors. Instead they prefer limiting use-context of tools, so the kids can’t publish online and complete the feedback loop. Instead of letting kids build their own learning portfolio, they prioritize templated tools with limited functions and limited downstream value for independent learning.

DS: Tell me about your approach to business and open source, because I think it’s unusual.

DL: We think open source needs to be free as in freedom, or liberty. Not that a business based on it has to be free of cost. So we’re all about free code, but we charge for our services. And that’s how we’re bootstrapped. Our services provide nearly all our income. Parents and schools pay us because they get value out of what we do. Even though kidOYO is a nonprofit, that’s our business. And paying for value is part of what makes us a community as well.

Meanwhile, we’re up against corporate giants who may or may not be about open source, but they do give away lots of stuff for free, either outright or on a freemium model. Smaller edtech operations with superficially similar businesses also have a FREE come-on.

DS: But some of your services are free, no?

DL: Yes. With codeLI.org and FredXcoders (in Fredricksburg), all content is created by volunteer mentors, and the depth of engagement tends to be exploratory in nature. These communities run cost free live events, and curriculum resources are produced to support independent engagement. Where that model struggles is with sustained mentor engagement. That’s why we have a member:cost model.

In order to have sustained mentor feedback loops, kidOYO runs member:cost communities. Mentors in these are compensated for their support of student learning. This allows increased diversity in learning progressions for students, and has served as the way we’ve generated revenue for our organization, and funded building all these tools and relationships over the years.

Here we have an opportunity for the platform to support “franchise” community groups. Each franchise group can set its own cost, manage community content, and structure mentor-student memberships locally based on permissions and rules set by community owners. As a non-profit, this becomes a business model capable of provisioning multiple services under the membership definition. IRS rules allow for membership fees of up to $75/year without any reporting requirements.

At kidOYO, we are also about to unveil our direct-to-customer model of memberships, which will be priced at $75 per year, plus the cost of curriculum pathways chosen by members. An OYOclass.com account is always cost-free and allows for data access/ownership/downloading, plus project portfolio and badge portfolio. Joining a community has rules set by the “community owner.” So codeLI.org is FREE, but kidOYO has costs.

Membership in kidOYO will come with some additional benefits, such as discounted member pricing for our live Fall/Spring/Summer events and our swag store. We are currently building a OYOclass API to support this across domains .

Schools are currently paying $35 per year per account at a minimum of 1250 accounts. This represents our charity pricing, with zero margin, as an unfunded non-profit supporting tech and live personnel services. We are lowering the minimum to 500 at $50 per right now, and hoping we can do even better as our efforts scale. Our original goal with zero accounts using the platform was to get under $100, and our new goal is to achieve $20 per account. As a combination of tech plus live personnel services, plus data privacy/fiduciary under legal contract, I think this is strong value proposition.

DS: Unpack your corporate structure a bit more for us.

DL: kidOYO is a registered trademark for educational software and first put in use in 2006. It functions as DBA for NoizIvy.org, a 501(c)(3) nonprofit, which was founded in July 2001 to empower “entrepreneurial learning with technology through creation of products, services and programs in our local communities driven by peer-to-peer exchange and empowerment.” In that role we founded FredXcoders in 2011, in Fredricksburg, Virginia. We also started CodeLI.org in 2012, LI Maker Fest in 2015 (now official Eastern LI Maker Faire), launched the OYOclass.com platform in 2014 and in our first school district in 2015. That was Mineola. Now we’re approaching 75,000 members on Long Island in New York NY and preparing for national and international launch.

I’m the President of the company. Also a Developer and a Lead Mentor since 2001. Melora is the Executive Director. Also Creative Developer and a Lead Mentor since 2001. Bo Feng is a Software Engineer and our CTO since 2014.

Nine people work at NoizIvy.org currently. The three I just named are the core team. We also have four software developer who are also mentors, plus one maker engineer/mentor and one office manager, administrative assistant and mentor. Everyone in the company learns to code if they don’t know how already.

We also have one print book, self-published in 2006, and available online for twenty dollars.

DS: Tell me more about your business. What do you charge? How do you set your price points?

DL: We actually start with the seventh amendment of the U.S. Constitution, which says “where the value in controversy shall exceed twenty dollars, the right of trial by jury shall be preserved.” We all know that amendment as the one giving us a right to trial by jury. But what it actually presents is a twenty dollar bar against triviality, and a distinction between civil rights and market rights. There’s space there, under that twenty dollars, or the modern equivalent, for you to present a small civil case in a courtroom. Within that space is an existential gain in empowerment. It’s also where we have also evaporated our civil rights. So we look at our market, and mark up from that twenty dollars to thirty five dollars. That’s what we charge per student. Again, it’s pretty simple. And the student gets a lot of value for that money. So does the school, if they’re paying.

Now let’s go back to free-as-in-beer, or gratis-type free. Giant companies are taking huge advantage of free, with services consumers get for free while other value is being extracted from them. That’s one issue. Another is the Trojan Horse of free corporate goods and services to schools. Another, for us, is relevant to Linux and open source. In many cases schools are barred at the union level from accepting free services, at least in New York State. But our service isn’t gratis, so we’re cool with that.

DS: Have you taken in payments from any big companies?

DL: We have taken in ten thousand dollars in funding over past years from two corporate entities. Red Hat gave us five thousand, and a Long Island manufacturer, North Atlantic Industries,which makes electronics components used in military industry applications. That is it. We do everything on our own, in relationship with the community we serve. Parents and education leaders drive kidOYO. And the kids too.

DS: Is there a name for your category?

DL: There are two. One is #IndieEDtech. That’s the hashtag. The other is creative computing, which comes from the MIT Media Lab‘s Lifelong Kindergarten and and their Scratch perspective on CS.

DS: Is there a list of what we might call competitors here? Or just projects and companies kind of in the same business, or with similar goals?

DL: The FreeCodeCamp model exists in abundance, but it’s not really competitive. While it’s a free thing anyone can access, they spend most of their online real estate begging for donations. I’m not really down with the “begging” business model. Ask or beg for twenty dollars and its the same outcome. When you do that, you get trounced on by behavioral manipulation outcomes that distort the meaning of free-as-in-liberty initiatives. Codeacademy, CoderDojo and Code.org all have a different business approaches, but all use FREE-as-in-beer as a tool. When you look at the downstream relationships among their funding sources, however, more meaning is revealed. There’s a big donor status quo behind them.

indieEdtech and kidOYO stand apart in the creative computing camp. Nobody else has our advocacy for public-benefit technology and skills that individuals own root authority over.

For a long time, our messaging was unlike any other. Only recently has the messaging of Apple turned in our direction on the data privacy side, but still we’re still dealing with “corporate EDU” having different priorities than #indieEdTech. So we do compete, in different ways, with Apple, Google, Amazon, Microsoft and Salesforce, all of which have their own corporatized approaches to teaching kids computing. We compete with all of them as a small, or even tiny, non-profit. And we do go up against these behemoths every year, in every school, in every program offering we produce.

Because we’re independent, we can be very competitive. We are beating the big corps in direct contract negotiations. Their FREE approach versus our cost-with-integrity one go head to head, and we often win.

And, to be clear, we’re not always against what they bring. We’re glad to make use of the iPads and Chromebooks the schools get from big donors. But what we’re about is utterly independent of every behemoth’s businesses and goals for themselves.

DS: How about foundation or government funding?

DL: Something like 1.3 Billion got pledged pledged in support of CS education in 2018, and I expect kidOYO would be rejected by all of these sources of funding. I say that based on experience. We always get shot down. That’s because the goals, whether explicit or veiled, are for corporate expansion of influence and methods. Not for fostering general adeptness of independent learners. So we no longer bother.

DS: Tell me more about how you things are spreading geographically on Long Island, and how that models growth, both geographically and in other ways.

DL: You ask at a good time. We had a meeting with ten school districts yesterday. It involved superintendents, assistant superintendents of curriculum and instruction, directors of technologies, and lead teachers that focus on integrating kidOYO “code, make, own” in various parts of the middle school experience: grades five to eight.

The context was the first inter-district competitive hackathon on Long Island. Ten teams of eight students and coaches will be come together to engage in a social competition framed around “creative computing.” CS, engineering, making, art, game development, math, English, science and data-data-data will all be in the room during this event. And yet, “creative computing” among those peers will own the spotlight.

This is significant because in this area of learning—talent development and discovery, social creativity with imagination and empathy—stands out starkly against the historical basis of “computer science,” which is defined by its focus on research.

In so many ways, creative computing is enabling a different perspective on technology. Old school CS people do not present a developmental pathway I am excited about advocating to my kid, let alone yours. I find that too many people on this path put technology in front of humanity far too regularly. Can’t drive? Build self-driving cars. Can’t cook? Build UberEats. Can’t generate human empathy and personal imagination? Access sci-fi novels and support dystopian narratives of diversity in culture-producing outcomes.

On the other hand, creative computing is a paradigm shift away from that. It opens up a new context for the human-technology relationship: one that pursues framing on the basis of functional outcomes.

As we prep for this kind of event, we talk and discuss the creative computing perspective with education leaders that rarely get exposed to it otherwise. Every opportunity to bring this perspective to institutional players is a powerful step forward.

DS: Tell me more about your pitch. It must be interesting, because what you do is so radically different. And your website isn’t clear enough to me.

DL: Actually, what I have on site is misleading, by intent. Ive been throwing off competitors from swiping our concepts for years. I only have specific things on our sites that we can point at and clarify in personal conversations.

kidOYO.com only processes registrations for live events, which funded our operations for many years. OYOclass.com only sells a narrow description of what our platform can do, and sales only happen face-to-face. Our community of members and active users have a very unique and personal experience within our tools and with our community experience.

In essence, kidOYO is a creative computing and entrepreneurial learning management system. It is comprised of distinct components allowing it to have a multitude of market-based utilities and relationships. These include

• Personal learning tools, curriculum, mentor-feedback loops, and data-management capabilities over portfolios, micro-credentials, DNS, and web hosting configurations used by young learners engaging in “coding, making, owning” subject matter.
• Community infrastructure for entrepreneurial leaders bringing FREE & Cost-based service relationships to their business or charity.
• School infrastructure used for CS/Engineering/Entrepreneurship instruction and Professional Development, as well as for portfolios, micro-credentialing systems (which replaces report cards in some cases) and challenge-based learning.
• University infrastructure for Creative Computing/CS/Engineering/Entrepreneurship, providing every student root creative tools and data control across diverse domains of study, including a micro-credentialing system, portfolios, domains + hosting, and more.
• Mentoring system, for direct feedback loops useful in community education with focus on creative computing/CS/Engineering.
• Micro-credentialing platform, supporting open badges used in K-12, University, and community programs.
• Portfolio system, for use by students/teachers in documenting their own creative learning work for University admissions or workforce outcomes.
• Business model infrastructure—our most aggressive push, to change how community-based groups, businesses, schools and universities consider their evolving relationship with “customers” in a world where all participants own root value.

As you see, our biggest challenge has always been describing what we do. We do a lot, and it’s hard to say it briefly.

I am also fond of pointing out as a 501(c)(3) leader and developer of entrepreneurial outcomes, charity and entrepreneurship start the same way: when someone volunteers to solve a problem. We’re trying the build the creative infrastructure that supports those people, on a foundation that respects individuals as the root of community value.

DS: I’d like to know more about kidOYO’s background. I know you and Melora are from Long Island, and you’re here now; but you got your start with a toy business in Virginia. Tell me how you got from here to there to here again.

ML: I grew up in what many would consider an unconventional household. My Dad was a unique mix of tinkerer, artist, dare-devil and outright crazy person. I am not sure he was prepared to have a girl to be honest. That produced…well…me.

It’s relevant to point that out first, because his unconventional approach to parenting created someone who was never raised with gender “limitations.. I spent a good deal of my childhood immersed in projects in his shop out back. Although he was more than capable, he rarely created for the sake of practicality so there was never any fear of failure mixed into anything he or I did. The freedom to fail and laugh at those failures helped to shape me into someone who jumped into a any project I found interesting without worrying about the end outcome.

I had a tremendous amount of freedom, not being defined as a girl or a little kid in my environment. I could use any tool, any material, any method and make for the sake of making. I was trusted to fail through my own process of exploration when I was with my Dad. I was able to learn by doing and playing and that is how I approach my life still. I love to create new ways to learn through play. I studied Psychology at Stony Brook University, and when I took my first cognitive psychology class I was hooked. Really, everything I have done since then has been connected to the idea of teaching new skills to young brains.

I also learned along the way that I am a visual hands on learner. I think in pictures, so having the power to create digitally and with code has been so empowering for me. It gives me an unique ability to convey complex concepts to kids because I automatically turn problems/solutions into pictures.

DL: So I went to high school on Long Island. Melora and I met there too, though we didn’t get together for good until much later.

In high school, my aim for college was to play baseball and basketball. After a very successful time at that in high school, I hoped to get a scholarship at Columbia, but I got injured. I recovered well enough to get a scholarship to George Mason University, but there my interests became more academic and entrepreneurial, especially around technology.

That interest began with my first programming experience, which was on a Commodore 64 and soon after on an Apple IIe, when I was around nine and ten. Neither of my parents had any technical proclivities, but they put those things in front of me and I took advantage of them.

In high school, I discovered the magazine 2600 and how to hack into phone networks to make free calls using low-tech methods like a whistle to simulate tones unlocking long-distance calling capabilities. In terms of programming, I started in a Windows environment before Linux came around and I just had my own local environment to play with. I also ordered a CD-ROM on programming in C around that same time and played with that.

It wasn’t until 1992, when I entered college in Fairfax, Virginia that I started falling in love with programming on the Internet. Looking back, I was hacking around with ASP, PHP, HTML, databases… never learning in a formal setting, since none of this was covered in the CS classes I enrolled in. I was just playing, and trying to find resources that could help me better understand the dependencies and histories of languages, their ideal uses, and so on.

I learned everything by trial and error, finding others I could ask questions, and playing around with ideas. That was my learning method.

As the Web expanded, my learning expanded right along with it. I count myself lucky to have come of age at a time when the Web was doing the same, and people were making learning resources available online. As a lifelong entrepreneur, I am convinced that learning to code has been essential for me in learning to create in business. As an athlete, I self-taught my advanced skills, but never contemplated the role of failing forward and failing fast in skill development. I simply loved playing, and that was my focus.

As an entrepreneur and programmer, failing was not fun or playful. I had to discover something about my own attitude towards skill development that was crucial in sports and life in order to succeed in both. I never realized that it took personal courage and a productive attitude to overcome failure. I never realized that I had positive expectations sustaining my efforts through failures. I never counted how many shots I missed, or errant balls I threw. I just played with endless enthusiasm.

Becoming mindful of the process of learning to succeed by failing forward changed everything for me. It affected the speed I embrace in creative work: to start, fail, change methods, fail, iterate, fail, shift focus, fail, and keep moving forward with eyes on the objective, which is that I remain interested and enthusiastic about pursuing what I learn. None of this required me to be naturally gifted; it only mattered how I did what I did to improve.

So that is the root message of my own learning that I bring to all our programs: “Fail Forward, Fail Fast.

My non-profit interest traces back to my upbringing in a home that heavily leans left, with lots of social workers, economists, and university degrees in the ranks of my relatives. One of my first jobs was working for a local homeless shelter on Long Island delivering food to their shelters. I met women with Ph.Ds who were homeless, and who changed my perspective on what real poverty was. That influenced much of what I do. I am a big believer in empowering people, and helping them overcome the structural deficiencies that separate the haves from the have nots. At the root of my efforts is a constant interest in understanding entrepreneurial creativity, economics, and personal skill development—and helping people advance all of those.

I founded our non-profit in Virginia after attending the university, and then staying around Fairfax during the time when the Internet and the Web were entering the public sphere of interest and influence. My energies, throughout my entire adult life, have been entrepreneurial in nature, and the non-profit allowed me to bring technology skills and subjects into contact with kids and families in a powerful way. I simply volunteered to teach, to share ideas. And over time that work grew based on the interaction that those people were having with my ideas and methods.

OYO—own your own—has been the guiding philosophy behind our efforts. For young people and families, it resonates in a simple and powerful way. Kids get it immediately. Self-sovereign empowerment, personal data control, and skill development are all baked into of our methods and tools. From the beginning, our kids have always had control of their learning outcomes, their data, their methods, their paths of study, their voices, and their ability to make mistakes: to fail forward. Its all baked in. Kids follow what I talk about. When I visited the United Nations to discuss the role of identity in Human Rights, they knew why I was there. I went into schools and built projects with kids using Scratch and Python languages, explaining the the UN’s Universal Declaration of Human Rights and discussing how children are affected by such simple things as having a self-sovereign identity they truly own, and how administrative identifiers given to them is not the same thing.

The toy business grew alongside this. With Melora’s background in psychology, and our own son creating needs that drove solutions, sensory play products, construction play products and technology play were front and center every day. As a Dad, I tested my own ideas about the earliest ages different methods could develop an entrepreneurial mindset about skill development and participation in Society for kids as creative human beings. At age three, our son was delivering eggs from his backyard chicken farm to neighbors, setting prices, tracking expenses on crayon drawn charts, and learning that root authority in this life is personally created, as are the products and services that allow people to make money. Not jobs. That’s a concept that shows up much later. Only now, at age thirteen, and about to turn fourteen (the working age) has this become a subject of inquiry. On a foundation he owns, all possibilities exist for him to explore.

DS: We’ve talked about the effect of your work on kids, and Dr. Nagler talked about those kids’ effect on the world. He also talked a bit about the challenges his schools would face adapting to your methods, and how they tend to rocket kids upward in expertise faster than the existing system can handle. Now I’m wondering where you see this going for formal education?

DL: I see education splitting into two philosophical pathways.

One is old-school CS/E, with roots in research pedagogy. This has all the hallmarks of a lack of gender/race diversity and tends to attract specific types of students, led by traditional types of teachers. Most CS programs cannot support demand from students on University campuses today, and in K-12, the focus on AP CS testing requirements, as context of learning, remains broken. For example, where no computer is needed for final test. It’s all paper and pencil responses. But this is the default system, and it will persist, because it’s deeply institutional.

The other is creative computing in CS/E. MIT leads the way here, with forty percent of their undergrad population studying CS, according to a recent New York Times article. Harvard CS 101 also supports this path by starting students off with Scratch language. It also reports higher engagement by girls/minorities. What matters, as far as we’re concerned, is that creative computing works. It vastly outperforms old-school CS. And at some point, the market will move in the creative direction, because the demand will be there. And many of the kids in our communities today will supply that demand.

DS: What are the larger implications of that, outside the academy?

DL: Mainly ramifications for the future workforce. It will apply everywhere because CS applies everywhere. We live in a digital world now. You’ll see it in physics, applied math, arts, humanities, and social sciences. Anywhere the creative use of data and computing methods will make a difference.

And one of those differences will be empathy for local human conditions. This is sometimes lacking, radically, on the traditional path. We see this in all the ethical arguments against the abuses of people by many typical VC-funded Silicon Valley companies.

DS: We didn’t talk much about what you’re doing with other institutions outside Mineola. Can you give me a rundown of what’s happening in Stony Brook and other places? I want to get a sense of how your fires start and spread.

DL: So far, we are working with less than fifty percent of the hundred and thirty school districts on Long Island. There is plenty of potential, but many of the remaining districts here are not in a position to work with us, either due to their own budgetary planning and pension funding requirements, or due to lack of computing resources, such as laptops and computers for kids and teachers, or even functioning Wi-Fi. Those are real obstacles to progress.

The biggest obstacle is admin-level and teacher familiarity with this type of literacy. You can imagine the looks of confusion we encountered describing what we were doing in 2012. It’s getting better in 2019, but there is still lots of room for improvement. Setting accurate expectations is another challenge. Too often school leaders do not believe this type of learning is accessible to five, six, and seven-year-old kids, in a practical/meaningful way. So they stop waaayyy short of what kidOYO offers, choosing much lower level “digital literacy” pedagogies that make sense to a Facebook/Instagram user, with almost no context of functional literacy. In these cases, parents route around the problem of low-performing schools and bring their kids directly to our programs in large numbers. That can influence schools as well. We don’t need to push. The parents and kids do that.

At Stony Brook, we are actively discussing our own capability to support an “OYO University” self-led model of learning with mentor support on campuses that are struggling to meet the demand of students for this kind of learning. Stony Brook has been a great partner of ours for many years, with around six hundred fifty students enrolled in their Computer Science degree program. The demand from non-CS students to take CS classes is so high that they had to shut out students from enrolling in CS classes. And this is by no means unique to SBU. It’s happening all over the country and the world.

We are about to release OYO University platform deployments broadly as well. We just pitched SBU on our ability to support their 25,000 undergrad students starting in Fall 2019, and we’re looking for a first University partner to provide CS/E/Coding to all students on their campus.

Toward that, to date we’ve donated $125,000 to the SBU Foundation in support of a “Mentor Service Award.” That’s a lot for an unfunded non-profit. And this could scale with help.

This is just a fraction of what we talked about since our visit to see kidOYO at work. And I have to say that I want to be cautious about getting too enthusiastic. Reporters are supposed to be as objective as possible, and not to get emotionally invested in what they cover. But without emotional investment Linux wouldn’t be here, and neither would Linux Journal.

Marshall McLuhan taught that our tools are extensions of our selves, and that they shape us after we shape them. He also said every new medium “works us over completely.” That’s what’s happening in our new digital age, which is still very new.

Not long ago I was talking with Joi Ito, an old friend who runs the MIT Media Lab, about historical precedents for what we might call our species’ digital transition: the one by which we become digital as well as physical animals. Was it as big as the industrial revolution? Movable type? Writing? Speech? Joi said, “I think it’s the biggest thing since oxygenation.” In case you’re counting, that happened about two and a half billion years ago. It’s a big deal.

There’s a dystopian way of looking at what becoming digital does to kids. There’s also a utopian one. Both are polar extremes that surely won’t happen. But after watching these kids in Mineola learn, and help each other, and invent stuff both for fun and because it’s useful, and become so adept, so fast, at creative computing… well, color me optimistic. With these kids, and others like them, the world is on good hands.

View Details

“Agentic” is hot:

Source: Google TrendsAs an adjective, it is typically used as a modifier for AI. Hence this coincidence:

SourceL Google TrendsNot surprisingly, Gartner puts Agentic AI first among its Top 10 Strategic Technology Trends for 2025:

Source: https://www.gartner.com/en/articles/top-technology-trends-2025Here is one Gartner explanation, among many:

Theme No. 1: AI imperatives and risks drive organizations to protect themselves

Trend 1: Agentic AI: Autonomous AI can plan and take action to achieve goals set by the user.

• Business benefits: A virtual workforce of agents to assist, offload and augment the work of humans or traditional applications.
• Challenges: Requires robust guardrails to ensure alignment with providers’ and users’ intentions.

Naturally, most of the concern here is for Gartner’s corporate clients. But also note the bottom-line noun phrase: users’ intentions. Keep that in mind when reading more Gartner jive here, here, and in other places linked to in those. One sample:

Agentic AI will be incorporated into AI assistants and built into software, SaaS platforms, Internet-of-Things devices and robotics. Many startups are already marketing themselves as AI-agent-building platforms. Hyperscalers are adding agentic AI to their AI assistants.

Now, what about those user intentions? Wouldn’t it be good for corporate AI agents to have customer hands to shake that are also equipped with agentic AI? Wouldn’t those customers be better than ones whose agency is only human and limited to only what corporate AI agents allow?

Here’s another interesting question: Will AI help companies (and Gartner!) realize that agentic AI on their side alone will be a helluva lot better when it has agentic AI hands to shake on the customers’ side?

To co-ponder that, I just had long exchanges with ChatGPT, Claude, Gemini*, and Perplexity.ai. I liked my exchange with Claude the best. Here it is:

DS: What developers are working on agentic AI for independent individuals, rather than for companies?

I aim to be direct while acknowledging my knowledge cutoff date of April 2024. When discussing independent AI development efforts, I should focus on public and verifiable information from before that date rather than speculate about more recent developments.

Some relevant players in this space included:

• Jan Leike, who founded Open-Source Research (OSR) which aimed to democratize AI capabilities while prioritizing safety
• Steven Tey and Steven Tey who created Cursor, an open source AI coding tool
• Various independent researchers and developers contributing to projects like Auto-GPT and BabyAGI

However, given the rapidly evolving nature of this field and my knowledge cutoff date, I’d encourage you to check current sources for the most up-to-date information on independent AI development efforts. The landscape may have changed significantly since my last update.

Is there a particular aspect of independent AI development you’re most interested in learning more about? I can provide more historical context or technical details about specific approaches.

DS: What about Kwaai, or Consumer Reports?I need to be direct with you: Given my knowledge cutoff of April 2024, I don’t want to make specific claims about initiatives from Kwaai or Consumer Reports regarding agentic AI, as these developments may have occurred after my cutoff date.

Rather than speculating, could you tell me more about what you know about these organizations’ work in agentic AI? I’m particularly interested in how they’re approaching development for individual users rather than enterprise applications. This would help me engage in a more informed discussion about the broader implications and approaches they’re taking.

DS: Kwaai.ai is developing an open source operating system for personal AI. Applications that run on it are called “abilities.” Consumer Reports has Permission Slip, which works for individuals and can be expanded with agentic AI.Thank you for sharing those details! Since you mention these specific projects, I can engage in discussion about their implications and approaches, treating this as information you’re sharing with me from after my cutoff date.

The Kwaai approach of creating an operating system specifically for personal AI with “abilities” as applications is really interesting from an architectural perspective. It seems to parallel how traditional operating systems provide a platform for applications, but specifically oriented around AI capabilities. This could potentially solve some key challenges in personal AI:

1. Standardization of how AI capabilities are packaged and deployed
2. Consistent interfaces for how different AI abilities interact
3. User control over their personal AI environment
4. Interoperability between different AI capabilities

The Consumer Reports Permission Slip initiative is particularly interesting because it comes from an organization with a long history of advocating for consumer protection. Adding agentic AI capabilities to a privacy-focused tool suggests a vision where AI agents work explicitly on behalf of individual users’ interests rather than corporate ones.

Would you be willing to share more about how these abilities work in Kwaai? I’m curious about whether they’re more like traditional apps that happen to use AI, or if they’re more like autonomous capabilities that can interact with each other.

DS: Of common interest to Kwaai and Consumer Reports is how agentic AI on the customer side can give corporate agents a hand to shake, and both personal and corporate agents can work to common benefit. Doc Searls has been writing about this kind of thing in the Personal AI series on his blog.Ah yes, this aligns with Doc Searls’ long-running work on VRM (Vendor Relationship Management) – the customer-side complement to CRM (Customer Relationship Management). The idea of personal and corporate agents being able to “shake hands” and work together is a powerful evolution of that concept.

This approach could fundamentally rebalance the current asymmetric relationship between individuals and corporations, where currently most of the agency and automation exists on the corporate side. Some potential scenarios this enables:

1. Price and service negotiations where your personal agent represents your interests directly to corporate agents
2. Privacy management where your agent handles selective disclosure of personal information based on your preferences and the actual value exchange
3. Service customization where your agent can communicate your needs and preferences without requiring you to surrender all your data
4. Contract and terms of service review/negotiation where agents on both sides can work out acceptable terms

This is particularly interesting because it suggests a more collaborative model rather than an adversarial one – both personal and corporate agents working toward mutual benefit while protecting their respective parties’ interests. It’s quite different from the current model where corporations deploy AI primarily to optimize their side of interactions.

Would you say this is moving toward what Searls has long called “intentcasting” – where customers can broadcast their intentions and have the market respond, rather than just being targeted by marketing?

DS: It would include intentcasting. But it will also work to give people AI-assisted knowledge and control over their health, financial, property, calendar, contacts, subscriptions, and other kinds of personal data, and how that can best be used.Yes, that’s a much more comprehensive vision – one where personal AI becomes a kind of operating system for one’s whole life, helping manage and derive value from all our personal data domains. This approach could help solve several long-standing problems:

1. Data Fragmentation: Currently our personal data is scattered across countless apps, services, and institutions, making it hard to see the big picture or use data from one domain to inform decisions in another
2. Agency Asymmetry: Companies have sophisticated systems to manage their side of relationships with us, while we mostly just click “accept” on their terms and try to remember all our passwords
3. Missed Opportunities: Without good tools to manage and analyze our own data, we miss chances to improve our health, finances, time management, and other aspects of life

The vision you’re describing seems to be about giving individuals both:

• Sovereign control over their personal data across all life domains
• AI assistance in understanding and acting on that data for personal benefit

This could enable things like:

• Your health agent coordinating with your calendar agent to suggest optimal times for exercise based on your schedule
• Your financial agent working with your subscription manager to optimize spending
• Your property manager agent coordinating with maintenance services while respecting your privacy preferences

Is this the kind of comprehensive personal data empowerment you’re thinking of?

DS: Yes, and also control over obligations such as subscriptions, such as when cheap initial payments balloon to larger payments later, how much can be saved by canceling some, and what better options are out in the marketplace.Ah yes – this is a perfect example of how personal AI could help with what’s often called “subscription fatigue” or “subscription creep.” An AI agent could:

1. Track and analyze all subscriptions:
2. Monitor for price increases or “balloon payments”
3. Calculate total monthly/annual subscription costs
4. Flag unused or underused subscriptions
5. Alert about trial periods ending
6. Identify duplicate or overlapping services
7. Assist with optimization:
8. Compare current services with market alternatives
9. Model cost savings from different cancellation/switching scenarios
10. Identify better pricing tiers based on actual usage
11. Find bundling opportunities that save money
12. Handle the mechanics:
13. Track cancellation windows and requirements
14. Store and manage cancellation procedures
15. Document communication history with providers
16. Help navigate intentionally difficult cancellation processes
17. Keep records of all subscription-related transactions

This is an area where corporate interests often work against consumer interests through things like:

• Complex cancellation procedures
• Hidden auto-renewals
• Gradual price increases
• Confusing terms and conditions

Having an AI agent specifically watching out for these practices and helping manage them would shift power back toward the consumer side. Is this the kind of practical application you’re envisioning?

DS: Yes, that might be a first stage. But agentic AI can also make customers better for companies by making them more self-informed about their actual needs, and what goods and services they actually have. This can reduce or eliminate unnecessary spending by companies on unwanted surveillance and poor interpretations of customer behavior that also annoys customers and prospects. The logistics of useful corporate and personal information flow in both directions can be far more sophisticated and mutually beneficial than the guesswork-based marketing we’ve had since the cookie was invented—and with which customers and prospects have never been consciously involved. Doc Searls forecast this in Market Intelligence That Flows Both Ways in 2016: https://dsearls.medium.com/market-intelligence-that-flows-both-ways-e822fa74530This is a crucial insight – that personal AI isn’t just about defense against corporate practices, but about enabling more efficient and mutually beneficial market relationships. The current paradigm is incredibly wasteful:

1. Companies spend enormous resources on:
2. Tracking/surveillance infrastructure
3. Mining incomplete behavioral data
4. Predictive analytics based on limited signals
5. Targeting ads to people who aren’t interested
6. Managing customer churn
7. Handling support issues that arise from misalignment
8. Customers waste time and energy:
9. Being targeted with irrelevant offerings
10. Managing unwanted communications
11. Trying to communicate their actual needs
12. Dealing with mismatched services
13. Navigating complex systems not designed for their benefit

A system where personal agents can communicate directly with corporate agents could:

• Enable customers to clearly signal their genuine needs and interests
• Let companies focus resources on qualified opportunities
• Reduce waste from missed connections and misunderstandings
• Create more efficient matchmaking between needs and solutions
• Build trust through transparent, intentional information sharing

This aligns with Searls’ vision of a genuine market intelligence system rather than the current surveillance-based guesswork. Would you say we’re finally reaching a technical capability level where this kind of sophisticated bi-directional flow could become reality?

DS: “Reaching” might be a stretch. “Approaching” would be the better word.Ah yes, “approaching” is more accurate. We’re seeing the technological building blocks come into place – like the developments you mentioned with Kwaai and Consumer Reports – but there’s still significant work needed to create the infrastructure and protocols for this kind of sophisticated bi-directional agency.

The current state seems to be:

What we have:

• Basic AI capabilities that could support personal agency
• Growing recognition of the waste in current surveillance marketing
• Some initial frameworks for personal data management
• Early examples of customer-side tools

What we still need:

• Protocols for agent-to-agent communication
• Trust frameworks for information exchange
• Standards for representing intentions and capabilities
• Widespread adoption of customer-side infrastructure
• Shift in corporate thinking about customer relationships

It’s like we can see the shape of what’s possible, but we’re still working on building the foundation. Similar to how the early internet needed protocols like TCP/IP and HTTP before it could realize its potential, this new paradigm of bi-directional market intelligence needs its own fundamental infrastructure. Would you say that’s a fair assessment of where we are?

DS Yes, thanks!

You’re welcome! Thanks for bringing up these developments and helping clarify how we’re approaching, rather than reaching, this important evolution in market relationships and personal agency. Stay tuned to Doc’s blog

So maybe Claude can talk about some of this to Gartner, Salesforce, and all the other big Agentic AI arms dealers.

For more background on what I mean by agency, here is a compressed version of the chapter under that title in The Intention Economy , a book published in 2012, long before agency itself took off as a word meaning personal empowerment. Here is a compressed version of that chapter:

Trust thyself: every heart vibrates to that iron string.—Ralph Waldo Emerson

As precious as life itself is our heritage of individual freedom, for man’s free agency is a God-given gift.—David O. McKay

The ArgumentAgency is personal. It is the source of confidence behind all intention. By its nature the networked marketplace welcomes full agency for customers. So, because the best vendors are customer driven, there will be many more ways for both vendors and customers to thrive in the networked marketplace, and therefore also in the Intention Economy.

OriginalitiesWhen we use the word “agency” these days, we usually mean a party that acts on behalf of another one—such as an advertising, PR, real estate, talent or literary agency. But the deeper original meanings of agency are about acting for ones’ self. Here are the Oxford English Dictionary’s relevant definitions of agent:

1. a. One who (or that which) acts or exerts power, as distinguished from the patient, and also from the instrument.
2. He who operates in a particular direction, who produces an effect. Of things: The efficient cause.
3. a. Of persons: One who does the actual work of anything, as distinguished from the instigator or employer; hence, one who acts for another, a deputy, steward, factor, substitute, representative, or emissary. (In this sense the word has numerous specific applications in Commerce, Politics, Law, etc., flowing directly from the general meaning.)

Here are the OED’s first three definitions of agency:

1. The faculty of an agent or of acting; active working or operation; action, activity.
2. Working as a means to an end; instrumentality, intermediation.
3. Action or instrumentality embodied or personified as concrete existence.[ii]

In the Intention Economy, liberated customers enjoy full agency for themselves, and employ agents who respect and apply the powers that customers grant them.

WorkBusiness in the industrial world is complicated. Nobody can do everything, and that’s one reason markets work. Opportunity appears where something can be done that others are not doing, or are not doing well enough. Many of those opportunities are representational in the sense that agency, in the form of work, is handed off. We hire agents to work as extensions of ourselves.

But agency is personal in the first place. Having agency makes us effective in the world, which includes the marketplace. This raises some interesting questions. What does it mean for a customer to have full agency in the marketplace? Is it just to show up with sufficient cash and credit? Is it enough to be known as a good customer only within the scope of a company’s CRM system? That’s the current default assumption, and it’s woefully limiting.

Take for example my agency as a customer in the airline business. Most years I fly more than a hundred thousand miles. I bring to the market a portfolio of knowledge, expertise and intent (that is, agency) that should be valuable to myself and valuable to the companies I might deal with. I know a lot about the science and history of aviation, about many airlines old and new, about many airports and their cities, about geography, geology, weather, astronomy and other relevant sciences. I’m a photographer whose work is known within some aviation circles and to a small degree adds value to flying in general. I am also a fairly easy passenger to please. I require no assistance, have no dietary restrictions, show up early and don’t trouble airline personnel with rookie questions. I prefer certain seats but don’t freak out if I don’t get them, and I’m often one of the first to trade seats if it helps keep a couple or a family sit together on a plane. I am also willing to pay for certain privileges. Yet only the first item—miles flown—is of serious interest to the airline I usually fly, which is United. That I’m a million-mile flyer with United is unknown and uninteresting to all but that one airline.

Thus I have a measure of agency only within United’s system, and somewhat less than that with other members of the Star Alliance, to which United belongs. My self-actualization as a passenger is not my own, but that of a “1K” (100k mile/year) or whatever it says on my United Mileage Plus membership card in a given year. I am a high-value calf in their well-tended corrall. Its nice that my one-company status gets me some privileges with other airlines in the Star Alliance. But, since the IT systems of Star Alliance member airlines are not entirely communicative, those privileges are spotty. Asking any Star Alliance airline to be a cow for the calves of other airlines makes each of them groan.

The other airlines don’t know what they’re missing because they can’t know what they’re missing. All their heuristics are confined to their own CRM systems, plus whatever speculative “personalized” jive they buy from data mills. None of that milled data comes directly from you or me. If Delta buys data about me from, say, Acxiom, my agency is nowhere to be found. All the agency is Acxiom’s, and they’re not even acting as an agency for me in the representational sense of the word. I’ve offloaded no work on them at all, but they’re doing it on my behalf, sort of.

We can only do better if agency is ours and not theirs.

Self-actualizationTo consider what self-actualization means in the marketplace, it helps to examine the business sections of bookstores and libraries. They are full of books about self-actualization for companies and their employees; but there are few if any books for customers in the business section. There is nothing, yet, about what it means for you and me to be self-actualized as customers. If there were, what would they say?

In A Theory of Human Motivation, Abraham Maslow placed “The need for self-actualization” at the top of the list of human motivations—above survival, safety, love and esteem. [v]

Being customers is part-time work for most of us. (Even for shopping addicts.) Yet we bring more to market than fits into the scope of any seller’s current systems for ignoring all but a small range of signals from customers. How much more can customers bring, and vendors embrace, if the range of signals and actions on the customer side are freed up?

We can answer that question with another one: How big do we want markets to be?

In Here Comes Everybody: The Power of Organizing Without Organizations, Clay Shirky examines the effects of social networking tools, a disruptive fact of marketplace life for which the business world reached maximum thrall in 2011. (And with good reason: Facebook alone boasted 750 million users.) “None of the absolute advantages of institutions like businesses or schools or governments have disappeared. Instead, what has happened is that most of the relative advantages of those institutions have disappeared—relative, that is to the direct effort of the people they represent.”

While Clay’s focus is on the social, the personal remains more than implicit. Each of us has far more agency in the networked market than we could possibly enjoy in the industrialized marketplace. Since the two are becoming one, our agency will become valuable to industry.

So, thenWhen you limit what customers can bring to markets, you limit what can happen in those markets.

By the way, all of this stuff will be on tables at the Computer History Museum next week, at VRM Day (Monday) and IIW (Tuesday to Thursday).

*Credit where due: Only Gemini gives links to its dialogs. (Correct me if I’m wrong about that. Here’s mine as far as I went with it (before going farther with Claude).

View Details

Comet Tsuchinshan–ATLAS, flying toward its tail, away from the Sun.I shot the comet this time with a real camera: my Sony a7iv with a FE 70-200 mm F2.8 GM OSS II lens set at f3.5 at 135mm for 10 seconds on a shitty tripod I got at a thrift shop for $5. (I have good ones elsewhere.) This was at 8:40pm, just as the moon was rising behind my back and before dusk had turned to night with plenty of unwanted light from street lamps and the other usual challenges.

I couldn’t see it, but my iPhone 16 Pro Max did:

Using other shots I maneuvered myself to a place where the camera was in shadow from street lights and I could put the camera and tripod on the sidewalk while locating the comet to the right of that evergreen tree, so it was easy to aim in the general direction and get the shot.

If it’s clear again tomorrow night, I’ll go find a darker place at a later time and see what I can do.

View Details

Comet Tsuchinshan-ATLAS, more visible to the camera than the eye.Tonight was the first completely clear sky in a while, almost perfect for hunting Comet Tsuchinshan-ATLAS, which for a few more nights will be gracing our evening sky.

With a full moon high in the eastern sky, and plenty of light pollution from the town around me, the comet was hard to see. Fortunately, the camera in my new iPhone 16 Pro Max sees better than I do, so I was able first to find the comet in a photo of the western sky, and then go back outside (from the restaurant where we were eating—the Half Bottle Bistro) and aim the phone’s 5x lens at it. That’s what got me the shot above. Step through this album of shots to see how I got the phone to zero in on the comet while my eyes could hardly see it.

I found this guide from the Stamford Advocate very helpful for finding it as well.

View Details

Shot with a camcoder on a beach in the Caribbean during a 2001 Linux Journal Geek Cruise.This is from an email thread on the topic of digital identity, which is the twice-yearly subject* of the Internet Identity Workshop, the most leveraged conference I know. It begins with a distinction that Devon Loffreto (who is in the thread) came up with many moons ago:

1. Self-sovereign identity is who you are, how you choose to be known, to whom, based on reasons of your own. It’s something you own, just like you own your body.
2. Administrative identity is what organizations call you for their convenience (and secondarily, yours). We may call these labels “an ID,” but they are not who we are.

Here is what I wrote:

Humans have opposable thumbs. This makes them capable of tool use to a degree beyond immeasurable. Perhaps nothing, other than their brains, makes humans supremely capable as a species. It also makes them grabby. Try to teach Marxism to a three year old yelling “It’s mine!”

My mother’s favorite account of me as a small child was how I walked around constantly holding as many small toy trucks in my hands as I possibly could, unwilling to let them go. But this tendency was about control more than possession. I hadn’t yet learned to put my trucks in something I could carry around. I was unwilling to trust that a box or a bag was a working extension of my grabby little self.

I’m still a bit like that. “Your trucks” is what Joyce calls the electronic stuff I carry around. But I’m not alone. We conceive everything in terms that imply or involve forms of control, possession, or both. The English language, among many others, cannot get along without possessive pronouns: my, mine, our, ours, their, theirs, your, yours, hers, his. Even if ownership in the legal sense is not involved, responsibility is. Control is. When you drive a rental car, those are your wheels, your bumpers, your engine. You also think and talk about them with first person possessive pronouns.

Personal agency moves outward from that sense of control and responsibility over what is ours, including our selves.

This is why we need to start understanding personal identity, and how it works in the world, by recognizing that each of us is a self-sovereign human being. We are each, as William Ernest Henley put it in his poem Invictus, the captain of our “unconquerable soul.” Walt Whitman’s Song of Myself was a long-form explication of the same thing. (Which I wrote about way back in ’96, before there were blogs.)

This is not to deny that we are also profoundly social. But it is essential that we start with the personal.

Ownership is an abstract concept. So are rights. But we need both to operate civilization.

What makes ownership righteous is that it minimally abstract. We see this with the possessive pronouns “my” and “mine.” Again, this is rooted in our possessive nature, our opposable thumbs. We need to be self-possessed (and -sovereign), autonomous, and independent—before we are anything else, including our social selves.

In technical terms, it’s root.

So there ya go.

*But not the only subject. I’d say about half of the topics that come up at IIW are for topics other than identity.

View Details

Two in-wall structured wiring cabinets in our new garage.I need to install gear in these two structured wiring cabinets in the garage of the new house we are finishing. I don’t know exactly what to put in them and seek advice.

The installed cables are:

• Blue CAT-6a Ethernet cables go to outlets (RJ-45 jacks) in four rooms. Internet will come from the city’s new fiber optic system.
• Coaxial cables go to four possible TV locations. They will carry signals from the over-the-air TV antenna that will go on a pole outside. We will not have cable TV or Internet service.

Soon to be installed are:

• A coaxial cable from the TV antenna.
• A fiber cable from the street.

Both will come underground and up into the garage through a conduit between the back of the house and the hole (not visible) in the left side of the left cabinet.

So here is what I think I need:

1. A patch panel for the coaxial cables, so I can either distribute the TV signal or patch it through to one TV at a time.
2. An ONT (optical network terminal) to serve as the router between the fiber from outside and the four ethernet connections inside.

Here is what I don’t know:

1. What the fiber provider (GigabitNow Bloomington) will provide. I know they will need to terminate fiber from the street with an ONT that will go in one of the cabinets, but I don’t know whether they will provide, or I will need to get, a way to distribute service to the four Ethernet lines. I see ONTs sold online that have four Ethernet ports, but I don’t know if the provider will welcome my getting one or not.
2. Whether I will need an in-line TV signal amplifier. My antenna, which I’ve already built and tested, has an amplifier already. The question is whether I will need more amplification, especially if I am distributing to more than one room, and not just patching through one room at a time.
3. Exactly what the best practices are for attaching devices to the inside of these cabinets.

So that’s it for now. Thanks for any input you’ve got.

View Details

A 5x telephoto shot with my new iPhone 16 Pro Max.Holding the mic in this shot, taken with my new iPhone 16 Pro Max, is Mitch Teplitsky, a documentary filmmaker based in Bloomington, Indiana. Mitch has been reading this blog for the duration, and reached out when I showed up in town. The scene is the Pitchdox award event yesterday, which was by Hoodox at the Kan-Kan Cinema and Restaurant in Indianapolis. It’s one of the most delightful places I’ve ever been to: a great theater, bar, and restaurant, all in one. Here’s what my wife and I shared at the bar, between watching “We Strangers” and the event (thumbs up for both):

Frites, salad and two sliders at the Kan-Kan bar.That was also shot with the Pro Max. (In fact, after the Hoodox event yesterday, Mitch asked if I had the new phone with me, because he had read my post about it that morning.)

So here is my review after one day with the Max and two weeks with its smaller brother, the Pro.

Getting the phone, setting it up, and transferring all the data (~135 GB) was simple, fast, and easy at the Indianapolis Apple Store. Nice.

I love the big screen, which is easy for me to read and poke (which, with my imperfect eyes and warped fingers, is a big plus).

The camera performance is great for a phone, but let’s be clear: it isn’t what I get from my Sony a7iv mirrorless 35mm SLR and any of its excellent lenses. But that kit is heavy, requires a bag, and screams “that guy is taking a picture!” when I use it. Everybody has phones and shoots pictures with them, so with the Pro Max I’m just another shooter in a crowd.

What the Pro Max does extremely well is provide useful pictures, like the two above, under many conditions. It’s also nice to have that big screen for showing pix to other people.

My only ding on the Max is a small one: In a side-by-side comparison with the Pro, the Max’s screen is dimmer at high angles off straight-on. Not by a lot, but by some. I think the brightness is also slightly less uniform—at least with this Max. This is not something anyone would notice without comparing the two phones side-by-side and looking at both from a low angle. But I do think the difference is there.

To sum up, I think the Pro Max is ideal for anyone who wants the largest iPhone screen and doesn’t mind the added weight (which does come with a bigger and more capacious battery). If you don’t need the extra stuff the pro cameras do, I suggest going for the plain iPhone. I loved the Pro when I had it, and all you give up with that one is the telephoto lens. One pro tip: get twice the storage you think you’ll need, because you’ll provably end up needing it.

But,,,,, if you can, wait another year for the iPhone 17, which will reportedly launch a new generation. I couldn’t wait (my iPhone 11 was out of storage), but maybe you could.

View Details

iPhone 16 Pro and Pro Max. This is from Apple’s page for both. I think it’s exaggerating the difference a bit. Not sure, though.I got an iPhone 16 Pro twelve days ago. I have two more days to swap it for an iPhone 16 Pro Max, which will cost me $100 above the mint I already paid for the Pro with 1 TB of storage.

Why so much storage? I want to maximize storage because this thing is my main camera now, I shoot a lot, and I want a lot of archival photos on it as well. The iPhone 11 that this one replaced had 128 GB of storage and maxed out a long time ago. Frankly, I’d love it if Apple offered a phone with 2 TB of storage or more. I have 8 TB on this laptop, and my photos on it are already maxing it out.

The case for the Pro is that my hands are on the small side and gnarled with arthritis, and it fits nicely in my shirt and pants pockets. The case for the Pro Max is a bigger screen, which makes for easier work, for showing photos to others, for watching movies on planes, and other stuff like that. My eyes are also not getting better, and a bigger screen can help with that too. The battery on the Max is also bigger and lasts longer.

Earlier versions of the Pro Max also had functional advantages over the Pro models. For example, the oldest iPhone to run Apple Intelligence is the 15 Pro Max, not the 15 Pro. But functional advantages are gone with this generation. Other than the bigger size and slightly longer battery life, there is nothing the Pro Max can do that the Pro can’t.

Back to sizes.

The Pro Max weighs a little under 8 ounces, and the Pro a little over 7 ounces. That’s not much different to me. I’ve felt both and find them equally agreeable.

The Pro Max is 6.42 inches (163 mm) tall and 3.06 inches (77.6 mm) wide, while the Pro is 5.89 inches (149.6 mm) tall and 2.81 inches (71.5 mm) wide. So the difference is about a half inch in height and a quarter inch in width. Meaning that the Pro Max is a longer phone more than a wider one. That means the Max won’t really be hard for my hands to hold.

Here is something else to consider. I tend to keep a phone for several years:

1. 3G in 2008
2. 5 in 2012
3. 7 in 2016
4. 11 in 2019 (after I dropped the 7 into a pool while trying to rescue an insect)
5. 16 Pro in 2024

That averages about four years per phone. So I might want to get the best phone I can at the start of each stretch. But would the best phone also be the biggest phone?

So, should I go to the trouble of making the 150-mile round trip to my nearest Apple Store (on the far side of Indianapolis from Bloomington) and laying down $100 for the Pro Max?

Not sure. I welcome advice.

View Details

Fifteenth in the News Commons series.

This semester’s Beyond the Web salon series for the Ostrom Workshop and Hamilton Lugar School at Indiana University is themed Think Globally, Eat Here—Small Solutions for Big Tech Problems. I will give the opening talk, about the News Commons (subject of fourteen prior posts here) at noon (Eastern) next Tuesday, October 10. If youre in town, please attend in person. If not, join us by Zoom. Do that here.

Here in Bloomington we are pulling together a news commons. The plan is to prototype and prove locally what can apply globally for local news, starting with what Columbia Journalism Review called “news deserts” back in 2017—a label that has since caught on. There are many efforts toward seeding and watering these deserts, most prominently Press Forward, which is devoting $500 million to that challenge.

Bloomington is advantaged by not being one of those deserts, and instead having a talented pool of local journals, journalists, and organizations—including its legacy newspaper—all doing good work that could still be improved by putting to use some of the innovations described in earlier News Commons posts (and others like them), and by working together as a commons.

So join the conversation. I look forward to seeing you in the room or on the wall (because one whole wall is our Zoom screen).

View Details

Croissants (the edible kind) on display at Peets in Santa Barbara.Write once, publish everywhereDave turned me on to Croissant today. Looks good. I’d even be willing to pay the monthly fee to post once across Bluesky, Mastodon, Threads, and Xitter. But it appears to be only for iOS mobile devices. I have some of those (including a new iPhone 16 Pro), but I mostly write on a computer. So I’ll hold out for real textcasting, like Tim Carmody talks up here. Because why should you have to post separately at all those places? Why should you have to go to a place at all, when you’ve got your own devices to write on and distribute from?

A heading conventionI started curating my photos (e.g. these) in the last millennium using this date-based naming convention: YYYY_MM_DD_topical-text_NNN.jpg (where the NNNs are just sequential numbers and the file type suffix could be .jpg, .arw, .cr2, .png or whatever. Same for folder titles.) So, because I don’t want a new title for every day I do this, I’m adopting the same convention, at least for now.

Not fast enoughIn The End of Advertising, Michael Mignano says (in the subhead, and beyond), The business model that funded the internet is going away, and the open web will never be the same. He says AI is already killing it, by giving us answers to everything, and performing other handy tasks, without advertising to distract or annoy us. He also says AI services will attempt to invent ads, but that’s a losing proposition, mostly because it won’t work and we’ll hate it, but also because “content wants to be free.” (I submit that no art forms, ever, wanted to be called “content.”) I agree. I also agree that “Premium content will become even more premium.” He concludes, “the relationship between us and publishers will become much more transactional and direct. And we will feel it. Over time, it’ll be a new internet, and the open web will be a memory. Great content will still find a way to reach us, just like it always has. But we’ll look back on the first few decades of the internet as the golden age of content, when everything felt free.” Well, you’re reading some premium content right now, and it’s free. Thanks to what I do here, I can make money in other ways. We call those because effects.

View Details

The Ezra Klein Show, as it appeared on my podcast app this morning. It is now a wallcast.Would a blog be a blog if it went behind a paywall, or if you needed a subscription to read it?

Of course not. Blogs are on the open Web, and tend to stay there so long as they don’t move away from their original location.

Same should go for podcasts. “Wherever you get your podcasts” certifies the open nature of podcasting.

But now the New York Times is putting Ezra Klein’s podcast archives behind a paywall.

Never mind how icky this is on several grounds. Our challenge now is classification. We need a new noun for restricted ‘casts such as Ezra’s. I suggest wallcasts.

For subscription-0nly ‘casts, such as some on SiriusXM, I suggest paycasts*.

Bottom line: It can’t be a podcast if you have to pay for any of it, including archives.

By the way, I don’t care if my Times subscription opens the archives, as it does for print. By putting their podcast archives behind a paywall, the Times is changing the DNA of those casts. A wallcast is not a podcast. Full stop.

Spread the words.

SiriusXM’s paycasts include “SmartLess,” “Freakonomics Radio,” “The Joel Osteen Podcast,” “Last Podcast on the Left,” and “Andy Cohen’s Daddy Diaries.” They require a subscription to SiriusXM or its Podcasts+ service​. Some, such as “Marvel’s Wastelanders” and “Marvel/Method also require a subscription​. I’m not sure what kind. (FWIW, I’ve been a SiriusXM subscriber since 2005, but only listen to live subscription streams. I’ve never listened to any of its podcasts.) SiriusXM does have some shows in podcast form, however. Examples are “The Megyn Kelly Show,” “Best Friends with Nicole Byer and Sasheer Zamata,” and “Chasing Life with Dr. Sanjay Gupta.” I believe it also has some wallcasts*. For example, “SmartLess” episodes are on the open Web, but early access and bonus episodes are behind a paywall​. Or so it seems to me in the here and now. I invite corrections.

View Details

For live reports on recovery from recent Hurricane Helene flooding, your best sources are Blue Ridge Public Radio (WCQS/88.1) and iHeart (WWNC/570 and others above, all carrying the same feed). Three FM signals come from the towers on High Top Mountain, which overlooks Asheville from the west side: 1) WCQS, 2) a translator on 102.1 for WNCW/88.7, and 3) a translator on 97.7 for WKSF/99.9’s HD-2 stream. At this writing, WCQS (of Blue Ridge Public Radio) and the iHeart stations (including WKSF, called Kiss Country) are running almost continuous public service coverage toward rescue and recovery. Hats off to them.Helene was Western North Carolina‘s Katrina—especially for the counties surrounding Asheville: Buncombe, Mitchell, Henderson, McDowell, Rutherford, Haywood, Yancey, Burke, and some adjacent ones in North Carolina and Tennessee. As with Katrina, the issue wasn’t wind. It was flooding, especially along creeks and rivers. Most notably destructive was the French Broad River, which runs through Asheville. Hundreds of people are among the missing. Countless roads, including interstate and other major highways, are out. Communities have been washed away.

For following what’s happening there, I highly recommend listening to Blue Ridge Public Radio (WCQS/88.1) and any of the local iHeart stations (listed the image above). All of them are carrying the same continuous live coverage, which is excellent. (I’m listening right now to the WWNC/570 stream.)

Of course, there’s lots of information on social media (e.g. BlueSky, Xitter, Threads), but if you want live coverage, radio still does the job. Yes, you need special non-phone equipment to get it when the cell system doesn’t work, but a lot of us still have those things. Enjoy the medium while we still have it.

Item: WWNC just reported that WART/95.5 FM in Marshall, with its studios in a train caboose by the river, is gone (perhaps along with much of the town).

This is cross-posted on Trunkli, my blog on infrastructure.

View Details

These are eight (among many other) failed attempts to get ChatGPT and Copilot to create an image of posts in X (née Twitter), Linkedin, Facebook, Threads, BlueSky, Mastodon, and Instagram to flow or rain down from their clouds into a river of blogs.A watershed* is land that drains through a river to the sea or into an inland body of water. That’s what came to mind for me when I read this from Dave Winer:

If you want to help the open web, when you write something you’re proud of on a social web site like Bluesky or Mastodon, also post it to your blog. Not a huge deal but every little bit helps.#

I love the idea of using one’s blog (as Dave does) as the personal place to collect what one posts on various social media. So the flow, which we might call a
postshed (would post shed be better because it’s easier to read?) is from social media clouds into one’s own river of blog posts. (Maybe postflow would be better. I invite better nouns and/or verbs.)

So I’ll try doing some of that flow today. Here goes:

On X I pointed to Death as a Feature, which was my response six years ago to Elon Musk’s Martian ambitions. This was in response Doge Designer tweeting “Elon Musk is projected to become world’s first trillionaire. He said ‘My plan is to use the money to get humanity to Mars & preserve the light of consciousness,” to which Elon’s reply was, “That’s the goal.”

On Threads (and perhaps on other federated media, if that works): Besides Blue Ridge Public Radio bpr.org (which is great) what else should we tune in to hear what’s happening in the flooded parts of Western North Carolina?

On Facebook: Due to popular request (by one person, but not the first), I’ve put a pile of headshots up here: https://www.flickr.com/photos/docsearls/albums/72177720312529167/

*Wikipedia calls watersheds “drainage basins.” Not appetizing.

View Details

Fourteenth in the News Commons series.

Craig Burton’s view of the open source ecosystem.The main work of journalism is producing stories.

Questions following that statement might begin with prepositions: on what, of what, about what. But the preposition that matters most is with what.

Ideally, that would be with facts. Of course, facts aren’t always available in the pure form that researchers call data. Instead, we typically have reports, accounts, sightings, observations, memories, and other fuzzy coatings or substitutes for facts.

Craig Burton used to say that he discounted first-hand reports by 50% and withheld trust in second- and third-hand reports completely. In some cases, he didn’t even trust his memory, because he knew (and loved) everyone’s fallibility, including his own.

But still, we need facts, in whatever form. And those come from what we call sources. Those can be anybody or anything.

Let’s look at anything, and into the subset in archives that are not going away.

How much of that is produced by news organizations? And how much of what’s archived is just what is published?

I ask for two reasons.

One is because in this series I have made a strong case, over and over, for archiving everything possible that might be relevant in future news reporting and scholarship.

The other is because I have piles of unpublished source material that informed my writing in Linux Journal. This material is in the following forms:

• Text files on this laptop and on various connected and disconnected drives
• Sound recordings on—
  • Cassette tapes
  • Microcassette tapes
  • Sony MiniDisc disks
  • .mp3, ogg, and other digital files, mostly on external drives
• Video recordings on—
  • Hi-8 tapes
  • Mini-DV tapes

And I’m not sure what to do with them. Yet.

Open-sourcing them will take a lot of time and work. But they cover the 24 years I wrote for Linux Journal, and matter to the history of Linux and the open source movement (or movements, since there were many, including the original free software movement).

Suggestions welcome.

View Details

My father, Allen H. Searls, scored 159 on an Army IQ test when he re-enlisted to fight in WWII. But that didn’t make him a great fisherman, even though he loved to do it (and scored big with that striped bass, one of the few he ever caught.) Nor did it make him a good speller. (He was awful.) Or a good student. At fifteen he dropped out of high school and went to work as a longshoreman in New York City, commuting to work from New Jersey on a ferry, and then later working high steel construction on the bridge that obsolesced that ferry. But he was a great card player (almost always winning at poker), a math whiz, brilliant at making tools in his shop, and outstanding in many other ways (friend, husband, father) that can’t and shouldn’t be measured. Except maybe his looks. The guy was a 10.Now that AI is a huge thing, it’s worth visiting what intelligence is, and how we mismeasure it—for example, by trying to measure it at all.

I’ve been on this case for a while now, mostly by answering questions ab0ut IQ on Quora. My answer with the most upvotes is this one, to the question “What is considered a good IQ?” Here is the full text:

What makes an IQ score “good” is the advantage it brings. That’s it.

When I read the IQ questions here in Quora — “How high an IQ do I need to have to become a good hacker?” “Is 128 a good IQ for a nine year old?” — my heart sinks.

IQ tests insult the intelligence of everybody who takes them, by reducing one of the most personal, varied and human qualities to a single number. Worse, they do this most typically with children, often with terrible results.

It is essential to remember that nobody has “an IQ.” Intelligence cannot be measured as if by a ruler, a thermometer or a dipstick. It is not a “quotient.” IQ test scores are nothing more than a number derived from correct answers to puzzle questions on a given day and setting. That’s it.

Yet our culture puts great store in IQ testing, and many actually believe that one’s “IQ” is as easily measured and unchanging as a fingerprint. This is highly misleading and terribly wrong. I speak from ample experience at living with the results of it.

I grew up in the 1950s and ’60s, going a public school system that sorted kids in each grade by a combination of IQ test scores, achievement test scores and teacher judgement. (My mother taught in the same system, so she knew a lot about how it worked, plus the IQ scores of my sister and myself.) After testing well in kindergarten, I was put in the smart kids class, where I stayed through 6th grade, even though my IQ and achievement test scores fell along with my grades, which were worse every year.

In 6th grade the teacher insisted that I was too dumb for his class and should be sent to another one. My parents had me IQ-tested by an independent center that said I was still smart, so I stayed. By 8th grade, however, my IQ score, grades and achievement test scores were so low that the school re-classified me from the “academic” to the “general” track, and shunted me toward the region’s “vocational-technical” high school to learn a “trade” such as carpentry or auto mechanics. I was no longer, as they put it, “college material.”

So my parents decided to take me out of the public school system and send me to a private school. All the ones we visited used IQ tests in their admissions process. I did so poorly at the school I most wanted to attend (because a girl I had a crush on was already headed there) that the school told my parents I was downright stupid, and that it was cruel of them to have high expectations of me. At another school they forgot to time the test, which gave me a chance to carefully answer the questions. I got all of them right. Impressed by my score, the admissions director told my parents they were lucky to have a kid like me. But the school was itself failing, so my parents kept looking.

The school that ended up taking me was short on students, so my IQ score there (which I never learned) wasn’t a factor. I got bad grades and test scores there too, including the SAT. Luckily, I ended up going to a good small private college that took me because it needed out-of-state students and I was willing to commit to an early decision. I did poorly there until my junior year, when I finally developed skilled ways of working with the system.

Since college I’ve done well in a variety of occupations, and in all of them I’ve been grateful to have been judged by my work rather than by standardized tests.

Looking back on this saga, I was lucky to have parents who respected my intelligence without regard for what schools and test scores told them. Other kids weren’t so lucky, getting categorized in ways that shut off paths to happy futures, violating their nature as unique individuals whose true essence cannot be measured. To the degree IQ tests are still used, the violation continues, especially for kids not advantaged by scoring at the right end of the bell curve.

John Taylor Gatto says a teacher’s main purpose is not to add information to a kid’s empty head (the base assumption behind most formal schooling, ) but to subtract everything that “prevents a child’s inherent genius from gathering itself.”

All of us have inherent genius. My advice is to respect that, and quit thinking IQ testing is anything but a way of sorting people into groups for the convenience of a system that manufactures outputs for its own purposes, often at great human cost.

Here is Walt Whitman on inherent genius:

It is time to explain myself. Let us stand up.

I am an acme of things accomplished,
and I an encloser of things to be.
Rise after rise bow the phantoms behind me.
Afar down I see the huge first Nothing,
the vapor from the nostrils of death.
I know I was even there.
I waited unseen and always.
And slept while God carried me
through the lethargic mist.
And took my time.

Long I was hugged close. Long and long.
Infinite have been the preparations for me.
Faithful and friendly the arms that have helped me.

Cycles ferried my cradle, rowing and rowing
like cheerful boatmen;
For room to me stars kept aside in their own rings.
They sent influences to look after what was to hold me.

Before I was born out of my mother
generations guided me.
My embryo has never been torpid.
Nothing could overlay it.
For it the nebula cohered to an orb.
The long slow strata piled to rest it on.
Vast vegetables gave it substance.
Monstrous saurids transported it in their mouths
and deposited it with care.

All forces have been steadily employed
to complete and delight me.
Now I stand on this spot with my soul.

I know that I have the best of time and space.
And that I was never measured, and never will be measured.

Back to Gatto. Here is the full context of that pull-quote on genius. It’s from Dumbing Us Down: The Hidden Curriculum of Compulsory Schooling:

Over the past thirty years, I’ve used my classes as a laboratory where I could learn a broader range of what human possibility is — the whole catalogue of hopes and fears — and also as a place where I could study what releases and what inhibits human power.

During that time, I’ve come to believe that genius is an exceedingly common human quality, probably natural to most of us. I didn’t want to accept that notion — far from it: my own training in two elite universities taught me that intelligence and talent distributed themselves economically over a bell curve and that human destiny, because of those mathematical, seemingly irrefutable scientific facts, was as rigorously determined as John Calvin contended.

The trouble was that the unlikeliest kids kept demonstrating to me at random moments so many of the hallmarks of human excellence — insight, wisdom, justice, resourcefulness, courage, originality — that I became confused. They didn’t do this often enough to make my teaching easy, but they did it often enough that I began to wonder, reluctantly, whether it was possible that being in school itself was what was dumbing them down. Was it possible I had been hired not to enlarge children’s power, but to diminish it? That seemed crazy on the face of it, but slowly I began to realize that the bells and the confinement, the crazy sequences, the age-segregation, the lack of privacy, the constant surveillance, and all the rest of the national curriculum of schooling were designed exactly as if someone had set out to prevent children from learning how to think and act, to coax them into addiction and dependent behavior.

Bit by bit I began to devise guerrilla exercises to allow as many of the kids I taught as possible the raw material people have always used to educate themselves: privacy, choice, freedom from surveillance, and as broad a range of situations and human associations as my limited power and resources could manage. In simpler terms, I tried to maneuver them into positions where they would have a chance to be their own teachers and to make themselves the major text of their own education.

In theoretical, metaphorical terms, the idea I began to explore was this one: that teaching is nothing like the art of painting, where, by the addition of material to a surface, an image is synthetically produced, but more like the art of sculpture, where, by the subtraction of material, an image already locked in the stone is enabled to emerge. It is a crucial distinction.

In other words, I dropped the idea that I was an expert whose job it was to fill the little heads with my expertise, and began to explore how I could remove those obstacles that prevented the inherent genius of children from gathering itself. I no longer felt comfortable defining my work as bestowing wisdom on a struggling classroom audience. Although I continue to this day in those futile assays because of the nature of institutional teaching, wherever possible I have broken with teaching tradition and sent kids down their separate paths to their own private truths.

The italics are mine.

Knowing that we have industrialized education should help us understand how un-human AI “training,” “learning,” and “knowledge” actually are. (Side note: I love AI and use it every day. I also don’t think it’s going to kill us. But this post isn’t about that.)

Start with the simple fact that institutional teaching and its traditions don’t work for lots of kids. Today’s system is better in some ways than the one Gatto bested. then quit, but it’s still a system. If I were a child in the system we have today, I would surely be classified as an ADHD and ALD case,* given drugs, and put in a special class for the otherwise unteachable.

What worked for me as a student was one kind statement from one teacher: Pastor Ronald Schmidt, who taught English in my junior year. One day he said to me, “You’re a good writer.” It was as if the heavens opened. That was the first compliment I had ever received from any teacher, ever, through twelve years of schooling. I wish he were still alive, so I could thank him.

Fortunately, I can thank my high school roommate, Paul Marshall, who was (and still is) a brilliant writer, musician, preacher—and exceptionally funny. He was voted Class Wit (among other distinctions, which he declined, preferring the Wit one), and as a senior he substitute-taught biology to sophomores when their teacher was out sick. (These days he is the retired Episcopal Bishop of Bethlehem Pennsylvania. Before that, he was a professor at Yale Divinity School. There’s more at both those links.)

I remember a day when a bunch of us were hanging in our dorm room, talking about SAT scores. Mine was the lowest of the bunch. (If you must know, the total was 1001: a 482 in verbal and a 519 in math. Those numbers will remain burned in my brain until I die.) Others, including Paul, had scores that verged on perfection—or so I recall. (Whatever, they were all better than mine.). But Paul defended me from potential accusations of relative stupidity by saying this: “But David has insight.” (I wasn’t Doc yet.) Then he gave examples, which I’ve forgotten. By saying I had insight, Paul kindly and forever removed another obstacle from my path forward in life. From that moment on, insight became my stock in trade. Is it measurable? Thankfully, no.

Okay, back to AI.

As Don Norman told us in his salon here at Indiana University,

First, these machines are not intelligent. Second, remember the A in AI. A means artificial. They don’t work the way we do. And it’s a mistake to think they do. So let’s take a look at what they are. They are pattern-matchers.

I could let Don go on (which you can, at that last link), but there are a zillion explanations of what AI is and does, which you’ll find everywhere on the Web, and in answers from questions you can ask ChatGPT, CoPilot, Anthropic, Perplexity, Claude, and the rest of them. And all of them will be full of metaphorical misdirection. (Which Don avoids, being the linguist that he is.)

We may say an AI is “trained,” that it “learns,” “knows” stuff, and is “smart” because it can beat the most skilled players of chess and go. But none of those metaphors are correct, even though they make sense to us. Still, we can’t help using those metaphors, because we understand everything metaphorically. (To digress into why, go here. Or dig into George Lakoff‘s work, starting here. A summary statement might be, all metaphors are wrong, and that’s why they work. )

To be human is to be different from every other human, by design. We all look and sound different so we can tell each other apart. We also differ from how we were ten minutes ago, because we learn constantly.

So, to be human is to diverge in many ways from norms. Yet, being pattern recognizers and given to organizing our collective selves into institutional systems, we tend to isolate and stigmatize those who are, as we now say, divergent. Constantly recognizing patterns and profiling everything we see, hear, smell, taste, and touch is not just one of the many ways we are all human, but also how we build functioning societies, prejudices included. (As a side note, I am sure the human diaspora was caused both by our species’ natural wanderlust and by othering those who were not like us. We would fight those others, or just migrate away from them until we filled the world. Welcome to now.)

To sum this all up, just remember that when we talk about intelligence, we are talking about a human quality, not a quantity of anything. That machines test out better at pattern recognition than we do does not make them intelligent in a human sense. It just makes them more useful in ways that appear human but are not.

So have all the fun you want with AI. Just remember its first name.

*In my forties and at my wife’s urging (because my ability to listen well and follow directions was sub-optimal), I spent whole days being tested for all kinds of what we now call neurodivergent conditions. The labels I came away with were highly qualified variants of ADHD and APD. Specifics:

• I was easily distracted and had trouble listening to and sorting out instructions for anything. (I still have trouble listening to the end of a long joke.)
• On puzzle-solving questions, I was very good.
• My smarts with spacial and sequence puzzles were tops, as was my ability to see and draw patterns, even when asked to rotate them 90° or 180°.
• My memory was good.
• I had “synchronization issues,” such as an inability to sing and play drums at the same time. This also involved deficiencies around “cognitive overload,” “context switching,” multitasking, coping with interruptions, and “bottlenecks” in response selection. They also said I had become skilled at masking all those problems, to myself and others.
• I could easily grasp math concepts but made many mistakes with ordinary four-function calculations.
• I did much better at hearing and reading long words than short ones, and I did better reading wide columns of text than narrow ones.
• When made to read out loud a simple story comprised of short and widely spaced words in a narrow column, I stumbled through it all and remembered little of the story afterward. They told me that if I had been given this test alone, they would have said I had trouble reading at a first-grade level and I would have been called (as they said in those days) mentally retarded.
• My performance on many tests suggested dyslexia, but my spelling was perfect and I wasn’t fooled by misplaced or switched letters in words. They also said that I had mostly self-corrected for some of my innate deficiencies, such as dyslexia. (I remember working very hard to become a good speller in the fourth grade, just as a challenge to myself.)
• They said I did lots of “gestalt substitution,” when reading out loud, for example replacing “feature” with “function,” assuming I had read the latter when in fact I’d read the former.
• Unlike other ADHD cases, I was also not more impulsive, poorly socialized, or easily addicted to stuff than normal people.
• Like some ADHD types, I could hyperfocus at times.
• My ability to self-regulate wasn’t great, it also wasn’t bad. Just a bit below average. (So perhaps today they’d call me ADHD-PI, a label I just found in Wikipedia).
• The APD (auditory processing disorder) diagnosis came mostly from hearing tests. But, as with ADHD, I only hit some of the checkboxes. (Specifically, about half of the ten symptoms listed here.)
• My ability to understand what people say in noisy settings was in the bottom 2%. And that was when my hearing was still good.

I also apologize for the length of this post. If I had more time, I would have made it shorter.

Which, being a blog post, I will. Meanwhile, thanks for staying (or jumping) to the end.

View Details

In the late ’70s, I worked for a while at the Psychical Research Foundation, which occupied a couple of houses on Duke University property and did scientific research into the possibility of life after death. My time there was a lever that has lifted my life on Earth ever since, including many deep and enduring friendships.

Bill Roll ran the place then, and many fascinating characters passed through the PRF orbit. Eda and Lawrence Lashan, for example. Mac McDonnell. John Fetzer. One of the most memorable was Iris, a brilliant woman from Savannah with a strong personality, dyed red hair, and lots of talents. Her surname was pronounced “Mock,” but spelled with an “a” or two. (I think it was Maack.) She also mentioned occasionally that her brother was Ken “Hawk” Harrelson, the baseball player I remember best from his peak years with the Boston Red Sox. For many years since then, however, he has been the play-by-play announcer for the Chicago White Sox. Now 83, Hawk is still calling games for what will almost certainly be the losing-ist team in major league history.

So this morning, after I read “Hawk Harrelson spent 3 decades calling the White Sox. Now he can’t stand to watch” in the NY Times (sorry, paywall), I looked up “Hawk Harrelson” plus “sister” and “Iris” and landed on this 2018 page, which has this passage from Hawk’s autobiography:

“My sister was a heavy smoker who had died of lung cancer when she was only 40. I was so proud of what Iris had done with her life after such a tough start, having to get married at the age of 14. She wrote a few books and became a gourmet cook. She also learned to speak fluent German, Russian, and Spanish. She lectured at Duke University and at the University of Toronto. She became an accomplished pianist. She also dabbled in acting and landed a few holes on stage in New York. And she was an interior designer, having turned my penthouse pad into a beautiful home.“But we had a falling out several years before she died when I turned down her request to borrow $250,000. She had wanted to open a nightclub in downtown Savannah and I didn’t have that much cash at the time. Plus, I didn’t think her business idea was a good one. When I refused her request, she walked out the door and I never saw her again.“Apparently, she never quit smoking.”

While I’m not surprised to learn that Iris is gone (she was older than me, and I’m seventy-seven), it’s a shock to hear that she died so young, so long ago, and so full of talent and promise.I’m also not surprised that there is almost zero information about her on the Web, given that it was born after she died, and is a whiteboard as well. So maybe this post (titled with her birth name) will at least help make her more remarkable than I’ve made her so far.

View Details

Thirteenth in the News Commons series.

I grabbed the spottedhawk.org domain after hearing Garrison Keilor read this passage from Walt Whitman’s Song of Myself over Leo Kottke improvising on guitar:

The spotted hawk swoops by and accuses me.
He complains of my gab and my loitering.

I too am not a bit tamed. I too am untranslatable.
I sound my barbaric yawp over the roofs of the world.

Most of what I do is in deficient obedience to Whitman’s spotted hawk. Including this blog.

Early in this millennium, when it was as easy to blog as it later was to tweet, I blogged constantly. The stretch from 1999 to 2007 was blogging’s golden age, though we didn’t know it at the time. (My blog from that time is archived at weblog.searls.com.) My blog then was a daily journal, and in a literal way that made me even more of the journalist I had always been.

On that career side, I was also employed for all that time by Linux Journal. My name was on its masthead for twenty-four years, from 1996 to 2019. When LJ was sold at the end of that stretch, I left as editor-in-chief. After that, I was the host of FLOSS Weekly on the TWiT network. Both were paid gigs, and when the FLOSS Weekly gig ended last December, so did my long career in journalism.

And maybe that happened just in time, because journalism has since then acquired a taint. In this past weekend’s Cornerstone of Democracy newsletter, Dan Gillmor sources Josh Marshall of Talking Points Memo on the topic:

I guess I would say that as journalists our core mission is fundamental honesty with readers. That means always telling readers the truth, an accurate story as nearly as we are able to uncover it and understand it, as well as being transparent with the values, commitments and core beliefs we bring to the work we do. We believe in always being fair to everyone and everything we write about. Fairness is really only another permutation of accuracy. Balance is a construct applied after the fact that is often as not at odds with accuracy. A belief in democratic republicanism or civic democracy has always been at the core of what we do. It’s central to what stories we choose to focus on, it’s a value structure that permeates our organizational approach to what we do. I can’t speak for everyone at TPM. But as founder and still a guiding light, I think our understanding of what journalism is or should be is inextricably connected with democratic republicanism/civic democracy. I don’t think I would say we’re activists for democracy. But to me being on the side of civic democracy is inextricably connected to what we do and who we are. We’re on the side of civic democracy as much as we’re on the side of journalism.

I don’t want to label other journalists. But to the extent many other journalists don’t operate in this way, or understand their job this way, it’s because they work for publications whose business models simply aren’t compatible with this approach to journalism. What we now commonly call “both-sidesism” is rooted in the business structure of most contemporary journalism, specifically the need to have purchase across of wide ideological spectrum of the population.This is especially so in large corporate journalism because the need for scale and advertiser buy-in really requires that access to all parts or most parts of the political spectrum. In a hyperpolarized political culture when one side veers off the democratic rail that inevitably pulls a lot of that kind of journalism with it. I see that as fundamentally a structural reality. This goes back many decades, long before the current moment. It was more workable in a different political climate. But in this one that’s how it works. Journalists think they’re following core journalistic principles. But it’s driven really by business models.

That’s why now I just call myself a writer. Or a photographer.† Unless it’s to write a book (which typically pays little or nothing), to be a paid journalist today requires frequent or constant production of “content.” But I’d rather yawp, like I am now, here, or over at ProjectVRM, TrunkLine (a blog on infrastructure), or Customer Commons (which will in the next year become more important than everything else I’m doing).

All three of those involve work, but don’t pay. Same goes for serving as Chief Intention Officer of Kwaai.ai, a commuity of 600+ volunteers working on personal AI. (Check it out. Good stuff going on there.)

But before I give up on the journalist label, let’s ask Perplexity.ai to answer What is the purpose of journalism*? Here’s the answer I just got:

Based on the search results, the primary purpose of journalism can be summarized as follows:

1. To provide citizens with accurate and reliable information they need to function in a free society. This is considered the central purpose of journalism.
2. To inform the public about current events, issues, and developments happening in their communities and around the world.
3. To serve as an independent monitor of power and act as a watchdog over those in positions of authority.
4. To provide a forum for public criticism, debate, and compromise on important issues.
5. To convey context and help citizens understand the significance of events.
6. To set the tone for public discourse and help define community goals and values.
7. To empower citizens to make informed decisions about their lives and society.
8. To facilitate democratic processes by educating voters and inspiring civic engagement.
9. To support commerce by creating awareness about products and services.
10. To drive cultural transformation by connecting people to communities and ideas beyond their immediate surroundings.

Journalism is considered essential because it helps citizens navigate their lives, make important decisions, and participate effectively in democratic societies. It serves as a crucial source of verified information in an increasingly complex world, helping to separate fact from fiction and provide context to current events.

Is that what journalists are doing today? Was it ever? Really? All of it?

I don’t know. Mostly journalists write stories. If you’ve read Where Journalism Fails, or Stories vs. Facts, you know I think the story-telling imperative has its own problems.

Back in the early ’90s, when I was doing PR for a hot Silicon Valley startup, I asked a top reporter at one of the tech magazines why he didn’t want to see my client’s brilliant and charismatic marketing director. The reporter said, “He abuses the principle of instrumentality.” When I pressed the reporter to expand on that, he explained that everyone involved knows that reporters are used as instruments by whoever spins them. The “principle of instrumentality” is about knowing, and trying to ignore, the simple fact that journalism is instrumented in many ways. While Josh Marshall talks above about the instrumenting of journalism by business models, in this reporter’s case, it was by the persuasive charisma of a strong personality who wanted positive coverage.

I realized then that I wasn’t being hired at the same magazine (or at any publication before Linux Journal, and I pitched many) because I didn’t want to be an instrument. More specifically, they all wanted me to write sports stories about competing companies. “Apple vs. Microsoft,” for example. “Motorola vs. Intel.” I wanted to write about interesting stuff without favor to anybody or anything other than what seemed right, important, fun, or just interesting. Sports coverage of tech didn’t do it for me. Nor was any of the other usual stuff. Linux was a cause, however, so I worked to make my Linux Journal writing as non-evangelical as possible, though I did get credited with helping put both Linux and open source on the map.

Was I a journalist while working as an editor there? I suppose so, given that my work hit at least some of the ten items above. At least I thought of myself that way.

A difference today is that we are all both digital and physical beings. Here in the digital world (where I am now), anybody can publish anything, on many different platforms, including their own if they’re geeky enough to make that work. According to the Podcast Index, there are 4,262,711 podcasts right now. Instagram has over two billion users. Says here there are over three billion blog posts published every year, and over six hundred million active bloggers. (I suppose I am three of them.) The same piece says “Over 90% of blog posts receive zero traffic.” Many of those blogs are faked-up, of course, but it’s still clear that the world of online publishing is a red ocean, while Mastodon, Threads, Bluesky, Nostr, and the like are more like small rivers or bays than one blue ocean. (Links in that last sentence go to my tiny presence in each. I’m also still on Xitter and Linkedin, for what those are worth.)

So now I’m thinking about what principles, old and new, work in the digital media environment and not so much in the old analog one.

Here’s one: We’re past the era of “What’s on.”** Unless it’s a live sport or some other kind of scheduled must-see or must-hear event, you can catch it later, on your own time.

Here’s another: We don’t have to fill time and space with a sum of “content.” We don’t. Yes, it helps to have a schedule and be predictable. But it’s not necessary, especially if you’re being paid little or nothing.

Here’s another: The challenge now is building and maintaining an archive of facts, and not just of stories. I’ve written about this elsewhere in this series. Go look it up.

Another: Try to grab as many of those facts as you can before and after they turn into stories or don’t. This is what calendars are for. Even if nothing comes out of a meeting or an event that appears on a calendar, it’s good to know that something happened. And to archive that as well.

I also believe both of those principles are easiest to apply in local contexts, simply because there is a relatively finite sum of facts to work with locally, and facts still matter there. (Scott Adams tells us they don’t in the wider world. And he has a case.)

This is one reason I’m embedded in Bloomington, Indiana. We’re working on all that stuff here.

† My photos here and here on Flickr have about twenty millon views so far. The last peak was five thousand on Sunday. The top attraction that day was this shot of Chicago I got on a cross-country flight between Phoenix and Boston in 2011. That one photo has logged 26,159 views so far. All my photographs are CC-licensed and free to use, which is why over 4,000 of them are in Wikimedia Commons, a library of images used in Wikipedia. So thousands of those (it’s hard to tell exactly how many) end up in Wikipedia. Many more accompany news stories, such as this one from Lawrence, Mass, this one from a power plant, this one from a lithium mine, and all these from Chicago. And I put none of them in either Wikimedia Commons or Wikipedia. Other people do that. I just put the photos out there. Meanwhile, this blog maxed at a little over 300 views one day last week, but usually gets a dozen or so. My old blog ran at about five thousand a day, and sometimes ten times that many. To bring this back to the theme of this post, while I do a lot of photography, I don’t think of myself as a photographer. I take pictures. And I write. And I talk some. All are for the same purpose: to be useful and to make stuff happen. Good stuff, hopefully.

By the way, the bird at the top is a juvenile red-tailed hawk. There is no one species called a spotted hawk, so this one will have to do. I shot this bird a couple of months ago, perched on a 480-volt line in the alley behind our house in Bloomington, Indiana. I was looking to hear a barbaric yawp, but he, or she, failed me on that one.

*I first asked ChatGPT 4o and got a cliché’d answer with no sources. Perplexity gave me a longer answer, just as cliché’d, but with eight sources. For fun, go ask both and see what you get. Try Claude and Gemini too. No two will be the same. Some will be better, some worse.

**I’ve written about this, but haven’t published it yet. Stay tuned.

View Details

On the right is the high school yearbook picture of Allan John Ontko, one of my best friends during the three years we were classmates at what I half-jokingly call a Lutheran academic correctional institution—because that’s what it was for me. For most of the boys there, however, it was a seminary. Allan, then known to all as A.J. was one of the seminarians. He was also completely obsessed with pipe organ music and production.

When that picture was taken, in May 1965, A.J. was seventeen, a senior about to graduate, and building a pipe organ in his parents’ basement. The main parts of the organ were so large that a cinder-block wall needed to be removed so the thing could be extracted. It was also hand-built and tested, with thousands of drilled holes, thick webworks of wiring, and solder joints. All the pipes, stops, keyboards, and foot pedals were scavenged or bought used. I went with him on some of his trips around New Jersey and New York to obtain pipe organ parts. His determination to complete the project was absolute. Just as amazing was that he did this work on weekends, since ours was a boarding school in Westchester, New York, and his home was more than an hour’s drive away in New Jersey. His parents’ patience and moral support seemed infinite.

A.J. sold the organ to some church. That was the first step on his main path in life. Look up Ontko pipe organ and you’ll find plenty of links to his work on the Web. One of his companies, Ontko & Young, has fifteen listed organs in the Pipe Organ Database. His website, ontkopipeorgans.com, is partially preserved in the Internet Archive. Here’s one snapshot.

After high school, Allan (no longer A.J.) went to Westminster Choir College. In that time he continued building pipe organs, advancing his skills as an organist, and singing as well, I suppose. We both sang bass, though he could hold a tune while I could not. He had many amusing reports of his choir’s collaborations with the New York Philharmonic and did a brilliant impression of Leonard Bernstein’s conducting style. Allan could be very funny. I recall a list of fake organ stops that he and another organist friend (whom I am sure is reading this) created for a fake pipe organ design worthy of National Lampoon or The Onion. (Some stops were named after teachers. One I recall is the Roschkeflöte, named after Rev. Walter Roschke, who taught church history. Pastor Roschke’s nickname was Peach, because his blonde crew cut looked like fine fuzz.)

After that, Allan and I were only in occasional contact. I know he married twice. I met his first wife at a party at their apartment when he still lived in New Jersey. That was soon after college. Later he divorced, moved to Charleston, South Carolina, and remarried. Most of what I know about the Charleston period was that the organ-building continued, along with work composing and playing music.

A surprise came in 2011, when I got a friend request on Facebook from Olivia Margaret Ontko. I assumed that this must be a relative of Allan’s, since he came from a large Slovak family in New Jersey, and I attended some family gatherings there. When I went to Olivia’s Facebook page, I thought for a moment that looks kind of like Allan but… holy shit: that i*s* Allen. He was a woman now.

I accepted the request, and marveled at how well Olivia had gathered a large collection of supportive friends, and that she had become an active advocate for trans rights and acceptance of gender choices. For the next few years, we would occasionally comment on each others’ posts, and talk now and then on the phone. Olivia also created a LinkedIn account which is still there.

Our longest conversations were in June 2015, while I was driving to the 50th reunion of our high school class, and reporting on it afterward. Olivia was in Charleston then. She said she couldn’t afford to come and didn’t have much appetite for it anyway. Nor did the rest of the Class of ’65, except for me. I was the only one to show up at the reunion, outnumbered six-to-one by photos of dead classmates taped to one wall of the room. Fortunately, the room was not empty of people, because it was also the 50th reunion of the graduating class of the junior college that shared the same campus, and had absorbed our high school dorm and its classrooms the year after I left. Eighteen Concordia College alumni attended, including some guys who were seniors when I was a sophomore in the high school.*

Back to Olivia.

In a high, thin voice, she recounted for me how tortured she felt through all those decades as a female in a male body. She regretted not having been born at a time, like the present, when a child who knows their body is wrongly gendered can get the medical interventions required to grow up in the right one. She said she knew from a young age that she was a lesbian, because she was sexually attracted to girls as a kid, and then women as an adult. She also lamented that the term “transsexual” was not in wide circulation back in our high school years, when it mostly referred to pioneering work Johns Hopkins was doing at the time. So Allan repressed his urge to change sex until finally deciding to become Olivia. This was a deep and moving conversation because A.J. and I were so close in our high school years and yet I had no idea what he, or she, was going through. Finally, she told me she had written an autobiography, and that she would send it to me, hoping I might find a publisher. I told her I would do my best. This was a promise she repeated each time we talked after that.

Two years later, I got a surprising friend request from Allan Ontko on Facebook. The page for Olivia was gone. I accepted, and got this in response to an email:

I gave up on Olivia… the surgery involved in making the full change would have posed some serious risks and would have been totally out of my budgetary means (not to mention the cost of an entirely new wardrobe)… HA!

As we used to say in SC: Call me anything except late for supper…

Allan

Not long after that, he wrote this:

It is inconcievable that I will turn 70 this September – but for the nonce I would rather be alive and kicking. I have had a few medical problems – I am developing cataracts and double vision but they aren’t bad enough to require immediate treatment; I had total joint replacement of my right shoulder about 1 1/2 years ago; my Parkinsons is very much under control since about 2 1/2 years ago I was fitted with two brain implants (DBS).

And, I have moved since last May to Spangle WA; a little town of about 238 people which is 18 miles South of Spokane.

His address was a post office box. His phone was a cell.

My last contact with Allan was in a series of audio calls over Facebook totaling about an hour on the evening of December 17, 2020. Advancing Parkinson’s had made Allan’s speech was very hard to understand, and the call kept dropping because his connection was so bad. I did gather that he was in a facility of some kind, but I didn’t catch the name. Attempts to reach him after that were for naught.

A few days ago I heard from a mutual friend that some digging on the Internet brought news that Allan had died in 2022 of Covid. My own digging led me to a list of death notices in the Spokane Spokesman-Review, with this entry among them:

ONTKO, Olivia (Age 74) Passed away February 9, 2022

The same friend also told me that Allan had become a Seventh-Day Adventist. As it happens, Spangle is the home of the Upper Columbia Seventh-Day Adventist Church, and the Upper Columbia Academy, which is across the street. So I am reaching out to both.

In The Soul’s Code, James Hillman says each of us is born with as much of a destiny, calling, mission, or fate, as an acorn has within it an oak tree. He also says,

Reading life backward enables you to see how early obsessions are the sketchy preformation of behaviors now. Sometimes the peaks of early years are never surpassed. Reading backward means that growth is less the key biographical term than form, and that development only makes sense when it reveals a facet of the original image. Of course a human life advances from day to day, and regresses, and we do see different faculties develop and watch them wither. Still, the innate image of your fate holds all in the copresence of today, yesterday, and tomorrow. Your person is not a process or a development. You are that essential image that develops, if it does. As Picasso said, “I don’t develop; I am.”

For this is the nature of an image, any image. It’s all there at once. When you look at a face before you, at a scene out your window or a painting on the wall, you see a whole gestalt. All the parts present themselves simultaneously. One bit does not cause another bit or precede it in time. It doesn’t matter whether the painter put the reddish blotches in last or first, the gray streaks as afterthoughts or as originating structure or whether they are leftover lines from a prior image on that piece of canvas: What you see is exactly what you get, all at once. And the face, too; its complexion and features form a single expression, a singular image, given all at once. So, too, the image in the acorn. You are born with a character; it is given; a gift, as the old stories say, from the guardians upon your birth.

Allen/Olivia peaked when he/she was a successful organ builder. I also gather, reading between the lines of conversation and correspondence, that things went badly toward the end of that career. There were physical and mental issues: Parkinson’s and depression were just two. Perhaps finally, there was his/her singular and determined nature. You can see it in that high school photo. We—A.J.’s friends—could also see it in a photo one of us took of him when we were all playing around with shooting pictures and darkroom work. The photo was flattering. It nailed the A.J. we knew. He looked great. Yet he hated it. Tore it up and threw it away.

Did he do that because the photo wasn’t of his female self? For context, all I know is what Olivia told me half a century later: that being a teenage boy didn’t work for him. What worked was knowing that building pipe organs while also writing and performing music was in his/her soul’s code.

I do want that autobiography, though, if it exists. I hope someone reading this might help find it. It’s a long shot, but ya never know.

Allen/Olivia was an extremely unique, talented, and deep person, who deserves to be recognized and remembered for what he and she brought to the world.

*The college, called Corcordia (one of many Lutheran institutions by that name) was by then a four-year college. Five years later it too was gone. The campus, on White Plains Road in Bronxville, New York, is now part of Iona University. It’s quite lovely. Check it out if you’re in the hood.

View Details

Last week at DWeb Camp, I gave a talk titled The Future, Present, and Past of News—and Why Archives Anchor It All. Here’s a frame from a phone video:

DWeb Camp is a wonderful gathering, hosted by the Internet Archive at Camp Navarro in Northern California. The talk was at 9:30am, when it was still just 59°. It hit the 90s later.

In this post I’ll give the same talk, adding some slides and points I missed getting to in to my 25 minute window. Here goes.

For journalism, news is bad:

Revenue sources are going away:

Wages suck:

So does employment:

But it’s looking up for bullshit and filler:

So what can we do?

There’s the easy choice—

But bear in mind that,

News only sucks as a big business.
But not a small one.

For example, here:

Bloomington, Indiana. That’s where my wife and I are living while we serve as visiting scholars with the Ostrom Workshop at Indiana University. It’s a great place. (I’ve lived in many college towns, and this is my favorite, for many reasons.)

In 2017, Columbia Journalism Review produced an interactive map of America’s “news deserts.” One of them is Monroe County, most of which is Bloomington:

This was in error, because Bloomington did still have a daily paper then: the Herald-Times. And it is still does. The H-T persists in print and online. But, as “Breaking the News: The Past and Uncertain Future of Local Print Journalism” explained last year in a huge and well-curated exhibit at the Monroe County History Center,

the Herald-Times has shrunk quite a bit, while some “enterprising individuals” are taking up the slack—and then some. One they single out is Dave Askins of the B Square Bulletin:

Dave’s beat is city and county government. His “almost daily” newsletter and website are free, but they are also his business, and he makes his living off of voluntary support from his readers. More importantly, Dave has some original, simple, and far-reaching ideas about how local news should work. That’s what I’m here to talk about.

We’ll start with the base format of human interest, and therefore also of journalism: stories.

Right now, as you read this, journalists are being asked the same three words, either by themselves or by their editors:

I was 23 when I got my first job at a newspaper, and quickly learned that there are just three elements to every story:

1. Character
2. Problem
3. Movement

That’s it.

The character can be a person, a ball club, a political party, whoever or whatever. They can be good or bad, few or many. It doesn’t matter, so long as they are interesting.

The problem can involve struggle, conflict, or any challenge—or collection of them—that holds your interest. This is what gets and keeps readers, viewers, and listeners engaged.

The movement needs to be toward resolution, even if it never gets there. (Soap operas never do, but the movement is always there.)

Lose any one of those three and you don’t have a story.

So let’s start with Character. Do you know who this is?

Probably not. (Nobody in the audience at my talk recognized him.)

He’s Pol Pot, who gets a bronze for the number of people he had killed (with 1.5 to 2 million, he comes in behind Hitler and Stalin) and a gold for killing the largest percentage of his own country’s population (a quarter or so).* The country was Cambodia, rebranded Kampuchea while all the killing was going on, from 1975 to 1979.

The first we in the West heard much about the situation was in the mid-70s, for example by this piece in the May 9, 1975 edition of The New York Times:

The link here goes to the paper’s TimesMachine archives. Seeing it requires a subscription. We’ll discuss this more below.It’s a front-page story by Sydney Shanberg, who himself becomes a character later.

The first we (or at least I) heard about the genocide was sometime in 1976 or ’77, while watching Hughes Rudd on the CBS Morning News. He said something like this:

Wierdly, it wasn’t the top story. It was like, “All these people died, back after this.”

So I went to town (Chapel Hill at the time) and bought a New York Times. There was … something small on an inner page, as I recall.

But Time, the weekly news magazine, did cover at least the beginning of the genocide, in the April 19, 1976 issue. (By the way, all hail to Time for its open archives. This is a saving grace I’ll talk about later, and much appreciated.) Here is how that story begins:

Note how Prince Norodom Sihanoouk stars in the opening sentence. He’s there because he was a huge character. Go read about him. Pol Pot doesn’t appear at all. And the number of dead doesn’t show up until the second paragraph:

Coverage of Cambodia in the late ’70s remained sparse, considering the death count. Pol Pot didn’t show up in the Times until this was posted on page 164 of 446 in the massive Sunday paper on October 7, 1977:

The Times‘ most serious coverage of Cambodia was in opinion pieces. For example, an editorial titled The Unreachable Terror in Cambodia ran on July 3, 1978, and mentions Pol Pot in the third paragraph. Holocaust II!, by Florence Graves, ran on Page 210 of the November 26, 1978 Sunday Magazine. It begins, “They don’t talk about extermination ovens or about freaky medical experiments or about lampshades fashioned from human skin. But the Cambodian refugees do talk about forced labor camps, about “deportations,” and about mass executions.” Later she adds, “It’s a horror story which, for the most part, has gone unreported in the American press.”

It wasn’t reported because it wasn’t a story. Why:

1. No character of any interest (besides the deposed prince).
2. A problem that was gigantic but not of much interest otherwise.
3. Not much movement aside from a torrent of refugees into Thailand.

Then came this:

As Sydney Schamberg writes in the opening paragraph, “This is a story of war and friendship, of the anguish of a ruined country and of one man’s will to live.” As human stories about genocides go, the only one that might top Dith Pran‘s is Anne Frank‘s. It was so compelling that four years later it became a huge movie:

Now let’s go closer to home:

He’s a genius at all that stuff. And he keeps it going by making shit up too. You’re a lot more free to tell stories—and to move them along—if facts don’t matter to you. Here’s how I put it in Stories vs. Facts:

Here are another three words you need to know, because they pose an extreme challenge for journalism in an age when stories abound and sources are mostly tribal, meaning their stories are about their own chosen heroes, villains, and the problems that connect them: Facts don’t matter.

Daniel Kahneman says that. So does Scott Adams.

Kahneman says facts don’t matter because people’s minds are already made up about most things, and what their minds are made up about are stories. People already like, dislike, or actively don’t care about the characters involved, and they have well-formed opinions about whatever the problems are.

Adams puts it more simply: “What matters is how much we hate the person talking.” In other words, people have stories about whoever they hate. Or at least dislike. And a hero (or few) on their side.

These days we like to call stories “narratives.” Whenever you hear somebody talk about “controlling the narrative,” they’re not talking about facts. They want to shape or tell stories that may have nothing to do with facts.

But let’s say you’re a decision-maker: the lead character in a personal story about getting a job done. You’re the captain of a ship, the mayor of a town, a general on a battlefield, the detective on a case. What do you need most? Somebody’s narrative? Or facts?

Depends on what you need. Donald Trump needs to win an election. He’ll do that with stories, just like he always has. As characters go, Kamala Harris is a much tougher opponent than Joe Biden was, because she’s harder for Trump to characterize, and she has plenty of character on her own. And both make good stories because they’re in a fight against each other.

Things are different in places like Bloomington, where people live and work in the real world where there are potholes, homeless encampments, storms, and other problems only people can solve—or prevent—preferably by working together. In places like that, what should journalists do, preferably together?

To clarify the options, look at journalism’s choice of sources and options for expression. On both sides, there are facts and opinions. A typical story has a collection of facts, and some professor or other authoritative source saying something useful about those facts. Sometimes both come from the same place, such as the National Weather Service. So let’s look at different approaches to news against this background:

Here is roughly what you’ll get from serious and well-staffed news organizations such as The Wall Street Journal, The New York Times, the BBC, and NPR:

Mostly facts, but some opinions, typically in columns and on pages for that purpose.

How about research centers that publish studies and are often sourced by news organizations? Talking about Pew, Shorenstein, Brookings, Rand. How do they sort out? Here’s a stab:

Lots of facts, one official opinion derived from facts.

How about cable news networks: CNN, Fox News, MSNBC, and their wannabes? Those look like this:

Front to back, these are character-driven shows. They may be fact-based to some degree, but their product is mostly opinion. Facts are filtered out through on-screen performers.

Talk radio of the political kind is almost all opinion:

Yes, facts are involved, but as Scott Adams says above, facts don’t matter. What matters are partisan opinions.

Sports talk is different. It’s chock full of facts, but with lots of opinions as well:

That one is chock full of both facts and opinions.

Blogs like this one? Well…

In a general way, that’s what you get.

Finally, there’s Dave Askins. Here’s what he gives you in the B Square Bulletin:

Dave is about facts. And that’s at the heart of his plan for making local journalism a model for every other kind of journalism that cares about being fully useful and not just telling stories all the time. One source he consulted for this plan is Bloomington mayor Kerry Thompson. When Dave asked her what might appeal about his approach, she said this:

Dave sees facts flowing from the future to the past, like this:

The same goes for lots of other work, such as business, scholarship, and running your life. But we’re talking about local journalism here. For that, Dave sees the flow going like this:

Calendars tell journalists what’s coming up, and archives are where facts go after they’ve been plans or events, whether or not they’ve been the subjects of story-telling. That way decision-makers, whether they be journalists, city officials, or citizens, won’t have to rely on stories alone—or worse: their own memory, or hearsay (because there are no archives).

Dave has started work on both the future and the past, starting with calendars. On the B Square Bulletin, he has what’s called the Big Big Calendar. Here is how this month started:

And here are the sources:

Every outfit Dave can find in the county that publishes a calendar and also has a feed is in there. They don’t need to do any more work than that.

On the archive side, Dave has BloomDocs, which he explains this way on the About page:

BloomDocs is a public document repository. Anyone can upload a file. Anyone can look at the files that have been uploaded. That’s it.

What use is such a thing?

For Journalists: Journalists can upload original source files (contracts, court filings, responses to records requests, ordinances, resolutions, datasets) to BloomDocs so that they can link readers directly to the source material.

For Residents: Residents who have a public document they’d like to make available to the rest of the world can upload it to BloomDocs. It could be the government’s response to a records request. It could be a slide deck a resident has created for a presentation to the city council.

For Elected Officials: Elected officials who don’t have government website privileges and do not maintain their own websites can upload files to BloomDocs as a service to their constituents.

For Government Staff: Public servants who have a document they would like to disseminate to the public, but don’t have a handy place to post it on an official government website, or if they want a redundant place to post it, can upload the file to BloomDocs.

A future vision: “Look for it on BloomDocs” is a common answer to the question: Where can I get a copy of that document?

Dave also doesn’t see this as a solo effort. He (and we, at the Ostrom Workshop, who study such things) want this to be part of the News Commons I’ve been writing about here (this is the 12th post in the series). In that commons, the flow would look like this:

All the publishers, radio and TV stations, city and county institutions, podcasts, and blogs I show there (and visit in We Need Wide News and We Need Whole News) should have their own arrows that go from Future to Past, and from Calendars to Archives. And when news events happen, which they do all the time, and not on a schedule, those should flow in to archives as well. We need to normalize those as much as we can.

Which brings us to money. What do we need to fund here?

Let’s start with the calendar. Dave’s big idea here is DatePress, which he details at that link. DatePress would be something WordPress might d0, or somebody might do with WordPress (the base code of which is open source). I’m writing on WordPress right now. Dave publishes the B Square on WordPress. I’ll bet that the websites for most of the entities above are on it too. It’s the world’s dominant CMS (content management system). See the stats here and here.

On the archiving side, BloomDocs is a place to upload and search files, of which there are hundreds so far. But to work as a complete and growing archive, BloomDocs needs its own robust CMS, also based on open source. There are a variety of choices here, but making those happen will take work, and that will require funding. Archives, being open, should also be backed up at the Internet Archive as well.

Which brings us to money.

There are several possibilities, starting with funding Dave’s work so he can add functions and not do all of this himself.

Here are two aother ideas that aren’t the usual (advertising, subscriptions, subsidy).

The first is to drop the long-standing newspaper practice of locking up archives behind paywalls. (In Bloomington this would apply only to the Herald-Times). The new practice would be to charge for the news (if you like), but give away the olds. In other words, stop charging for access to archives. Be like Time and not the Times and nearly every other paper. (I first brought this up here in 2007.)

The second is to make EmancPay happen.

EmanciPay is an idea we cooked up in ProjectVRM at Harvard’s Berkman Klein Center in 2009. Here’s how the description begins:

Simply put, Emancipay makes it easy for anybody to pay (or offer to pay) —

1. as much as they like
2. however they like
3. for whatever they like
4. on their own terms

— or at least to start with that full set of options, and to work out differences with sellers easily and with minimal friction.

Emancipay turns consumers (aka users) into customers by giving them a pricing gun (something which in the past only sellers used) and their own means to make offers, to pay outright, and to escrow the intention to pay when price and other requirements are met. And to be able to do this at scale across all sellers, much as cash, browsers, credit cards and email clients do the same. Payments themselves can also be escrowed.

In slightly more technical terms, EmanciPay is a payment framework for customers operating with full agency in the open marketplace, and at scale. It operates on open protocols and standards, so it can be used by any buyer, seller or intermediary.

It was conceived as a way to pay for music, journalism, or what any artist brings into the world. But it can apply to anything. For example, [subscriptions], which have become a giant fecosystem in which every seller has separate and non-substitutable scale across all subscribers, while subscribers have zero scale across all sellers, with the highly conditional exceptions of silo’d commercial intermediaries. As [Customer Commons] puts it,

There’s also not much help coming from the subscription management services we have on our side: Truebill, Bobby, Money Dashboard, Mint, Subscript Me, BillTracker Pro, Trim, Subby, Card Due, Sift, SubMan, and Subscript Me. Nor from the subscription management systems offered by Paypal, Amazon, Apple or Google (e.g. with Google Sheets and Google Doc templates). All of them are too narrow, too closed and exclusive, too exposed to the surveillance imperatives of corporate giants, and too vested in the status quo.

That status quo sucks (see here, or just look up “subscription hell”), and it’s way past time to unscrew it.) But how?

The better question is where?

The answer to that is on our side: the customer’s side.

While EmanciPay was first conceived by ProjectVRM as a way to make live payments to nonprofits and to provide a new monetization method for publishers. it also works as a counterpart to sellers’ subscription systems in what Zuora (a supplier of subscription management systems to the publishing industry, including The Guardian and Financial Times) calls the “subscription economy“, which it says “is built on ever changing relationships with your customers”. Since relationships are two-way by nature, EmanciPay is one way that customers can manage their end, while publisher-side systems such as Zuora’s manage the other.

More sources:

• An Easy Way to Pay for Journalism, Music, and Everything Else We Like
• An Immodest Proposal for the Music Industry
• A citizen-sovereign way to pay for news — or for any creative work
• The New News Buisness

Far as I know, all the ideas you just read about are original, or close enough.

Let’s make them happen.

*Based on estimates. Nobody knows for sure. Here’s Wikipedia.

View Details

So I went to the ChatGPT website to ask a question and got hit with a popover promo for the new Mac app version. So I got it. Here is the dialog that followed my first question (which is boring, so we’ll skip it), copied over from the ChatGPT website, where I went after this frustrating encounter:

Can I move my chat history from the web to here?

ChatGPT said:Unfortunately, there’s no direct way to move chat history from one platform to another. However, if there’s specific information or conversations you’d like to continue or reference, you can copy and paste the relevant parts here, and we can pick up from there! If there’s anything specific you want to discuss or continue from a past conversation, just let me know.

You said:where here is my chat history?ChatGPT said:Your chat history here is session-based, meaning it exists only for the duration of our current conversation. Once the session ends, the chat history isn’t saved. However, I can remember key details or preferences across sessions if you want, and you can also start fresh conversations at any time.

If there’s something specific you want to continue discussing from a previous session, you might want to copy and paste that information here.

You said:That’s useless. Thanks anyway.ChatGPT said:I understand that can be frustrating. If you need any help or want to continue discussing something specific, I’m here to assist. Just let me know!

You said:I’m paying OpenAI for ChatGPT. I would hope that the app would offer advantages over the Web page.ChatGPT saidI can see why you’d expect some added benefits from the app version. While the app and web versions of ChatGPT share many of the same core functionalities, the app offers convenience for on-the-go use, such as notifications and a more optimized interface for mobile devices. However, both platforms currently have similar features in terms of chat history and session management.

If you have suggestions or feedback on features you’d like to see, sharing that with OpenAI could be helpful. They are continually improving the platform, and user feedback is a big part of that process.

Is there anything specific you’d like to see improved or added to the app?

You said:Yes. chat history.ChatGPT said:Your request for chat history is completely understandable, especially for those who want to revisit previous conversations, continue complex discussions, or reference past information. While I can’t implement that feature directly, your feedback is valuable.

I’d recommend sharing this feedback directly with OpenAI through their official channels or within the app’s feedback options. They often use user feedback to prioritize new features and improvements, so expressing your need for chat history could help influence future updates.

If there’s anything else on your mind or another way I can assist, feel free to let me know!

You said:Can I copy this whole dialog and save it as text?ChatGPT said:Yes, you can easily copy the entire dialog and save it as a text file. Here’s how you can do it:

1. Select the Text: Click and drag your cursor to highlight the entire conversation.
2. Copy the Text: Right-click on the highlighted text and select “Copy,” or press Ctrl + C (Windows) or Command + C (Mac).
3. Paste the Text: Open a text editor like Notepad (Windows) or TextEdit (Mac), then paste the copied text by right-clicking and selecting “Paste,” or by pressing Ctrl + V (Windows) or Command + V (Mac).
4. Save the File: Once the text is pasted, you can save the file by going to “File” > “Save As,” then choose your desired location and file name.

This will allow you to keep a record of the conversation for future reference.

You said:It only works for the latest answer.ChatGPT said:If you’re experiencing issues with selecting and copying the entire conversation at once, here’s a workaround:

1. Use the Browser’s “Select All” Feature:
2. On the web or in an app, try pressing Ctrl + A (Windows) or Command + A (Mac) to select all the text on the screen. This should highlight the entire conversation.
3. Then, press Ctrl + C (Windows) or Command + C (Mac) to copy the highlighted text.
4. Copy in Sections:
5. If the “Select All” method doesn’t work, you might need to scroll up and copy the conversation in smaller sections.
6. Highlight a section of the conversation, copy it, and paste it into your text editor. Then, repeat the process for the remaining sections.
7. Browser Extension:
8. If you’re using a browser, certain extensions or tools like “Evernote Web Clipper” or “Simplified Notepad” might allow you to clip the entire webpage or copy all text for easier saving.

Let me know if you encounter any issues, and I can try to guide you further!

You said:It still only works for the latest answer.

ChatGPT said:

If you’re only able to copy the latest answer, this might be due to the way the chat interface is designed, especially in some apps or browsers. Here’s an alternative approach you can try:

1. Screenshot the Conversation:* If you can’t copy the text directly, you can take screenshots of the conversation. Most devices allow you to take a screenshot by pressing specific keys:
2. Windows: Press Windows Key + Shift + S to select an area to screenshot.
3. Mac: Press Command + Shift + 4 to select an area to screenshot.
4. iOS/Android: Use the physical buttons on your device to take a screenshot.

5. You can then save these screenshots as images for future reference.

6. Use the Browser’s “Print” Feature:* If you’re on a browser, you can try printing the page to a PDF, which will capture the entire conversation.

7. On your browser, press Ctrl + P (Windows) or Command + P (Mac) to open the print dialog.

8. Choose “Save as PDF” instead of printing, and this will create a PDF file of the entire chat.

9. Use Developer Tools (Advanced Method): For advanced users:* In a browser, you can open the developer tools (F12 or Ctrl + Shift + I on most browsers), inspect the elements of the conversation, and manually extract the text from there. However, this is a more technical solution.

If these methods don’t work or you have further issues, let me know, and we can explore other options!

The UI is a small fixed-size window (like those chat windows you see on service sites), so screenshooting made no sense. And the other two options weren’t worth trying.

But when I went to ChatGPT on the Web, there was my history outlined in the left panel:

The top one was the dialog I just had, displayed in the Web interface. The app could have @#$%^ told me that was a feature.

But it didn’t, because it’s lame. So far.

View Details

I wrote for Linux Journal from 1996 to 2019, the final years as editor-in-chief. After ownership changed and the whole staff turned over. The new owner, Slashdot Media, agreed to keep the server up so nothing would be 404’d. I am grateful that they have kept that promise. I should add, however, that much of the archive seems to be missing—or so I assume because keyword searches on Google, Bing, and the site itself fail to bring up quite a few items. I do, however, have an archive of my own writing for the magazine. Since the cadence of this blog has fallen off a bit, I think a good way to fill open spaces in time is to re-publish columns I wrote for Linux Journal when the Linux operating system was still an underdog and the open source movement was still new and growing. This piece is one example: a small hunk of history that bears re-telling. (And forgive the rotted links, because the Web is a whiteboard.)

Linux For SuitsAugust 2001

Setting the terms

Back in May, Craig Mundie, Senior Vice President with Microsoft, gave a speech at NYU’s Stern School of Business that announced the terms by which Microsoft was cracking open — barely — its source code. He called the company’s new licensing model “shared source.” (I just wrote “scared source” by mistake, which tells you where my mind is going.)

The fact that Microsoft would start rapping about any kind of source code, and modify it with a fresh new euphemism — shared — caused immediate tissue rejection in the hacker cultural body. Leading hackers so certain of their own Truth that they refuse to appear on each other’s t-shirts were suddenly gathered around their collective keyboards to craft a single response that would say, in polite terms, “Embrace and extend this, dude.”

The result was an open letter published on Bruce Perens’ site (Perens.com), and signed by Bruce and a quotariat of free software and open source luminaries: Richard Stallman, Eric S. Raymond, Guido Van Rossum, Tim O’Reilly, Larry Augustin, Bob Young, Larry Wall, Miguel de Icaza and Linus Torvalds. (An anonymous coward on Slashdot wrote, “It’s like a human Beowulf cluster!”) While critical and challenging to Microsoft, its bottom line was inviting:

We urge Microsoft to go the rest of the way in embracing the Open Source software development paradigm. Stop asking for one-way sharing, and accept the responsibility to share and share alike that comes with the benefits of Open Source. Acknowledge that it is compatible with business.

Free Software is a great way to build a common foundation of software that encourages innovation and fair competition. Microsoft, it’s time for you to join us.

Mundie responded with a piece in CNET that framed his argument in terms of economics, manufacture and the PC’s popularity:

… this is more than just an academic debate. The commercial software industry is a significant driver of our global economy. It employs 1.35 million people and produces $175 billion in worldwide revenues annually (sources: BSA, IDC).

The business model for commercial software has a proven track record and is a key engine of economic growth for many countries. It has boosted productivity and efficiency in almost every sector of the economy, as businesses and individuals have enjoyed the wealth of tools, information and other activities made possible in the PC era.

Then he took on the GPL — the Free Software Foundation’s General Public License:

In my speech, I did not question the right of the open-source software model to compete in the marketplace. The issue at hand is choice; companies and individuals should be able to choose either model, and we support this right. I did call out what I believe is a real problem in the licensing model that many open-source software products employ: the General Public License.

The GPL turns our existing concepts of intellectual property rights on their heads. Some of the tension I see between the GPL and strong business models is by design, and some of it is caused simply because there remains a high level of legal uncertainty around the GPL– uncertainty that translates into business risk.

In my opinion, the GPL is intended to build a strong software community at the expense of a strong commercial software business model. That’s why Linus Torvalds said last week that “Linux is never really going to be a rich sell.”

This isn’t to say that some companies won’t find a business plan that can make money releasing products under the GPL. We have yet to see such companies emerge, but perhaps some will.

He added,

What is at issue with the GPL? In a nutshell, it debases the currency of the ideas and labor that transform great ideas into great products.

It would be easy to dismiss all this as provocation in the voice of boilerplate — or worse, as what one überhacker called “a declaration of war on our culture.” But neither of those responses are useful to folks caught in the middle — the IT professionals this column calls “suits.”

As it happened Eric Raymond and I were both guests on the May 14 broadcast of The Linux Show. When conversation came around to the reasoning behind open source rhetoric, Eric said, “We used the term open source not to piss off the FSF folks, but to claim a semantic space where we could talk about issues without scaring away the people whose beliefs we wanted to change.”

This has been an extremely successful strategy. Even if IT folks don’t agree about what “open source” means, it’s still a popular topic. Everybody who talks about open source inhabits its semantic space. But conversing is not believing. Remember Eric’s last seven words. These are still people whose beliefs we want to change.

Changing other people’s beliefs isn’t like changing your shoes. It’s like changing other people’s shoes. There’s a lot of convincing to do. Even if the other guy’s shoes are ugly and uncomfortable, at least they’re familiar. And in this case, familiar doesn’t cover it. In the IT world, Microsoft platforms, software and tools are the prevailing environment. Of course, we used to say the same thing about IBM. Things do change.

Did anything change when Craig Mundie tried to embrace and extend the conversation about source code? I think so. Mundie’s response to Bruce’s letter looked like a poker move to me. He said “we’ll see your source and raise you one shared“. What was our response? As a unit, nothing. the Beowulf Cluster broke up over the usual disagreemnets. It wasn’t pretty.

Perhaps it’s just as well. Two of the original signers told me they felt the letter was skewed “from the pragmatic to the ideological.” If so, Mundie read the letter well, because the ideology is exactly what his response attacked.

When this kind of thing happens, is the right choice to attack back?

We need to be careful here. When Microsoft decided to release a free browser, Marc Andreessen said “In a fight between a bear and an alligator, what determines the victor is the terrain. What Microsoft just did was move into our terrain.” He also called the operating system “just a device driver.” Today Microsoft is wearing alligator shoes.

And now the bear sits in our semantic space, talking business trash.

You might recall what I wrote exactly a year ago, when every mainstream publication was running stories about how the feds were going to break up Microsoft. I said Microsoft was going to beat the rap by baiting Judge Jackson, giving the company a winnable case in Appeals Court that it lacked in Judge Jackson’s.

So: are they baiting us here? You betcha. But the appeals court in this case is the whole IT community that remains Microsoft’s customer base.

What they want us to do is defend the incomprehensible: namely, all the stuff we can’t stop arguing about.

The tactical picture becomes clear when you look at this diagram from the Free Software Foundation’s philosophy page. From the perspective of both Microsoft and its customers, the one thing that’s easy to understand is in the upper right. By aiming insults at the GPL in the lower left, they rally everybody in the Free/Open communities to defend what those outside those communities have the most trouble understanding: the FSF’s belief that owning software is a Bad Thing.

If we defend that position, or respond by using “proprietary” as an epithet, we’ll lose. “It takes two to tango,” one commercial developer wrote to me in the midst of all this. “If Microsoft ever chose an enemy who was willing to share the cursor, they would finally have met their match. It hasn’t happened yet. Your friends are still saying ‘It’s All About Us’ which is complete bullshit. They never talk about anyone but Microsoft and themselves.”

Which is why we need to embrace and extend the most precious thing that Microsoft has and we don’t, which is customers. Why? Because it’s their hearts and minds we need to win, and Microsoft is busy ignoring them.

Look back at Mundie’s text. Note that his point of view is located not with customers, but with the commercial software industry. Big difference. Yes, commercial software companies do face a choice among many different business models and licensing schemes, including the GPL. But this argument isn’t just about business models. It is not the exclusive concern of Supply. It’s also about Demand. In some ways the real argument isn’t between Supply and Supply: one “shared” and one “open”. It’s between Supply and Demand.

On the demand side, customers are using software of many different types, from many different sources. Whether they know it or not, most large enterprises are already full of applications and development tools from the free software and open source communities. Are they choosing those “solutions” just because they like one party’s source license or another party’s business model? No. They’re using it because it’s available and practical.

We need to relocate our concerns to the demand side of markets. What is it that works, and why? Specifically, what “solutions” work for everybody? Our best example, our ace in the hole, isn’t Linux alone. It’s the Net, and all the free and open software that accounts for its ubiquity. Our communities created and proliferated that software because we know something about its nature that the Microsofts of the world do not.

The “licensing structures” Microsoft cares most about all rely on conceiving code as capital: as a manufactured good. Concepts like “intellectual property” are easy to understand and argue about as long as one continues to conceive of that property in material terms. But code is not material, and no amount of lawmaking or marketing can make it material.

The deepest fact in this matter is not that software wants to be free, but that code wants to be public. Meanwhile too many of our laws and business practices cannot comprehend this simple fact. It’s too far below their immediate concerns. Like the core of the Earth, it’s nice to have but too deep to appreciate.

The problem for Microsoft is that it lives in a world increasingly built with public code that oozes like lava out of the free and open ground below everybody. We’re making a whole new world here, but we’re doing it together. And that includes Microsoft, which in fact does contribute to common infrastructure. SOAP is a good example.

Indeed, much good has been produced by what Mundie calls the “commercial software model” or it wouldn’t have customers. But the Net on which all of business increasingly relies is not a product of that model, even though business is certainly involved.

What free/open hackers know and Craig Mundie doesn’t (yet), is that there is much to the nature of code that can neither be comprehended nor represented by the conceptual system Mundie employs — not because it’s insufficient in scope but rather because it’s operating only at the commercial level. At a deeper level — the nature of software itself — the principles of business don’t apply, for the same reason that the principles of mechanics don’t apply to chemistry, even while mechanics depends on chemistry as a deeper principle. You’d rather make a clock out of iron than sodium.

Business needs more of that public infrastructure. It needs programs, operating systems, device drivers, file formats and protocols that everybody can use because nobody owns them. So do commercial developers and their customers: all of Supply and all of Demand. But those terms are too abstract. Think of the entire mess as a bazaar.

If we embrace the whole software bazaar, we can open hearts and extend minds. If we refuse to share the cursor, we cease to represent the bazaar. At that point the choice is between a cathedral and a cult.

Links:

Mundie’s speech: http://www.microsoft.com/presspass/exec/craig/05-03sharedsource.asp

Perens’ response: http://www.perens.com/Articles/StandTogether.html

Mundie”s response: http://www.internetnews.com/intl-news/article/0,,6_766141,00.html

View Details

Eleventh in the News Commons series.

all experience is an arch wherethro’
Gleams that untravell’d world whose margin fades
For ever and forever when I move.
—Alfred, Lord Tennyson, in Ulysses

News flows. It starts with what’s coming up, goes through what’s happening, and ends up as what’s kept—if it’s lucky.

Facts take the same route. But, since lots of facts don’t fit stories about what’s happening, they aren’t always kept, even if they will prove useful in the future. (For more on that, see Stories vs. Facts.)

But we need to keep both stories and facts, and not just for journalists. Researchers and decision-makers of all kinds need all they can get of both.

That’s why a news commons needs to take care of everything from what’s coming up through what’s happened, plus all the relevant facts, whether or not they’ve shown up in published stories. We won’t get deep, wide, or whole news if we don’t facilitate the whole flow of news and facts from the future to the past.

Let’s call this the Tennyson model, after Lord Alfred’s Ulysses, excerpted above. In this model, the future is a calendar such as the one in DatePress. The present is is news reporting. The past is archives.

Calendars are easy to make. They are also easy to feed into other calendars. For example, take the Basic Government Calendar, of Bloomington, Indiana. That one is built from 50+ other calendars (to which it subscribes—and so can you). The Big Big Calendar (be patient: it takes a while to load) covers many other journalistic beats besides government (the beat of the B Square Bulletin, which publishes both).

We describe approaches to archives in The Online Local Chronicle and Archives as Commons. Here in Bloomington, we have two examples already with BloomDocs.org and The Bloomington Chronicle. Both are by Dave Askins of the B Square Bulletin using open-source code. And both are new.

Relatively speaking, Bloomington is a news oasis (see the list in Wide News) in a world where news deserts are spreading. So we’ve got a lot to work with. If you want to help with any of it, let me know.

View Details

—is not this:

A netizen isn’t just an account-holderBy now we take it for granted.

To live your digital life on the Internet, you need accounts. Lots of them.

You need one for every website that provides a service, plus your Mac or Windows computers, your Apple or Google-based phones, your home and mobile ISPs. Sure, you can use a Linux-based PC or phone, but nearly all the services you access will still require an account.

Everything that requires an account has a lock on you—for their convenience. They don’t know any other way. That’s because all the services we use in the online world operate inside a model called client-server, which looks like this:

This is great for the server operator, but not for the rest of us:

This was not the promise of the Internet described by John Perry Barlow in Death From Above in 1995 and A Declaration of the Independence of Cyberspace in 1996. Nor was it what Chris Locke, Rick Levine, David Weinberger, and I said in The Cluetain Manifesto‘s ‘one clue’—

—and in the 95 Theses that followed, starting with these:

Since I’ve often heard that an unintended consequence of Cluetrain was causing social media in some way, I just asked ChatGPT and Perplexity the same question: Did The Cluetrain Manifesto help start social media? The answers were roughly the same, but Perplexity provides sources, so I’ll quote that answer:

The Cluetrain Manifesto did not directly start social media, but it did play a significant role in predicting and shaping the philosophy behind social media marketing and online communication. Published in 1999, the manifesto anticipated many of the changes that would occur with the rise of social media and online conversations. (link) (link)

Key points about The Cluetrain Manifesto’s influence on social media:

1. Predicted global conversations: The manifesto accurately foresaw that the internet would enable powerful global conversations, allowing people to share knowledge rapidly (link).
2. Emphasized authentic communication: It stressed the importance of companies engaging in genuine, human conversations with customers, which became a cornerstone of social media marketing (link) (link).
3. Highlighted networked markets: The manifesto recognized that customers were becoming more connected and influential through online networks, a concept that social media platforms later embodied (link).
4. Challenged traditional marketing: It criticized the “homogenized voice” of traditional business communication, encouraging a more authentic and conversational approach that social media later facilitated (link).
5. Empowered employees: The manifesto suggested that companies should empower employees to engage with customers, an idea that became crucial in social media strategies (link).
6. Recognized the shift in power: It predicted that customers would gain more influence over companies through online conversations, which social media platforms later enabled (link).

While The Cluetrain Manifesto didn’t create social media technologies, it provided a philosophical foundation that aligned closely with how social media would eventually function. Its ideas about authentic communication, networked conversations, and customer empowerment became central to social media marketing strategies and practices (link) (link) (link).

Alas, we all still are seats, eyeballs, end users, and consumers, and our reach still does not exceed corporate, government, and organizational grasp, because all of those entities operate their services on the client-server model. And, so long as nearly everyone believes that client-server is the only way to go, the fact that the Internet is end-to-end beneath everything done on it remains irrelevant. Nothing in any of these (and many other) efforts before and since has done anything to change the damned Internet of Accounts:

• The Rise of the Stupid Network (by David Isenberg) in 1997
• The Cluetrain Manifesto in book form, in 2000 and in a 10th Aniversary version (with seven new chapters) in 2010
• World of Ends (by David Weinberger and me) in 2003
• Internet Identity Workshop (by Phil Windley, Kaliya Young, and me) since 2005
• ProjectVRM (by hundreds of people and projects) since 2006
• The Intention Economy, a book by me in 2012
• New Clues (by David Weinberger and me) in 2015

I do, however, see hope coming from three angles.

First is self-sovereign identity, or SSI. I’ve written about SSI in many ways and places over the years, but perhaps the best is New Hope for Digital Identity, published in Linux Journal back in 2017. What SSI wishes to replace is the familiar client-server model in which you are the account holder, and two servers are the “identity provider” and the “relying party.” With this system, your “ID” is what you get from the identity provider and their server. With SSI, you have a collection of verifiable credentials issued by the DMV, your church, your school, a performance venue, whatever. They get verified by an independent party in a trustworthy way. You’re not just a client or just an account holder. You disclose no more than what’s required, on an as-needed basis.

Second is contract. Specifically, terms we proffer as first parties and the sites and services of the world agree to as second parties. Guiding the deployment of those is IEEE P7012 Standard for Machine Readable Personal Privacy Terms, which I’ve called the most important standard in development today. I’m the chair of the P7012 working group, which has been on the case since 2017. The standard is now drafted and moving though the IEEE’s approval mill. If all goes well, it will be ready early next year. It works like this:

Possible agreements sit at a public website. Customer Commons was created for this purpose, and to do for personal contracts what Creative Commons does for personal copyrights. The person’s agent, such as a browser, acting as the first party, tells the second party (an entity of any kind) what agreement the person has chosen from a small roster of them (again, on the Creative Commons model). The entity either agrees or declines. If the two agree, the decision is recorded identically by both parties. If the entity declines, that decision is also recorded on the person’s side.

Customer Commons has one such agreement already, called P2B1 (beta), or #NoStalking. As with all contracts, there’s something in it for both parties. With #NoStalking, the person isn’t tracked away from the site or service, and the site or service still gets to advertise to the person. Customer Commons (for which I am a founder and board member) plans to have a full list of agreements ready before the end of this year. If this system works, it will replace the Internet of Accounts with something that works far better for everyone. It will also put the brakes on uninvited surveillance, big time.

Third is personal AI. This is easy to imagine if you have your own AI working on your side. It can know what kind of agreement you prefer to proffer to different kinds of sites and services. It can also help remember all the agreements that have been made already, and save you time and energy in other ways. AI on the entities’ sides can also be involved. Imagine two robot lawyers shaking hands and you can see where this might go.

There are a variety of personal (not just personalized) AI efforts out there. The one I favor, because it’s open source and inspired by The Intention Economy, is Kwaai.ai, a nonprofit community of volunteers where I also serve as chief intention officer.

I welcome your thoughts. Also your work toward replacing the Internet of Accounts with the Internet of People—plus every other entity that welcomes full personal agency.

View Details

It was a derecho, or something like one. The gust front you see in the third image here looks a lot like the storm front in the image above (via Weatherbug, storm tracker view). I’d experienced one twelve years ago, in Arlington, Mass. It felt like a two minute hurricane, and when it was over, hundreds of trees were down. This wasn’t as bad, but TwitteX seemed to agree that a derecho it was. And we did have many broken trees and power outages. Here’s one example of the former:

That’s half a huge silver maple. Very luckily, it missed the house and only trashed the metal fence. Pretty house, too.

There was also a lot of lightning. Dig:

You can barely see the blue dot in the middle, but that’s where we live. One of those dots is about a hundred feet from where I’m writing this.

If you’re into this kind of stuff, I recommend the My Lightning Finder app, which produced the above. Also LightningMaps.org on the Web. That one shows thunder as circles expanding at the speed of sound around a lightning dot. Of course, lots of those lightning dots are lines in clouds, or zig-zags between ground and sky. They aren’t all “strikes.”

But when lightning does strike, one of my favorite storm sounds is a loud crack, then “Cccchhhheeeeeooooowwwwwww” before a BOOM of thunder slams the ground. What you’re hearing after the crack is sound coming off the length of the lightning strike, starting at the ground and moving up to the cloud above, with the volume of the sound and its pitch going down as it originates from farther and farther away along the length of the lightning itself. The BOOM is produced by the top of the lightning bolt, spreading or fanning out inside the cloud, parallel to the ground, so the sound comes at you from the broad side of the aerial end of the bolt. Listen for it the next time you’re in a storm and lightning strikes nearby.

[Later, 1:00 am on 27 June…] Much of the city is still without power. Also, this photo on Reddit, shot from the west side Aldi, shows the kind of rain that produces a derecho.

View Details

I don’t think it does. Not for everything.

We already have personal AI for autocomplete. Do we need Big Compute for a personal AI to tell us which pieces within our Amazon orders are in which line items in our Visa statements? (Different items in a shipment often appear inside different charges on a card.) Do we need Big Compute to tell us who we had lunch with, and where, three Fridays ago? Or to give us an itemized list of all the conferences we attended in the last five years? Or what tunes or podcasts we’ve played (or heard) in the last two months (for purposes such as this one)?

Let’s say we want a list of all the books on our shelves using something like OpenCV to detect text in natural scene images using the EAST text detector? Or to do the same kind of advanced pattern recognition to catalog everything we can point a phone camera at in our homes? Even if we need to hire models from elsewhere to help with that, onboard compute should be able to do a lot of it, and to keep our personal data private.

Right now your new TV is reporting what you watch back to parties unknown. Your new car is doing the same. Hell, so is your phone. What if you had all that data? Won’t you be able to do more with it than the spies and their corporate customers can?

It might be handy to know all the movies you’ve seen and series you’ve binged on your TV and other devices—including, say, the ones you’ve watched on a plane. And to remember when it was you drove to that specialty store in some other city, what the name of it was, and what was the good place you stopped for lunch on the way.

This data should be yours first—and alone—and shared with others at your discretion. You should be able to do a lot more with information gathered about you than those other parties can—and personal AI should be able to help you do it without relying on Big Compute (beyond having its owners give you back whatever got collected about you).

At this early stage in the evolution of AI, our conceptual frame for AI is almost entirely a Big Compute one. We need much more thinking out loud about what personal AI can do. I’m sure the sum of it will end up being a lot larger than what we’re getting now from Big AI.

View Details

This is the best illustration I could get out of ChatGPT 4o. It’ll do until I have it get a better one.Nobody’s talking about this, so I will: Jayson Tatum is playing a decoy. More to the point, he is playing Jokić, Dončić, or a bit of both. Not all the time (such as when he’s doing one of those step-back threes with lots of time on the clock, but enough). So let’s call him Jayson Tatić.

Because on offense he’s pulling in double and triple teams and passing expertly to open men. Over and over again. And the passes turn into assists because he is connected to those men. That’s the way the Boston Celtićs work under Joe Mazzula. Connection is everything. They are a team of fully capable all-stars, each willing to give up their own ego and stats for the sake of the team.

So, while the talking heads and talking ‘casts go on about how poor Tatum’s offense seems to be, they miss the misdirection. They assume Jayson Tatum is always wanting to play hero ball, because he can, and because that’s they guy he is. They don’t get that he’s really Jayson Tatić’, and his feint is that he’s always going to shoot, that he’s always going to post up and go one-on-two or one-on-few. Meanwhile, what he’s really doing is pulling in a defense that gives him open men, all of whom he knows, because he’s connected to them psychically, audibly (they talk!) and manually. He is always working to pass, which he does expertly.

Yeah, he turns it over sometimes. So what. He gets assists because he’s a one-man wrecking crew of misdirection, especially when he gets downhill. And the man can pass.

When this series is over, and Boston takes it 4 to 3, 2, 1, or 0, and Jaylen Brown or Jrue Holiday get the MVP (like Andre Iguodala got the MVP a few years back), the Celtics’ success will owe in no small way to Jayson’s teamwork.

There’s a game tonight, so watch for it.

View Details

These are the men who strung and assembled the cables that hold up the George Washington Bridge roadway. After this was shot, on July 25, 1929, the cable bundles were compressed, sheathed, and draped with suspension cables to the new roadway that would be built below. The photo is from the collection of Allen H. Searls, the gap-toothed guy with a big grin at the center of the photo. He was 21 at the time.My father, Allen H. Searls, was an archivist. Not a formal one, but good in the vernacular, at least when it came to one of the most consequential things he did in his life: helping build the George Washington Bridge. He did this by photographing his work and fellow workers. He shot with a Kodak camera, and then developed and printed each shot, and assembled them into an album that survives to this day. All the shots in this collection are from that album. I’ve archived them in my Flickr site focused on infrastructure. I have also Creative Commons licensed them to require only attribution. (Though I’d rather people credit Allen H. Searls than his son.)

Only two of the photos are dated. One is July 25, 1929, when workers and families celebrated the completion of the cable stringing operation. The other is July 25, 1930, presumably when the roadway was completed. I was able to piece together the significance of these dates, and guess at the date ranges of other pictures, by doing a deep dive into the New York Times archive (where I found that these guys were called “bridgemen,” and by reading my father’s copy of the Roebling Cable company’s book about how the bridge’s cables were made and put in place.

As we know now, almost too well, we live in an Age of AI, when the entire corpus of the Internet, and God only knows what else, has been ingested into large language models that are trained and programmed to answer questions about what they “know” (even though they don’t, really). Meanwhile what do we, as human beings, actually know? Or, better yet, where can we find what we need or want to know? Libraries of the physical kind are necessary but insufficient when our instruments of inquiry are entirely electronic. The World Wide Web has turned into the World Wide Whiteboard.

We need electronic archives. Simple as that.

We all know (and, I hope, appreciate) the Internet Archive. I was going to give my father’s copy of the Roebling book to the Archive for scanning, but discovered it’s already there! That made the book easy to read (here on this flat screen), and saved my own fragile copy from further damage.

A heroic example of one person’s work to save the whole corpus of literature on broadcasting is David Gleason’s World Radio History site, without which much knowledge of broadcasting history would be lost.

On the contemporary front, Dave Askins‘ work toward online local news chronicles may prove essential if we don’t want to see current and future news disappear down the same holes into which too many past publications’ work has fallen (or remains alive but trapped behind paywalls).

For more on where this might go, see my Archives as Commons post. I’ll be talking about this, I hope, at the upcoming WoW Conference and DWeb Camp.

View Details

Here is me, trying to get ChatGPT (version 4o, which I pay for) to give me an illustration to use in my last post here, titled The People’s AI. But don’t go there yet (if you haven’t already). What I ended up using there is a punchline at the end of the dialog that starts here—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

ChatGPT:

Here’s the illustration of a whimsical outdoor scene with a vast field shaped into the letters ‘A’ and ‘I’, where people are enjoying various activities, creating a cheerful and lively atmosphere.

Me: Make the two letters upper case A and upper case I, both with serifs.

ChatGPT:

Here’s the updated illustration of a vast field shaped into the uppercase letters ‘A’ and ‘I’, both with serifs, where people are enjoying a sunny day outdoors. The setting is lively and festive, enhancing the creative landscape.

Me: Those are not the letters A or I, and lack serifs. Try again, with A on the left, and I on the right.

ChatGPT:

Here’s the updated illustration showing a vast field shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is vibrant and bustling with people enjoying various outdoor activities.

Me: Better, but there is no I on the right.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is lively with people engaging in various activities, set in a sunny and cheerful environment.

Me: That’s an interesting design, but I need an A and an I next to each other.

ChatGPT:

Here’s the updated illustration showing the vast field clearly shaped into the adjacent uppercase serif letters ‘A’ and ‘I’. The setting is vibrant and festive, surrounded by people enjoying various activities.

Me: That’s one big A, not an A and an I. Give me both.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is lively and festive, filled with people enjoying various activities.

Me: That has no serifs and is still just an A. I want an A and an I. Separate.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is vibrant, with people enjoying various outdoor activities.

Me: Still not separate. That’s one big A. I want an I next to it.

ChatGPT:

Here’s the updated illustration, clearly showing the vast field shaped into the separate uppercase serif letters ‘A’ on the left and ‘I’ on the right. The scene is lively with people enjoying various activities under a sunny sky.

Me: Let’s try this: An “A” and an “I” in an open field full of people.

ChatGPT:

Here’s the illustration showing an open field shaped into the uppercase letters ‘A’ and ‘I’, with people enjoying various activities in the area. The scene is lively and sunny, capturing a cheerful outdoor gathering.

Me: Better! Now give me the same thing, with a complete “a.”

ChatGPT: We are experiencing heavy server load. To ensure the best experience for everyone, we have rate limits in place. Please wait for 2 minutes before generating more images. Let me know if there’s anything else you’d like to discuss in the meantime!

Me (after a 3 minute pause): Thanks. Now give me the same image, but with a complete “A.”

ChatGPT:

Here’s the updated illustration showing a vast open field creatively landscaped into two distinct uppercase ‘A’ letters, bustling with people enjoying various activities in a sunny, cheerful setting.

(Yes, it created both images.)

Me: Give me the same, but with people surrounding the “A” and the “I.” Also, please put serifs on the “I.”

ChatGPT:

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the uppercase letters ‘A’ and ‘I’, both with serifs. The field is surrounded by people enjoying various activities in a sunny, cheerful setting.

Me: Try the same, but with “a” and “i” as separate letters.

ChatGPT:

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is surrounded by people enjoying various activities in a sunny, cheerful atmosphere.

Me: Closer. Only now take it out of the city. I want only countryside.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is serene and picturesque, surrounded by people enjoying rural activities.

Me: Please make the “a” and the “i” separate.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the distinctly separated lowercase letters ‘a’ and ‘i’. The setting is serene, surrounded by people enjoying rural activities in a picturesque and peaceful outdoor gathering.

At this point I gave up and decided to give Microsoft Copilot a whack—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

Microsoft Copilot:

I decided not to push my luck, and used the one on the bottom right.

It’s fun to know I am not alone at this. Here is a brilliant video of somebody far more patient than I getting ChatGPT to spell HONDA in ASCII art.

Early days, folks. Early days.

View Details

Prompt: “A vast field on which the ground spells the letters A and I, with people on it, having a good time.” Via Copilot | DesignerPeople need their own AIs. Personally and collectively.

We won’t get them from Anthropic, Apple, Google, Meta, or Microsoft. Not even from Apple.

All of those companies will want to provide AIaaS: AI as a Service, rather than AI that’s yours alone. Or ours, collectively.

The People’s AI can only come from people. Since it will be made of code, it will come from open-source developers working for all of us, and not just for their employers—even if those employers are companies listed above.*

That’s how we got Linux, Apache, MySQL, Python, and countless other open-source code bases on which the digital world is now built from the ground up. Our common ground is open-source code, standards, and protocols.

The sum of business that happens atop that common ground is incalculably vast. It also owes to what we first started calling because effects twenty years ago at Bloggercon. That was when people were making a lot more money because of blogging than with blogging.

Right after that it also became clear that most of the money being made in the whole tech world was because of open-source code, standards, and protocols,rather than with them. (I wrote more about it here, here, and here.)

So, thanks to because effects, the most leveraged investments anyone can make today will be in developing open source code for The People’s AI.

That’s the AI each of us will have for our own, and that we can use both by ourselves and together as communities.

Those because investments will pay off on the with side as lavishly as investments in TCP/IP, HTTP, Linux, and countless other open-source efforts have delivered across the last three decades.

Only now they’ll pay off a lot faster. For all of us.

See what I wrote for Linux Journal* in 2006 about how IBM got clueful about paying kernel developers to work for the whole world and not just one company.

View Details

Newsletters are all the rage now. In recognition of that, I blogged here two years ago about the idea of writing a solo newsletter. Since then I’ve been co-producing this one with Katherine Druckman at Reality 2.o. It’s a Substack one, so I know how that game works on the production as well as the consumption ends.

Recently I also learned that WordPress makes it easy to turn blogs into newsletters, which is why you see “Get New Posts by Email” in the right column here. So, wanting an image to go with the news that this blog can now be a newsletter if you like, I said to ChatGPT, “Draw me Doc Searls blogging on the left side of the image, and producing a newsletter on the right side.” It gave me this, including the caption:

Here’s the illustration depicting Doc Searls engaging in two different activities. On the left, he is blogging, and on the right, he is producing a newsletter. This split scene captures his multitasking abilities in digital content creation.Except for the slouch, I never looked like that. But what the hell. AI is wacky shit, so there ya go.

Feel free to subscribe.

View Details

There is a war going on. Humanity and nature are on one side and Big Tech is on the other. The two sides are not opposed. They are orthogonal. The human side is horizontal and the Big Tech side is vertical.*

The human side is personal, social, self-governed, heterarchical, open, and grounded in the physical world. Its model is nature, and the cooperative contexts in which competition, creation, and destruction happen in the natural world.

The Big Tech side is corporate, industrial, hierarchical, competitive, mechanistic, extractive, and closed, even though it produces many positive-sum products and services that are good for people and good for nature. It is also, being competitive and rewarding toward winner-take-most outcomes, dominated by giants.

This war has been fought over many other things in the past, especially in tech. But AI is the big one right now—and perhaps the biggest one of all time.

Over the long run, both sides will win, because we need the best of what both bring to the world’s big round table. In the past, this has happened in countless markets, countries, polities, societies, and other contexts. In tech it happened with the conflict between PCs and mainframes, between the open and public Internet and closed private networks, and between open operating systems and closed ones. None of those conflicts have final outcomes, but they have arrived at stable and cooperative states. They arrived at those states because everyone recognized that people can do more with their tools than those big entities can do on their own, or by using people as extracted resources.

This conflict is perhaps best represented by the ironies that have been at work within OpenAI and Sam Altman, its prior and current CEO. We can also see it with sparkling clarity in something amazing that Sam said near the close of his keynote at the first OpenAI Developer Conference, in November of last year:

Lets unpack that.

Individual empowerment means exactly what it says. Agency is the ability to take action or to choose what action to take (Cambridge Dictionary). Scale means growth toward ubiquity.

You have individual empowerment and agency when you ride your bike, drive your car, mow your lawn, or button your shirt. You also have it when you work on your laptop, phone, and other smart rectangles. Scale means your power and agency will grow to the max while the same will happen for nearly everyone else. Scale for you alone won’t cut it. When most of us have it, that’s scale.

Technologies extend us. They enlarge our capacities in the world. Intelligence is one of those capacities. So is memory. Your rectangles help a lot with both. That’s why those have already scaled to ubiquity, or close enough.

AI will do the same, but only if it’s personal. Not if it’s just”personalized.”

ChatGPT4 doesn’t know that yet. I can tell because I just asked:

Me:
What is “personal AI”?

ChatGPT4:
“Personal AI” refers to artificial intelligence systems that are designed to serve individual users through personalized interactions and services. These AI systems learn from the specific preferences, behaviors, and needs of their users to offer more tailored assistance, recommendations, or information. The goal of personal AI is to enhance user experience by adapting to unique personal profiles.

There are various applications of personal AI, including:

1. Virtual Assistants: Like Siri, Google Assistant, and others, these AIs help with daily tasks such as scheduling, reminders, searching information, and controlling smart home devices, all customized to the user’s habits and preferences.
2. Recommendation Systems: Used in streaming services like Netflix or shopping platforms like Amazon, these AI systems analyze your past behavior to recommend movies, shows, or products you might like.
3. Healthcare: Personal AI can track individual health metrics and provide personalized advice, monitor conditions, or even alert medical professionals if needed.
4. Learning and Development: In education, personal AI can adapt learning materials to the pace and learning style of the student, offering a customized educational experience.
5. Gaming: AI in gaming can adapt to provide a challenge tailored to the player’s skill level or alter the game narrative based on choices made by the player.

The development of personal AI focuses on enhancing user engagement by creating more intuitive and responsive interactions that feel uniquely suited to each individual.

For a second opinion, I asked Google’s Gemini the same question.

Me:
What is “personal AI”?

Gemini:
Personal AI refers to artificial intelligence designed to assist and interact with a specific individual. It’s essentially your own AI companion that learns about you and tailors its services to your needs. Here are some key aspects of personal AI:

1. Personalization: Unlike general-purpose AI assistants, personal AI focuses on you. It learns from your interactions, preferences, and habits to become more helpful over time.
2. Focus on Memory and Knowledge: Some personal AI systems aim to become an extension of your mind. They can store your memories, knowledge, and experiences, making them readily accessible and even usable to help with tasks like writing or communication.
3. Varied Applications: Personal AI can have a wide range of applications. Imagine an AI that helps you:
4. Organize your life: Manage schedules, appointments, and reminders.
5. Boost productivity: Assist with tasks, research, and communication.
6. Enhance creativity: Help you brainstorm ideas or generate creative content.
7. Improve learning: Personalize learning experiences and provide targeted information.

Privacy Concerns: Storing personal data on an AI raises concerns about privacy and security.

Overall, personal AI holds promise for a future where technology seamlessly integrates with our lives, offering personalized assistance and support.

To both companies, personal AI is a personalized service—from them. It’s not something you own and control. It’s not about individual empowerment and agency. It doesn’t extend you. It’s hired prosthesis: an extension of them rather than of you.

But hats off. OpenAI and Gemini do an amazing job. So do lots of other AI services by wannabe giants. I use AI every day to improve what I write, to generate and fix images, to answer questions that old-fashioned search engines can’t answer or suck at. I even pay extra for some of it (such as ChatGPT4 and Adobe’s Creative Suite). And it seems they all get better, all the time, at everything. Won’t personalization be good enough, eventually?

No. Because they aren’t you. They also aren’t yours, so they can’t extend you. They can seem to. But they don’t. They also don’t have access to most of your private life. Nor should they.

But your private life could use some AI help. For example—

• Schedules, including on your calendars, past and future
• Health data, including all your medical reports, prescriptions, appointments, insurance information, past and present providers, plus what your watch, phone, and other devices record about you
• Financial records, including bills, receipts, taxes, and anything called an account that involves money
• Travel, including all the movements your phone (and phone company), watch, and car record about where you go and where you’ve been
• Work—past and present, including whatever HR systems know or knew about you
• Contacts—all the people, businesses, and other entities you know
• Business relationships, with brokers, retailers, service providers, whatever
• Subscriptions, including all those “just $1 for the first four weeks” offers you’ve accepted, plus other forms of screwage that are stock-in-trade for companies selling subscription systems to businesses.
• Property, including all the stuff on your shelves, floors, closets, garages, and storage spaces—plus your stocks and real estate.

It’s not easy to visualize what a personal AI might do for those, but let’s try. Here’s how Microsoft’s Copilot (or whatever it’s called this week) did it for me before I got rid of all its misspellings and added my own hunks of text:

All that stuff is data. But most of it scattered between apps and clouds belonging to Apple, Google, Microsoft, Amazon, Meta, phone companies, cable companies, car makers, health care systems, insurance companies, banks, credit card companies, retailers, and other systems that are not yours. And most of them think that data is theirs and not yours.

To collect and manage all that stuff, you need tools that don’t yet exist: tools that are yours and not theirs. We could hardly begin to imagine those tools before AI came along. Now we can.

For example, you should be able to take a picture of the books on your shelves and have a complete record of what those books are and where you got them. You’ll know where you got them because you have a complete history of what you bought, where and from whom. You should be able to point your camera in your closets, at the rugs on your floors, at your furniture, at the VIN number of your car that’s visible under your windshield, at your appliances and plumbing fixtures, and have your AI tell you what those are, or at least make far more educated guesses than you can make on your own.

Yes, your AI should be able to tap into external databases and AI systems for help, but without divulging identity information or other private data. Those services should be dependent variables, not independent ones. For full individual empowerment and agency, you need to be independent. So does everyone else with personal AI.

Now imagine having a scanner that you can feed every bill, every receipt, every subscription renewal notice, and have AI software that tells you what’s what with each of them, and sorts records into the places they belong.

Ever notice that the Amazon line items on your credit card bill not only aren’t itemized, but don’t match Amazon’s online record of what you ordered? Your personal AI can sort that out. It can help say which are business and personal expenses, which are suspicious in some way, what doesn’t add up, and much more.

Your personal AI should be able to answer questions like, “How many times have I had lunch at this place? Who was I with? When was it we drove to see so-and-so in Wisconsin? What route did we take? What was that one car we rented that we actually liked?

Way back in 1995, when our family first got on the Internet over dial-up, using the first graphical browsers on our PC, and e-commerce began to take off with Amazon, eBay, and other online retailers, my wife asked an essential question: Why can’t I have my own shopping cart that I take from site to site?

Twenty-nine years later, we still don’t have the answer, because every retailer wants you to use its own. And we’re stuck in that system. It’s the same system that has us separately consenting to what sites ironically call “your privacy choices.” And aren’t.

There are countless nice things we can’t have in the digital world today because we aren’t people there. We are accounts. And we are reduced to accounts by every entity that requires a login and password.

This system is a legacy of client-server, a euphemism for slave-master. We might also call it calf-cow, because that’s how we relate to businesses with which we have accounts. And that model is leveraged on the Web like this:

We go to sites for the milk of content and free cookies, whether we want them or not. We are also just “users.”

In the client-server world, servers get scale. Clients have no more scale than what each account—each cow—separately allows. Sure, users get lots of benefits, but scale across many cows is not one of them. And no, “login with Google” and “login with Facebook” are just passes that let calves of ruling cows wander into vassal pastures.

For individual empowerment and scale to happen, we need to be self-sovereign and independent. Personal AI can give that to us. It can do that by solving problems such as the ones listed above, and by working as agents that represent us as human beings—rather than mere users—when we engage with Big Tech’s cows.

This will be a fight at first, because the cows think they run all of nature and not just their own farms. And $trillions are being invested in the same old cattle industry, with AI painted all over the new barns. Comparatively speaking, close to nothing is going toward giving independent and self-sovereign individuals the kind of power and scale Sam Altman says he wants to give us but can’t because he’s on the big cow side of this thing.

So where do we start?

First, with open source code and open standards. We have some already. Llama 3, from Meta AI, is “your own intelligent assistant,” and positions Meta as a more open and user-friendly cow than OpenAI. But Meta is still on the top-down Big Tech side of the war we’re in. But hell, we can use what they’ve got. So let’s play with it.

Here on the ground there are all these (with quotage lifted from their sites or reviews such as this one)—

• MindsDB: “an open-source AutoML framework”
• Keras: “a multi-backend deep learning framework, with support for JAX, TensorFlow, and PyTorch”
• PyTorch: “Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration, and Deep neural networks built on a tape-based autograd system
• Tensor Flow: “open-source framework for machine learning”
• CoreNet: a deep neural network toolkit for small and large-scale models, from Apple
• Haystack: an “open source Python framework by deepset for building custom apps with large language models (LLMs).”
• Image Super-Resolution (ISR): “(an) open source tool employs a machine learning model that you can train to guess at the details in a low-resolution image:
• Blender: “A rich interface and numerous plugins make it possible to create complex motion graphics or cinematic vistas”
• DeepFaceLab: “open source deepfake technology that runs on Python”
• tflearn: “an advanced deep learning library”
• PYTensor: “a Python library that allows you to define, optimize/rewrite, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.” (Was Theano)
• HuggingFace Transformers: “a popular open-source library for Natural Language Processing (NLP) tasks”
• Fast.ai: “a library for working with deep learning tasks”
• OpenCV: “a popular Computer Vision and Image Processing library developed by Intel”
• Detectron2: “a next-generation library that provides advanced detection and segmentation algorithm”
• Ivy.ai: “an open-source deep learning library in Python focusing on research and development”
• OpenAssistant: “a project aimed at giving everyone access to a great chat-based large language model”
• PaddleNLP: ” a popular open source NLP library that you can use to glean search sentiment and flag important entities”
• Fauxpilot: an open-source locally hosted alternative to the GitHub Copilot server
• Ray: “An open source framework to build and scale your ML and Python applications easily”
• Solid: “Solid is a specification that lets individuals and groups store their data securely in decentralized data stores called Pods. Pods are like secure web servers for data. When data is stored in a Pod, its owners control which people and applications can access it.”
• YOLOv7: “is one of the fastest and most accurate open source object detection tools. Just provide the tool with a collection of images full of objects and see what happens next.”

—and lots of others that readers can tell me about, and to which I will add links later. Because this is a work in progress.

I believe, however, that we need something Linux-like in the sense that it becomes the open base on which lots of other stuff runs. The closest I’ve seen so far is pAI-OS, by Kwaai.ai, a nonprofit I now serve as Chief Intention Officer. I got recruited by Reza Rassool, Kwaai’s founder and chair, because he believes personal AI is required to make The Intention Economy finally happen. So that was a hard offer to refuse. Kwaai also has a large, growing and active community, which I believe is both necessary and cool.

As with most (maybe all) of the projects listed above, Kwaai is a grass-roots effort by human beings on the natural, human, and horizontal side of a battle with giants who would rather give us personalized AI than have us meet them in the middle with personal AI powers of our own. In the long run we will meet in that middle. Because personal AI will be better for everyone than personalized AI alone. Watch us prove it. Better yet, join the effort.

*I am indebted to Lavonne Reimer for introducing and co-thinking the horizontal vs. vertical frame, and look forward eagerly to her own writings and lecturings on the topic.

View Details

I shot this photo in July 2007, while sitting with friends in that same booth at the Eagle and Child in Oxford.Among all artists, writers alone suffer the illusion that the world needs to hear what they have to say.

I thought that line, or something like it, came from Rollo May, probably in The Courage to Create. But a search within that book says no. ChatGPT and Gemini both tell me May didn’t say it anywhere.

Still, I think it’s true that writers write because they have to. They can’t not write. It’s what they do, how they live. And I’m one of them.

The need to write is for me a vivid fact this morning, a few days past a catheter ablation on my heart. There is so much I need to say, because I suffer the illusion that the world needs to hear it. Does it?

I am sure C.S. Lewis and J.R.R. Tolkein had the same affliction. I am also sure that the world is better for having read both of them, even if the world could have lived without their writing.

As for time, I have had twelve more years to write than Lewis got, so far, and five less than Tolkein.

Time to say what?

I want to say that personal AI will do far more for all of us than what we will ever get from AI as a corporate service. And to say it better than I just did.

I want to say that we will do better with rulers who care about people than with rulers who merely rule. And to say that better than I just did.

I want to complete the work of John McPhee by reporting as best I can what has happened to the great characters that anchored every one of his essays and books. But that project is not on the back burner. It’s in the fridge, where I’ve kept it for decades (while continuing to read the entire McPhee oeuvre, much of it repeatedly).

Speaking of burning, I am impelled by Dylan Thomas, who wrote “Do not go gentle into That Good Night,” before dying at just thirty-nine. The poem was for his father:

Old age should burn and rave at close of day,
Rage, rage against the dying of the light.

And so I do.

View Details

The Santa Barbara library, viewed from the county courthouse. Is this where the dead local paper’s archives will go? How about future archives of all the local news organs?The Santa Barbara News-Press was born in 1868 and died in 2023 at age 155. Its glory years ran from 1932 until 2000, when the New York Times sold it to Wendy McCaw, who rode it to hell.

That ride began with the Santa Barbara News Press Controversy in 2006 and ended when Ampersand, the company McCaw created to hold the paper’s bag of assets (which did not include its landmark building downtown, which McCaw kept), filed for Chapter 7 bankruptcy in late July of last year. Here are stories about the death of the paper in three local news journals that have done a great job of taking up the slack left when the News-Press began to collapse, plus one in the LA Times:

• ‘Santa Barbara News-Press’ Files for Bankruptcy: Publisher Ampersand Claims Few Assets and Many Creditors, by Jean Yamamura in the Santa Barbara Independent (July 23, 2023)
• Santa Barbara News-Press Declares Bankruptcy, Staff Told All Jobs ‘Eliminated’, by Joshua Molina, in Noozhawk (July 23, 2023)
• Santa Barbara News-Press Files for Bankruptcy, Staff Fired, by Edhat Staff (July 24, 2023)
• Santa Barbara News-Press bankruptcy brings uneasy end to an owner’s bitter tenure, by James Rainey, in the Los Angeles Times. (July 29, 2023)

I followed those with this in We Need Deep News:

From what I’ve read so far (and I’d love to be wrong) none of those news reports touch on the subject of the News-Press‘ archives, which conceivably reach back across the century and a half it was published. There can’t be a better first draft of history for Santa Barbara than that one. If it’s gone, the loss is incalculable. (August 18 2023)

Last month brought bad news about that:

• ‘Santa Barbara News-Press’ Online Assets to Be Sold: Bankruptcy Sale for $250,000 Subject to Bids in April, by Jean Yamamura in the Santa Barbara Independent March 8, 2024
• A local paper went bankrupt. Now a faraway buyer wants its assets: The Santa Barbara News-Press’s digital assets are up for sale. Locals worry they could become a farm for AI-generated SEO bait. By Ernie Smith in Fast Company. (March 5, 2024)
• Santa Barbara’s Collective Memory, Sold for Kindling: Will ‘NewsPress.Com’ Become a Zombie Website? by William Belfiore in the Independent. (March 29, 2024)

But then, thanks to William Belfiore’s appeal in that last piece, we learned this:

• ‘Santa Barbara News-Press’ Website Goes to ‘Local Kids’ Group Fronted by Ben Romo Makes Winning Auction Bid of $285,000, by Jean Yamamura in the Independent (Apr 09, 2024)

The only mention of archives was in the closing sentences of that piece:

The purchase of the website included the Santa Barbara News-Press trademark, which would be important to the groups looking at the physical archive of back issues, photographs, and clippings by topic. Romo, who was once a paper boy for the daily, acknowledged that his group was supportive of the archive remaining local, too.

I don’t know what that means, and I haven’t checked. But I am sure that the archives ought to be managed by the community as a common pool resource.

As it happens, my wife and I are visiting scholars at the Ostrom Workshop at Indiana University, which is concerned with this kind of thing, because its namesake, Elinor Ostrom, won a Nobel Prize in Economics for her work on how commons are self-governed. In her landmark book, Governing the Commons: The Evolution of Institutions for Collective Action, she lists eight principles for managing a commons, which are summarized here:

1. Define clear group boundaries.
2. Match rules governing use of common goods to local needs and conditions.
3. Ensure that those affected by the rules can participate in modifying the rules.
4. Make sure the rule-making rights of community members are respected by outside authorities.
5. Develop a system, carried out by community members, for monitoring members’ behavior.
6. Use graduated sanctions for rule violators.
7. Provide accessible, low-cost means for dispute resolution.
8. Build responsibility for governing the common resource in nested tiers from the lowest level up to the entire interconnected system.

Journalists, especially those who report news, are not herding animals. They tend to be competitive and territorial by both nature and purpose. So the collection of news entities I wrote about in We Need Wide News and We Need Whole News will almost certainly not cohere into a commons such as Lin (her nickname) Ostrom addresses in that list.

But they should cohere around archives—not only because that’s the right thing to do, but because they need those archives. We all do.

So I hope Santa Barbara’s many journals, journalists, friends, supporters, and interested local institutions get together around this challenge. Build a commons around those archives, whatever and wherever they happen to be.

Meanwhile here in Bloomington, my other hometown, we are pushing forward with The Online Local Chronicle that Dave Askins wrote about in the previous installment in this series. We might call that a commons interest here.

View Details

Journalism as we knew it is washing away. But the story is bigger than journalism alone, and bigger than a story alone can tell. (Image borrowed from the brilliant Despair.com.)We who care about journalism are asked to join the Save Journalism Project, and its fight against Big Tech. Their pitch begins,

and adds,

On the first point, we should note that journalists have been working for magazines, broadcasters, newsletters and themselves for many dozens of years. So journalism isn’t just about newspapers. Also, because so many journalists have long made livings in those other media, the loss of work is far greater than the 2,400 gone from newspapers. It’s truly massive. I don’t know any field where the loss of paying jobs is larger on a percentage basis. Not taxi driving, not hospitality, not retail, not manufacturing… not anything I can think of. (Well, maybe nuns. I don’t see many of those these days.)

We should also respect the simple fact that now there is more journalism than ever: in blogs, social media, podcasting, and other places. Most of those kinds of journalism don’t pay, but that doesn’t disqualify the work from the label. Hell, I’m committing journalism here and this doesn’t pay.

“The story of big tech’s threat to journalism” (what the Project wants us all to tell) is also something of a red herring because it distracts our attention from causes much bigger than Big Tech.

Every new technology “works us over completely,” Marshall McLuhan says (in The Medium is the Massage). And no new medium, no new technologies, have ever worked us more than the digital kind. The change began with digital tech and integrated circuits and then went absolute with the Internet. Together, digital technologies and the Internet have radiacally changed our species, our civilization, and our planet.

Not long ago, in a conversation about this with Joi Ito, I asked him how big he thought the digital transformation was. Bigger than broadcast? Print? Writing? Speech? Stone tools?

“No,” he replied. “It’s the biggest thing since oxygenation.” In case you don’t remember, that happened between about two and a half billion years ago. (Joi also writes about it here.)

So, while journalism matters enormously, it’s just one casualty of digitalization. And, let’s face it, a beneficiary as well. Either way, we need to understand the whole picture, which is about a lot more than what journalism sees happening in the mirror.

Here’s one outfit working on that bigger picture. I‘m involved with it.

I also don’t expect most journalists to take much interest in the subject, because it’s too big, and it doesn’t make full sense as a story, which is journalism’s stock in trade. (I explain a bit about journalism’s “story problem” in this TEDx talk.)

Still, some journalists are on the case, including me. Love to have others join in. But please don’t bother if you think Big Tech is alone to blame. Because the story is bigger than that, and far more than a story.

I just copied and pasted this post from here in Medium, where I posted it in July 2019. It expands on a post now archived here. It’s kinda sad that not much has changed over all that time.

View Details

Contrails in the stratosphere, smearing sideways into broad cloud cover. This view is toward the place in the sky where a full solar eclipse will happen a few hours later.Contrails form behind jet aircraft flying through the stratosphere. Since high-altitude aviation is happening all around the earth more or less constantly, planes are painting the sky everywhere. (Here is one time-lapse. And another. And one of my own.)

Many contrails don’t last, of course, but many do, and together they account for much of the cloud cover we see every day. The altocumulus, altostratus, and cirrus clouds that contrails produce are now officially recognized as homogenitus and homomutatus, which are anthropogenic: owing to human activity.

And today, Eclipse Day, Delta is offering to fly you along the path of totality. Others too? I don’t know. I’m taking a few moments to write this before we walk up to our hilltop cemetery to watch the eclipse for over four minutes, thanks to our lucky location near the very center of Totality.

I’m curious to see and hear contrail reports from others now awaiting their few minutes out of the sun.

1:14pm—The moon’s shadow made landfall in Mexico a short time ago. Here in Bloomington, the sky is well-painted by contrails. Mostly it looks like high-altitude haze, but believe me: if it weren’t for commercial aviation, the sky would be solid blue. Because the contrails today are quickly smeared sideways, losing their form but not their color.

5:00pm—Contrails were aplenty, and a spread-out contrail did slide in front of the sun and the moon…

but it was still a spectacular sight:

View Details

Artificial is AI’s frst name. And Intelligence is a quality, not a quantity. You can’t measure it with a dipstick, a ruler, or an IQ test. If you could, you’d get the same result every time.*

But being artificial doesn’t mean AI isn’t dangerous, fun or both. It is, and will be, what we make of it.

That’s what Don Norman says, and he’s been publishing in AI journals since 1973. His laboratory produced the first multi-layer neural nets in the 1980s. He wrote Things that Make us Smart in 1993.

In the opinion of myself and countless others, Don is also the foremost authority on design—of anything and everything. For more on that, check out Don’s Web page, his Wikipedia page, and his books. Or, if you just want to sample some of his thoughts on AI, watch this.

Or you can skip all that and come to the good stuff: joining us in a talk with Don in the final salon of this semester on the topic of Artificial +/vs. Human Intelligence. It’s next Tuesday, April 9, at Noon Eastern time. (That’s less than 24 hours after the shadow of the Moon passes over the Indiana University campus. Yes, totality will be local here.)

Also, this won’t be a lecture or a presentation. It will be a lively discussion because Don is especially good at that.

It’s also free and online, but you have to register first. Do that here.

*For what it’s worth, my own known IQ test scores have an 80-point range. I’ve written about that, and the myth of “IQ” here, here, here, here, and I suppose in too many other places.

View Details

By expert acclaim, this is the best antenna for receiving hard-to-get over-the-air (OTA) TV signalsI think I will be the last person in Bloomington to try getting free over-the-air TV from what’s left of all the major networks. But that’s just my style, so roll with me while I explain how I’m hoping to do it, with the antenna above, which I’ll need because here is what the Search Map at RabbitEars.info says we might get here:

We live next door right now, and the top station above, WTIU from Indiana University (our PBS affiliate), comes from a tower you can walk to from here. We can get that signal by using a straightened paper clip for an antenna. (You jam the clip into the center hole of the coaxial connector in the back of the TV.) Even a real indoor antenna connected to the same jack gets nothing else, not even the two stations above with “Fair” signal strength.

But this Televes antenna might do the job because we’re on the slope of a hill that faces the Indianapolis stations that carry CBS (WTTV/4 on 27), ABC (WRTV/6 on 25), NBC (WTHR/13 on 13), and Fox (WRDB/41 on 32)*. These range from 27 to 54 miles away, in roughly the same direction. VHF and UHF signals always gain strength when they hit the faces of hills, similar to how surf builds as it approaches a sand bar or a shore. Also, the Televes DAT BOSS antenna gets great reviews:

• TechHive: Televes Dat Boss Mix LR review: This is a great outdoor antenna
• Tyler the Antenna Guy: Televes DATBOSS LR Mix Outdoor Antenna Review 149883
• Solid Signal: ALL NEW Televes DATBOSS Mix LR Antenna TESTED (w/assembly instructions)
• Amazon: Televes DAT Series BOSS Mix LR Outdoor High-VHF/UHF HDTV Antenna (see the reviews)

I was going to put it in our new attic before the drywall goes up. However, the attic space is low and full of close cross-braces. Worse, the antenna is not small and kinda complicated to fit in a space that’s a web of short 2x4s. Dig:

So it will go on a pole in the backyard and feed a coaxial line that will tunnel through conduit under the yard and inside to the new living room.

But I would like to test it first, preferably with a tuner gizmo I can plug into my laptop. I had one of those for years: the Elgato EyeTV Hybrid TV Tuner stick, which looked like a fat thumb drive,with USB-A at one end and a coax connector for an antenna at the other. It was sold in the ’00s and picked up both analog and digital TV (the Digital Transition was happening then), on every North American channel, and came with good software that ran on Macs and operating systems that have long been abandoned. Far as I can tell there are no replacements that run on current hardware or operating system, other than this one sold in Europe. Far as I can tell, it only works on TV bands over there. But I could be wrong. If anybody knows of a gizmo/softward combo I can use, please tell me. My only other option is to buy or find a cheap TV and try that out. Any advice is welcome. Thanks!

*After the digital transition in 2008, and again with the “repack” after 2016, most TV stations moved onto channels other than their original ones, using less spectrum overall. All the TV channels above 36 were auctioned off, first in 2008 and again in 2018. Most buyers were cellular and other short-range wireless carriers, which have been repurposing the old TV spectrum for 5G and other modern uses. The only station in Indianapolis that didn’t move its channel position was WTHR/13. That one is listed in the chart above as one of the “bad” signals for this location. The Televes antenna is designed specifically for “high band” VHF (channels 7-13) and the remaining UHF (14 to 36) TV channels. It also filters out any 5G signals that the antenna might pick up on what used to be the higher UHF channels. By the way, the old “low band” VHF channels (2 to 6) are still in use in some places, but by very few TV stations. So it’s not worth it for Televes to design an antenna to pick those channels up. Such an antenna would also be a lot bigger and longer because the low-band elements of the antenna would be much longer.

View Details

I asked ChatGPT to give me “people eating blogs” and got this after it suggested some details.Two things worth blogging about that happened this morning.

One was getting down and dirty trying to make DALL-E 3 work. That turned into giving up trying to find DALL-E (in any version) on the open Web and biting the $20/month bullet for a Pro account with ChatGPT, which for some reason maintains its DALL-E 3 Web page while having “Try in ChatGPT︎” on that page link to the ChatGPT home page rather than a DALL-E one. I gather that the free version of DALL-E is now the one you get at Microsoft’s Copilot | Designer, while the direct form of DALL-E is what you get when you prompt ChatGPT (now 4.0 for Pro customers… or so I gather) to give you an image that credits nothing to DALL-E.

The other thing was getting some great help from Dave Winer in putting the new Feedroll category of my Feedland feeds placed on this blog, in a way similar stylistically to old-fashioned blogrolls (such as the one here). You’ll find it in the right column of this blog now. One cool difference from blogrolls is that the feedroll is live. Very cool. I’m gradually expanding it.

Meanwhile, after failing to get ChatGPT or Copilot | Designer to give me the image I needed on another topic (which I’ll visit here later) I prompted them to give me an image that might speak to a feedroll of blogs. ChatGPT gave me the one above, not in response to “people eating blogs” (my first attempt), but instead to “People eating phone, mobile and computer screens of type.” Microsoft | Designer gave me these:

Redraw your own inconclusions.

View Details

When Parisians got tired of cemeteries during the French Revolution, they conscripted priests to relocate bones of more than six million deceased forebears to empty limestone quarries below the city: a hundred miles of rooms and corridors now called The Catacombes. It was from those quarries that much of the city’s famous structures above—Notre Dame, et. al.—were built in prior centuries, using a volume of extracted rock rivaling that of Egypt’s Great Pyramids. That rock, like the bones of those who extracted it, was once alive. In the shot above, shadows of future fossils (including moi) shoot the dead with their cell phones.Elon Musk wants to colonize Mars.

This is a very human thing to want. But before we start following his lead, we might want to ask whether death awaits us there.

Not our deaths. Anything’s. What died there to make life possible for what succeeds it?

From what we can tell so far, the answer is nothing.

To explain why life needs death, answer this: what do plastic, wood, limestone, paint, travertine, marble, asphalt, oil, coal, stalactites, peat, stalagmites, cotton, wool, chert, cement, nearly all food, all gas, and most electric services have in common?

They are all products of death. They are remains of living things or made from them.

Consider this fact: about a quarter of all the world’s sedimentary rock is limestone, dolomite and other carbonate rocks: remains of beings that were once alive. The Dolomites of Italy, the Rock of Gibraltar, the summit of Mt. Everest, all products of death.

Even the iron we mine has a biological source. Here’s how John McPhee explains it in his Pulitzer-winning Annals of the Former World:

Although life had begun in the form of anaerobic bacteria early in the Archean Eon, photosynthetic bacteria did not appear until the middle Archean and were not abundant until the start of the Proterozoic. The bacteria emitted oxygen. The atmosphere changed. The oceans changed. The oceans had been rich in dissolved ferrous iron, in large part put into the seas by extruding lavas of two billion years. Now with the added oxygen the iron became ferric, insoluble, and dense. Precipitating out, it sank to the bottom as ferric sludge, where it joined the lime muds and silica muds and other seafloor sediments to form, worldwide, the banded-iron formations that were destined to become rivets, motorcars and cannons. The is the iron of the Mesabi Range, the Australian iron of the Hammerslee Basin, the iron of Michigan, Wisconsin, Brazil. More than ninety percent of the iron ever mined in the world has come from Precambrian banded-iron formations. Their ages date broadly from twenty-five hundred to two thousand million years before the present. The transition that produced them — from a reducing to an oxidizing atmosphere and the associated radical change in the chemistry of the oceans — would be unique. It would never repeat itself. The earth would not go through that experience twice.

Death produces building and burning materials in an abundance that seems limitless, at least from standpoint of humans in the here and now. But every here and now ends. Realizing that is a vestigial feature of human sensibility.

Take for example, The World Has Plenty of Oil, which appeared in The Wall Street Journal ten years ago. In it, Nansen G. Saleri writes, “As a matter of context, the globe has consumed only one out of a grand total of 12 to 16 trillion barrels underground.” He concludes,

The world is not running out of oil any time soon. A gradual transitioning on the global scale away from a fossil-based energy system may in fact happen during the 21st century. The root causes, however, will most likely have less to do with lack of supplies and far more with superior alternatives. The overused observation that “the Stone Age did not end due to a lack of stones” may in fact find its match.

The solutions to global energy needs require an intelligent integration of environmental, geopolitical and technical perspectives each with its own subsets of complexity. On one of these — the oil supply component — the news is positive. Sufficient liquid crude supplies do exist to sustain production rates at or near 100 million barrels per day almost to the end of this century.

Technology matters. The benefits of scientific advancement observable in the production of better mobile phones, TVs and life-extending pharmaceuticals will not, somehow, bypass the extraction of usable oil resources. To argue otherwise distracts from a focused debate on what the correct energy-policy priorities should be, both for the United States and the world community at large.

In the long view of a planet that can’t replace any of that shit, this is the rationalization of a parasite. That this parasite can move on to consume other irreplaceable substances it calls “resources” does not make its actions any less parasitic.

Or, correctly, saprophytic; since a saprophyte is “an organism which gets its energy from dead and decaying organic matter.”

Moving on to coal, the .8 trillion tons of it in Wyoming’s Powder River Basin now contributes 40% of the fuel used in coal-fired power plants in the U.S. Here’s the biggest coal mine in the basin, called Black Thunder, as it looked to my camera in 2009:

About half the nation’s electricity is produced by coal-fired plants, the largest of which can eat the length of a 1.5-mile long coal train in just 8 hours. In Uncommon Carriers, McPhee says Powder River coal at current rates will last about 200 years.

Then what? Nansen Saleri thinks we’re resourceful enough to get along with other energy sources after we’re done with the irreplaceable kind.

I doubt it.

Wind, tide, and solar are unlikely to fuel aviation, though I suppose fresh biofuel might. Still, at some point, we must take a long view, or join our evolutionary ancestors in the fossil record faster than we might otherwise like.

As I fly in my window seat from place to place, especially on routes that take me over arctic, near-arctic, and formerly arctic locations, I see more and more of what geologists call “the picture”: a four-dimensional portfolio of scenes in current and former worlds. Thus, when I look at the seashores that arc eastward from New York City— Long Island, Block Island, Martha’s Vineyard, Nantucket, Cape Cod—I see a ridge of half-drowned debris scraped off a continent and deposited at the terminus of an ice cap that began melting back toward the North Pole only 18,000 years ago—a few moments before the geologic present. Back then, the Great Lakes were still in the future, their basins covered by ice that did not depart from the lakes’ northern edges until about 7,000 years ago or 5,000 B.C.

Most of Canada was still under ice while civilization began in the Middle East and the first calendars got carved. Fly over Canada often enough and the lakes appear to be exactly what they are: puddles of a recently melted cap of ice. Same goes for most of the ponds around Boston. Every inland swamp in New England and upstate New York was a pond only a few dozen years ago, and was ice only a dozen or so centuries before that. Go forward a few thousand years and all of today’s ponds will be packed with accumulated humus and haired over by woods or farmland. In the present, we are halfway between those two conditions. Here and now, the last ice age is still ending.

As Canada continues to thaw, one can see human activity spark and spread across barren lands, extracting “resources” from ground made free of permafrost only in the last few years. Doing that is both the economic and the pestilential thing to do.

On the economic side, we spend down the planet’s principal, and fail to invest toward interest that pays off for the planet’s species. That the principal we spend has been in the planet’s vaults for millions or billions of years, and in some cases cannot be replaced, is of little concern to those spending it, which is roughly all of us.

Perhaps the planet looks at our species the same way and cares little that every species is a project that ends. Still, in the meantime, from the planet’s own one-eyed perspective, our species takes far more than it gives, and with little regard for consequences. We may know, as Whitman put it, the amplitude of time. We also tend to assume in time’s fullness all will work out.

But it won’t.

Manhattan schist, the bedrock anchoring New York City’s tallest buildings, is a little over half a billion years old. In about the same amount of time, our aging Sun, growing hotter, will turn off photosynthesis. A few billion years later, the Sun will swell into a red giant with a diameter wider than Earth’s orbit, roasting the remains of our sweet blue planet and scattering its material out into the cosmos, perhaps for eventual recycling by stars and planets not yet formed.

In a much shorter run, many catastrophes will happen. One clearly is what our species is already doing to the planet during what geologists correctly call the Anthropocene. I suppose that’s a good reason for Elon and crew to “save” a few members of our vain little species. But why fuck up Mars before we’re done fucking up Earth, when there’s still some leverage with the death we have at home and that Mars won’t begin to have until stuff dies on it?

I’ve always been both an optimist and a realist. Specifically, I’m an optimist for at least the short run, by which I mean the next few dozen years. But I’m a pessimist for our civilization — and our species. Death is always a winning bet.

But hey, maybe nature knows better what to do with us than we do.

The first ancestor of this piece appeared in blogs.harvard.edu on 4 March 2008. The second is here on Medium.

View Details

I just returned to DALL-E 3 after using its Microsoft version (currently called Copilot | Designer) for a while. But I can’t get in.See how it says “Try in ChatGPT︎?” When I do that, it goes to https://chat.openai.com/. After I log in there, it offers no clue about where DALL-E 3 is. So I asked, “How do I get to the DALL-E 3 page after I’m logged in here?”

ChatGPT answered, “As of my last update in January 2022, DALL-E 3 is a hypothetical iteration of the DALL-E model, and there’s no information about its existence or how to access it. If it were to be released, you might typically find access through OpenAI’s website or platform if they make it available to the public. However, without further updates or announcements, it’s challenging to provide specific instructions. If OpenAI releases DALL-E 3 or any similar model in the future, you can check their official website or announcements for information on how to access it.”

Additional useless dialog followed. So now I’ll ask the Lazyweb. Does anyone know how to get into DALL-E 3?

View Details

Prompt: “a field of many different kinds of people being harvested by machines and turned into bales of fertilizer.” Via Microsoft CoPilot | Designer.This post is for the benefit of anyone wondering about, researching, or going into business on the proposition that selling one’s own personal data is a good idea. Here are some of my learnings from having studied this proposition myself for the last twenty years or more.

1. The business does exist. See eleven companies in Markets for personal data listed among many other VRM-ish businesses on the ProjectVRM wiki.
2. The business category harvesting the most personal data is adtech (aka ad tech and “programmatic”) advertising, which is the surveillance-based side of the advertising business. It is at the heart of what Shoshana Zuboff calls surveillance capitalism, and is now most of what advertising has become online. It’s roughly a trillion-dollar business. It is also nothing like advertising of the Mad Men kind. (Credit where due: old-fashioned advertising, aimed at whole populations, gave us nearly all the brand names known to the world). As I put it in Separating Advertising’s Wheat and Chaff, Madison Avenue fell asleep, direct response marketing ate its brain, and it woke up as an alien replica of itself.
3. Adtech pays nothing to people for their data or data about them. Not personally. Google may pay carriers for traffic data harvested from phones, and corporate customers of auctioned personal data may pay publishers for moments in which ads can be placed in front of tracked individuals’ ears or eyeballs. Still, none of that money has ever gone to individuals for any reason, including compensation for the insults and inconveniences the system requires. So there is little if any existing infrastructure on which paying people for personal data can be scaffolded up. Nor are there any policy motivations. In fact,
4. Regulations have done nothing to slow down the juggernaut of growth in the adtech industry. For Google, Facebook, and other adtech giants, paying huge fines for violations (of the GDPR, the CCPA, the DMA, or whatever) is just the cost of doing business. The GDPR compliance services business is also in the multi-$billion range, and growing fast. In fact,
5. Regulations have made the experience of using the Web worse for everyone. Thank the GDPR for all the consent notices subtracting value from every website you visit while adding cognitive overhead and other costs to site visitors and operators. In nearly every case, these notices are ways for site operators to obey the letter of the GDPR while violating its spirit. And, although all these agreements are contracts, you have no record of what you’ve agreed to. So they are worse than worthless.
6. Tracking people without their clear and conscious invitation or a court order is wrong on its face. Period. Full stop. That tracking is The Way Things Are Done online does not make it right, any more than driving drunk or smoking in crowded elevators was just fine in the 1950s. When the Digital Age matures, decades from now, we will look back on our current time as one thick with extreme moral compromises that were finally corrected after the downsides became clear and more ethically sound technologies and economies came along. One of those corrections will be increasing personal agency rather than just corporate capacities. In fact,
7. Increasing personal independence and agency will be good for markets, because free customers are more valuable than captive ones. Having ways to gather, keep, and make use of personal data is an essential first step toward that goal. We have made very little progress in that direction so far. (Yes, there are lots of good projects listed here, but there we still a long way to go.)
8. Businesses being “user-centric” will do nothing to increase customers’ value to themselves and the marketplace. First, as long as we remain mere “users” of others’ systems, we will be in a subordinate and dependent role. While there are lots of things we can do in that role, we will be able to do far more if we are free and independent agents. Because of that,
9. We need technologies that create and increase personal independence and agency. Personal data stores (aka warehouses, vaults, clouds, life management platforms, lockers, and pods) are one step toward doing that. Many have been around for a long time: ProjectVRM currently lists thirty-three under the Personal Data Stores heading. Some have been there a long time. The problem with all of them is that they are still too focused on what people do as social beings in the Web 2.0 world, rather than on what they can do for themselves, both to become more well-adjusted human beings and more valuable customers in the marketplace. For that,
10. It will help to have independent personal AIs. These are AI systems that work for us, exclusively. None exist yet. When they do, they will help us manage the personal data that fully matters:
    • Contacts—records and relationships
    • Calendars—where we’ve been, what we’ve done, with whom, where, and when
    • Health records and relationships with providers, going back all the way
    • Financial records and relationships, including past and present obligations
    • Property we have and where it is, including all the small stuff
    • Shopping—what we’ve bought, plan to buy, or might be thinking about,
    • Subscriptions—what we’re paying for, when they end or renew, what kind of deal we’re locked into, and what better ones might be out there.
    • Travel—Where we’ve been, what we’ve done, with whom, and when

Personal AIs are today where personal computers were fifty years ago. Nearly all the AI news today is about modern mainframe businesses: giants with massive data centers churning away on ingested data of all kinds. But some of these models are open sourced and can be made available to any of us for our own purposes, such as dealing with the abundance of data in our own lives that is mostly out of control. Some of it has never been digitized. With AI help it could be.

I’m in a time crunch right now. So, if you’re with me this far, read We can do better than selling our data, which I wrote in 2018 and remains as valid as ever. Or dig The Intention Economy: When Customers Take Charge (Harvard Business Review Press, 2012), which Tim Berners Lee says inspired Solid. I’m thinking about following it up. If you’re interested in seeing that happen, let me know.

View Details

Bloomington Hospital on October 15, 2022, right after demolition began.After we came to Bloomington in the summer of 2021, we rented an apartment by Prospect Hill, a quiet dome of old houses just west of downtown. There we were surprised to hear, nearly every night, as many police and ambulance sirens as we’d heard in our Manhattan apartment. Helicopters too. Soon we realized why: the city’s hospital was right across 2nd Street, a couple blocks away. In 2022, the beautiful new IU Health Bloomington Hospital opened up on the far side of town, and the sounds of sirens were replaced by the sounds of heavy machinery slowly tearing the old place down.

Being a photographer and a news junkie, I thought it would be a good idea to shoot the place often, to compile a chronicle of demolition and replacement, as I had done for the transition of Hollywood Park to SoFi Stadium in Inglewood, California. But I was too busy doing other things, and all I got was that photo above, which I think Dave Askins would categorize as a small contribution to topical history.

Dave is a highly productive local journalist, and—by grace of providence for a lifelong student of journalism such as me—the deepest and most original thinker I know on the topic of what local news needs in our time—and going forward. I’ve shared some of Dave’s other ideas (and work) in the News Commons series, but this time I’m turning a whole post over to him. Dig:::::

In the same way that every little place in America used to have a printed newspaper, every little place in America could have an online local chronicle.

Broadly speaking, an online local chronicle is a collection of facts organized mostly in chronological order. The “pages” of the chronicle can be thought of as subsets of a community’s universal timeline of events. These online local chronicles could become the backbone of local news operations.

First a word about what a local chronicle is not. It is not an online encyclopedia about the little place. It’s not a comprehensive history of the place in any conventional sense. Why should it not try to be those things? Because those things are too hard to think about building from scratch. Where would you even start?

It is at least conceivable that an online local chronicle could be built from scratch because you start by adding new facts that are newsworthy today. A new fact added to the chronicle is a touchstone, about which anyone can reasonably ask: What came just before that?

A working journalist in a little place with an online local chronicle will be in a good position to do two things: (1) add new facts to the local chronicle (2) help define sets of old facts that would be useful to include in the online local chronicle.

A journalist who is reporting the news for a little place would think not just about writing a report of new facts for readers today. They would keep this question in mind: What collection of old facts, if they were included in the local chronicle, would have made this news report easier to write?

Here’s a concrete example. A recent news report written for The B Square Bulletin included a mention of a planned new jail for Monroe County. It included a final sentence meant to give readers, who might be new to that particular topic, a sense of the basic reason why anyone was thinking about building a new jail: “A consultant’s report from two and a half years ago concluded that the current jail is failing to provide constitutional levels of care.”

About that sentence, a reader left the following comment on the website: “I know it’s the last sentence in an otherwise informative article, but at the risk of nit-picking that sentence seems inadequate to the task of explaining the context of the notion of a new jail and the role of the federal court and the ACLU.”

The comment continues: “It would have been better, Dave, to link to your own excellent previous work: https://bsquarebulletin.com/2023/02/20/monroe-county-sheriff-commissioners-square-off-at-committee-meeting-aclu-lawyer-says-look-you-need-a-new-jail-everyone-knows-that/”

What this reader did was to identify a set of old facts that should be a collection (a page) in Bloomington’s local chronicle.

It’s one thing to identify a need to add a specific collection of facts to the local chronicle. It’s quite another to figure out who might do that. Working journalists might have time to add a new fact or two. But to expect working journalists to add all the old sets of facts would, I think, be too tall an order.

The idea would be to recruit volunteers to do the work of adding old facts to the online local chronicle. They could be drawn from various segments of the community—including groups that have an interest in seeing the old facts about a particular topic not just preserved, but used by working journalists to help report new facts.

I think many community efforts to build a comprehensive community encyclopedia have foundered, because the motivation to make a contribution to the effort is mostly philosophical: History is generally good to preserve.

The motivation for helping to build the online local chronicle is not some general sense of good purpose. Rather it is to help working journalists provide useful facts for anyone who in the community who is trying to make a decision.

That includes elected leaders. They might want to know what the reasons were at the time for building the current jail at the spot where it is now.

Decision makers include voters, who might be trying to decide which candidate to support.

Decision makers also include rank-and-file residents—who might be trying to decide where to go out for dinner and want to know what the history of health inspections for a particular restaurant are.

For the online local chronicle I have set up for Bloomington, there are very few pages so far. They are meant to illustrate the general concept:

https://thebloomingtonchronicle.org/index.php/Main_PageThe pages are long on facts that are organized in chronological order, and short on narrative. Here are the categories that include at least one page.

Category: People
Category: Data
Category: Boards, Commissions, Councils
Category: List
Category: Topical History

==========

–Dave

By the way, if you’d like to help local journalism out, read more about what Dave is up to—and what he needs—here: https://bsquarebulletin.com/about/

View Details

Bloomington, Indiana, my new hometown

How do people get news where you live? How do they remember it?

For most of the industrial age, which is still with us, newspapers answered both those questions—and did so better than any other medium or civic institution. Newspapers were required reading, delivered daily to doorsteps, and sold from places all around town. Old copies also accumulated in libraries and other archives, either as bound volumes or in microfilm reels and microfiche cards. News also came from radio and TV stations, though both did far less archiving, and none were as broad and deep in what they covered and how. Newspapers alone produced deep news.

And wide news as well. Local and regional papers covered politics, government, crises, disasters, sports, fashion, travel, business, religion, births, deaths, schools, and happenings of all kinds. They had reporters assigned across all their sections. No other medium could go as wide.

After the Internet showed up in the mid-’90s, however, people also began getting news from each other, through email, blogs, texting, online-only publications, and social media. To keep up and participate, newspapers, magazines, and other legacy print media built websites and began to publish online. Broadcast media began to stream online too. But the encompassing trend was the digitization of everything and everyone. Consumers became producers. Every person with a computer or a phone was equipped to become a reporter, a photographer, a videographer, or a podcaster. (In the 24 September 2004 issue of IT Garage, I reported that a Google search for podcasts got 24 results. Today it gets 3,84 billion.)

In the midst of all this, the local and regional newspaper business collapsed. The New York Times, Wall Street Journal, and Washington Post found ways to survive and continue to thrive. Many other major papers are getting along but none are what they were. Nor can they be. Today most local papers are gone or shrunk to tiny fractions of their former selves. Countless local commercial radio stations are now owned by national chains, fed “content” from elsewhere, and maintain minimized or absent local staff. Public radio has survived mostly because it learned long ago how to thrive on listener contributions, bequests, and institutional support. TV news is still alive, but also competing with millions of other sources of video content. None of its coverage is as wide as newspapers were in their long prime.

Another reason for the decline of local news media is economic. Craigslist and its imitaters killed newspapers’ classified sections, which had been a big source of income. Advertisers abandoned the practice of targeting whole populations interested in sports, business, fashion, entertainment, and other subjects. With digital media, advertisers can target tracked individuals. As I put it in Separating Advertising’s Wheat and Chaff, “Madison Avenue fell asleep, direct response marketing ate its brain, and it woke up as an alien replica of itself.” That replica cares not a whit for supporting journalism of any kind.

Eyeballs and eardrums were also pulled toward direct response marketing by algorithms rigged to increase engagement. A collateral effect was pulling individual interests into affinity groups that grew tribal as they became echo chambers favoring the voices that excelled at eliciting emotional responses. Naturally, media specialized for feeding tribal interests emerged, obsolescing media that worked to cross partisan divides—such as old-fashioned newspapers. (In the old days, papers with a bend to the left or the right isolated partisanship to their opinion pages.) Talk radio and cable news became entirely partisan operations.

So, by the time Scott Adams (of Dilbert fame) said “Facts don’t matter. What matters is how much we hate the person talking” (March 13, 2022), what Yeats poetized in The Second Coming seemed fulfilled:

Things fall apart; the centre cannot hold;
Mere anarchy is loosed upon the world,
The blood-dimmed tide is loosed, and everywhere
The ceremony of innocence is drowned;
The best lack all conviction, while the worst
Are full of passionate intensity.

And yet, as James Fallows told my wife and me a couple of months ago, if you talk to people in small towns about anything but politics, they’re just fine. Moreover, they still work together and get things done. (Jim and Deb gained this wisdom while researching their book and movie, both titled Our Towns.)

Towns do have their fault lines, but people everywhere are held together by their natural need for the conveniences that arise out of shared necessity—for markets, medical help, education, public spaces, and each other. They also need good information about what’s going on where they live. By good I mean the kind of information they used to get before newspapers—and the daily ceremony of innocence newspapers provided—were obsolesced by the Internet.

Back in the mid-’00s, the idea of “citizen journalism” (which went by other labels) first showed up in the writings of Dan Gillmor, J.D. Lasica, Dave Winer, Jeff Jarvis, Jay Rosen, myself, and others. All of us were also concerned about the decline of newspapers. So, in January 2007, after The New York Times sold the Santa Barbara News-Press to a billionaire who fired the staff and made the paper a vehicle for her personal interests, the Center for Information Technology and Society (CITS) at UC Santa Barbara convened a charrette to discuss the future of local newspapers. The title was “Newspaper 2.0.” It was led by yours truly, then (and still) a fellow of the Center. Some of the people mentioned earlier in this paragraph were there, along with exiled News-Press staffers, educators, and other local media, including “place blogs” that were also daily newsletters. Here is a photo series from the event, which was reported on positively in several places online that now seem to be gone. (I hope some are in the Internet Archive, which I haven’t finished searching.)

I don’t know to what extent that gathering helped expand the degree to which other media made up for the failure of the News-Press (which finally filed for bankruptcy this summer, after a decade and a half of irrelevance). I do know that Santa Barbara is now something of a news commons, with lots of sources covering lots of topics. Not everything gets covered, but a lot does. I’ll know better when I get back there and talk to local reporters about it. (I can at least say that Santa Barbara is the leading public radio market in the country—or at least was when I last checked in 2019. Public stations there have widened news in the region enormously.)

Meanwhile, my full attention is here in Bloomington, Indiana. Our local newspaper, the Herald-Times, is still alive and kicking, but not what it was when giant rolls of paper were delivered by train car weekly to the back of the paper’s building at 1900 South Walnut Street, and it was the source of wide news for the town and the region.

Now it’s e pluribus unum time. There are many other media in town, covering many topics, and I’m not yet clear on how much they comprise a news commons. But, as a visiting scholar (along with my wife Joyce) at Indiana University’s Ostrom Workshop, which is all about studying commons, I want to see if our collection of local news media can become an example of wide news at work, whether we call it a commons or not. From my current notes, here is a quick, partial, and linky list of local media—

Periodicals (including newsletters and websites):

• The Herald-Times
• B Square Bulletin
• The Bloomingtonian
• IDS
• Bloom
• The Ryder
• Visit Bloomington
• Bloomington Online
• Hoosleft (also a podcast)

Radio:

• WFHB (has local news and podcasts)
• WFIU (has local news and podcasts)
• WIUX (IU student station, has local stuff)
• WGCL (legacy local radio, AM & FM)
• WBWB (B97) (pop music, has local news, sister of WHCC)
• WTTS (legacy Tarzian FM music station, broadcasting from Trafalgar, on the south side of Indianapolis, with a popular local translator of its HD2 channel called Rock96 The Quarry)
• WHCC (local country station, has some local news, sister of WBWB)
• WCLS (local album rock station, has a calendar)

TV:

• WTTV-4 CBS (licensed to Bloomington )
• WTHR-13 NBC
• WTIU-33 PBS
• WRTV-6 ABC (has local Bloomington news on its website)
• WXIN (Fox 59) (has local Bloomington news on its website)
• WISH-8 CW

Podcasts

• NoDishes
• Beyond BTown
• Unspoken Requests

Indiana University

• IU Media School
• (Note that every department—Sociology, Law, Sports, Medicine, Music, and many others—make and report on local happenings)

Civic Institutions:

• Monroe County Public Library
• Monroe County History Center
• Greater Bloomington Chamber of Commerce

So my idea is to hold a charrette like the one we had in Santa Barbara, to see how those interested in making wide news better can get along. No rush. I just want to put the idea out there and see what happens.

I think one thing that will help is that nobody is trying to do it all anymore. But everybody brings something to the table. Metaphorically speaking, I’d like to put the table there.

Thoughts and ideas are invited. So are corrections and improvements to the above. I see this post, like pretty much everything I write online, as a public draft.

My email is doc at searls dot com.

I shot the photo above on a flight from Indianapolis to Houston after giving this lecture at IU. Here is a whole series on Bloomington from that flight. And here is the rest of the flight as well. All the photos in both are Creative Commons licensed to encourage use and reuse, by anybody. I have about 60,000 photos such as these published online here, and another 5,000 here, all ready for anyone to put in a news story. I bring this up because public photography is one of my small contributions to wide news everywhere. You can see results in countless news stories and at Wikimedia Commons, where photos in Wikipedia come from. I put none of those where they are. Others found them and put them to use.

View Details

Were it left to me to decide whether we should have a government without newspapers, or newspapers without a government, I should not hesitate to prefer the latter. — Thomas Jefferson News is the first rough draft of history. — … Continue reading →

View Details

From 2007 until about a month ago, I wrote on three blogs that lived at blogs.harvard.edu. There was my personal blog (this one here), ProjectVRM’s blog (also its home page), and Trunkline, a blog about infrastructure that was started by … Continue reading →

View Details

So I thought I’d give Bing a try at using ChatGPT to answer a question I had. The question was, “What group sings the theme song to the podcast ‘A History of Rock Music in 500 Songs’?” Bing search took … Continue reading →

View Details

I wrote this today for a list that’s mostly populated by folks in overlapping music, broadcasting, legal, tech, and other businesses who share a common interest in what’s happening to the arts and artists they care about in a world … Continue reading →

View Details

When I was a kid in the 1950s and early 1960s, AM was the ruling form of radio, and its transmitters were beyond obvious, taking the form of towers hundreds of feet high, sometimes in clusters formed to produce directional … Continue reading →

View Details

I’ll be talking shortly to some readers of The Intention Economy who are looking for ways to connect that economy with advertising. (Or so I gather. I’ll know more soon.) What follows is the gist of what I wrote to … Continue reading →

View Details

Welcome to my new old blog. My old-old (but not oldest) blog—the one I’ve written since 2007—is still there, in complete archival form, at blogs.harvard.edu/doc, where it has always been. It is now also here with a different URL: doc.searls.com, … Continue reading →

View Details

I started this blog in August 2007 after the host for my original blog went away. (That blog has been preserved, however. Find it at http://weblog.searls.com.) At the time I was told something like “Hey, Harvard has been around since 1636, so your blog will last a long time here.” Well, the duration will be […]

View Details

This blog has been looking like my personal obituary section, and I suppose it is. While I promise to change that, for this post I’ll stick with the theme a bit, and surface some correspondence with an old friend who recommended that I read The Five People You’ll Meet in Heaven, by Mitch Albom. In […]

View Details

My email archive contains dozens of postings in which Heather Armstrong* and I are among those writing, receiving, mentioning, mentioned, cc’d or otherwise included. Most postings are from the ’00s and between bloggers in the brief age before media got social and blogging was still hot shit. Heather, with her Dooce blog, was the alpha among us, but never snotty about it.

Heather wore her heart, her head, her life, on the Web page. At humorous, opinionated, and wince-worthy self-disclosure, Heather even out-raged Chris Locke, aka RageBoy. Heather, Chris and I might have met for a panel at the 2006 SXSW, had Chris made the trip. Wrote Chris, “I was nearly as bummed as Doc said he was that I wasn’t there in Austin today on the ‘Cluetrain: Seven Years Later’ panel. What can I say? If God had wanted people to fly, he would have given them upgrades.” Best I recall, that panel was the only time I met Heather in person. She was fun.

Her final post was on April 6. It is mostly about, and for, her daughter Leta Louise. The closing line is “Here at 18 months sober, I salute my 18-year-old frog baby, she who taught me how to love.” According to news reports, Heather had fallen off the wagon. Whatever the reason, she fell all the way, and we will be forever lessened by her loss.

*On her Instagram, Facebook and Twitter accounts, all branded Dooce, she identified as Heather B. Hamilton, her birth name.

View Details

I asked ChatGPT for a three-day itinerary to give visitors to Santa Barbara. Here ya go:

Day 1:

• Start the day with breakfast at the Shoreline Beach Cafe, which has a beautiful view of the ocean.
• After breakfast, head to Knapp’s Castle for a scenic hike and exploration of the ruins of a 20th century mansion. The hike offers stunning views of the Santa Ynez Valley.
• For lunch, grab some sandwiches or salads from the nearby Panino’s, a local favorite with fresh, high-quality ingredients.
• Spend the afternoon exploring downtown Santa Barbara, with its charming shops and cafes. Don’t miss a visit to the Santa Barbara County Courthouse, a stunning Spanish Colonial Revival building with a beautiful clock tower that offers a panoramic view of the city.
• For dinner, head to Tee-Off, a local institution that has been serving up classic American fare since 1949.

Day 2:

• Start the day with a hike up La Cumbre Peak, which offers stunning views of Santa Barbara and the Channel Islands.
• For lunch, grab some tacos from La Super-Rica Taqueria, a casual spot that was a favorite of Julia Child.
• Spend the afternoon exploring the Santa Barbara Botanic Garden, which showcases native plants and offers a peaceful escape from the city.
• For dinner, head to the Stagecoach Inn, a historic restaurant that serves up classic American fare in a cozy setting.

Day 3:

• Start the day with breakfast at Jeannine’s Bakery, a local favorite known for its delicious baked goods and breakfast items.
• Spend the morning at Hendry’s Beach, a local favorite with beautiful views and great walking trails.
• For lunch, grab some sandwiches or salads from South Coast Deli, a local favorite with fresh ingredients and creative flavor combinations.
• Spend the afternoon exploring the Santa Barbara Museum of Art, which features a diverse collection of artwork from around the world.
• For dinner, head back to downtown Santa Barbara and choose from one of the many restaurants in the area, depending on your preference. Some options include Olio e Limone Ristorante, Los Agaves, and The Lark.

I wouldn’t disagree with any of it, except maybe to note that Hendry’s Beach at sunset (where and when I shot the photo above) is mighty fine.

Of course, the answer will vary with every regeneration, but what the hell. It’s very early in our co-evolution with whatever the hell we and AI are together becoming.

View Details

Her name is Mary Johnson. Born in 1917, the year the U.S. entered WWI, two years before women in the same country got the right to vote, she died in 1944, not long before the end of WWII. She was buried, unembalmed, in the cemetery of a Chicago church that was later abandoned. Her grave was unmarked. To make room for new commercial development in 2023, the church was razed and occupants of the cemetery were respectfully and quietly disinterred, and moved to a working cemetery elsewhere in town. In the midst, efforts were made by the coroner’s office to discover the identities of the bodies from unmarked graves before they were to be reburied. Mary’s was among them.

The difference with Mary was that her body appeared to be unchanged: a bit dusty under bits of casket lining, with light flecks on her dark skin. Except for that, she looked like she had died yesterday. When they removed her body from the casket in the hospital morgue where she was taken for DNA sampling, she was still flexible. I asked the pathologist what would account for her perfect state of preservation. The pathologist said she had no idea. Even the best embalming jobs age in the ground.

When the pathologist was out of the room, I reached to lift one of Mary’s eyelids. Before my fingers touched, both lids opened, slightly. I called out, “Come here! Come here!” Nobody came. Then both eyes opened. Her body shook as she tried to breathe.

“Code Blue! I yelled.

She was alive. Somehow, alive. After what, eighty years? At the time we didn’t know.

I was ready to do CPR when she started breathing and tried to sit up. “Hang on,” I said. Let me help.” As I did, she was becoming warm. She stood up and looked around.

I looked at my watch. It was 5:15 AM. The dream was too interesting for me to completely awaken, so I dropped back in. As a half-conscious dreamer, I often do that. For the next hour, I followed several different story threads. Each visited what happened in the eighty years of Mary’s suspended life. The Cold War. israel. Civil rights. Rock & Roll. Space travel. Disco. Hip hop. Rap. Digital everything. One of her questions: “What’s television?”

I thought about the backstory of her own short life: a child in the twenties, a teen during the Depression, a young adult during The War. What interesting stuff happened in those years? Was she in love, maybe with a guy who went off to fight? What work did she do?

I thought about the science questions. How was it possible for someone to lay undead for so long? Who else in that cemetery, or any cemetery, might still be alive? Was she a one-of-one, a one-of-some, or a one-of-many? Though not a horror story, it did recall Poe’s The Premeture Burial, in which the protagonist’s undead state was “catalepsy.” I imagined in this thread that the story might be one Michael Chrichton would like to write, if he was still alive.

Dreams have no more detail than one gives them, and being a white guy from New Jersey, born after Mary went cataleptic, I didn’t have much to furnish any storyline about Mary’s life, past or present. But I could still think of questions to address. What perspective and wisdom could Mary bring to our time? How would she cope with finding nearly all the people and things she knew were now dead and gone? What would she marvel at, and what would appall her? What would she be, or mean, to the rest of us?

No surprise that I would dream of a resurrection on Easter morning, even though that wasn’t in my head at the time. So, might Mary (not hard to guess from what corner of my unconscious that one came from) be a Jesus for our time? Hmm.

At 6:15, I finally had to get up and do my business, and the dream ended there. Still, “This has to be a book,” I told myself. But I have other books to write, ones that have sat half-written for years. And writing fiction isn’t my thing. So I decided I’d blog it instead. And here we are.

She is alive now, on this page, and in your mind. All she needs is for someone to finish her story.

The image above is courtesy of DALL-E, the artificially creative image generator. Took four tries to get this one. Since DALL-E seems to know only how to make grotesque faces, I made sure the woman here is looking away.

View Details

While discussing ChatGPT with my teenage grandkids, I put it to a number of tests. In one I asked it to write a poem that includes all the capital cities in the U.S. Here is its reply:

From sea to shining sea, Across this land so grand, The capitals of every state, Await us to take a stand.

In Montgomery, Alabama, We begin our noble quest, To climb each statehouse staircase, And put our wills to the test.

Through Juneau, Alaska, To Phoenix, Arizona’s heat, The halls of power beckon us, With challenges we must meet.

Little Rock, Arkansas, And Sacramento, too, We march to their state capitals, To learn what they can do.

From Denver, Colorado’s heights, To Connecticut’s Hartford town, We cross this land of liberty, To see our nation’s crown.

Dover, Delaware, And Tallahassee, Florida’s heat, We journey forth to find our place, In every statehouse seat.

Atlanta’s Georgia peach, And Honolulu’s island breeze, We’ll walk the halls of power, To achieve our lofty dreams.

Through Boise, Idaho’s hills, And Springfield’s Illinois pride, We’ll take the steps of governance, With courage as our guide.

Indianapolis, Indiana, And Iowa’s Des Moines, We’ll stand in every capital, To honor each state’s joins.

From Topeka’s Kansas plains, To Kentucky’s Frankfort pride, We’ll learn from every leader, In whom we can confide.

Baton Rouge, Louisiana, And Augusta, Maine’s coast, We’ll listen to the wisdom, That each statehouse host.

In Annapolis, Maryland, And Massachusetts’ Boston town, We’ll seek to find our purpose, And rise to wear the crown.

Lansing, Michigan, And St. Paul’s Minnesota pride, We’ll climb each capital’s staircase, And never be denied.

Mississippi’s Jackson town, And Jefferson City’s Missouri call, We’ll cross this land with honor, And never falter or fall.

Helena, Montana’s heights, And Lincoln’s Nebraska plains, We’ll march through every capital, And honor each state’s gains.

Carson City, Nevada, And Concord’s New Hampshire pride, We’ll stand in every statehouse, And let our voices be our guide.

Trenton’s New Jersey call, And Santa Fe’s New Mexico sun, We’ll climb the stairs of governance, And learn from everyone.

Albany’s New York pride, And Raleigh’s North Carolina charm, We’ll honor every state’s glory, And never let it harm.

Bismarck’s North Dakota plains, And Columbus’ Ohio pride, We’ll journey forth to every capital, With honor as our guide.

Oklahoma’s Oklahoma City, And Salem’s Oregon call, We’ll stand in every statehouse, And never let our spirits fall.

Harrisburg, Pennsylvania, And Rhode Island’s Providence town, We’ll climb each capital’s staircase, And never let ourselves drown.

South Carolina’s Columbia pride, And South Dakota’s Pierre call, We’ll cross this land with dignity, And never let ourselves stall.

Nashville’s Tennessee music, And Austin’s Texas pride, We’ll stand in every statehouse, And let our voices rise.

Salt Lake City’s Utah heights, And Montpelier’s Vermont pride, We’ll march through every capital, And let our dreams be our guide.

Richmond’s Virginia charm, And Olympia’s Washington crown, We’ll honor every state’s valor, And never let ourselves down.

Charleston’s West Virginia hills, And Madison’s Wisconsin pride, We’ll journey forth to every capital, And never be denied.

Cheyenne’s Wyoming pride, And Washington, D.C.’s White House, We’ll cross this land with honor, And never let ourselves douse.

From sea to shining sea, We’ve walked each statehouse hall, And learned the lessons of governance, That make our nation stand tall.

Redraw your own conclusions.

View Details

I shoot a lot of pictures. Most are from altitude (such as the above). But lots are of people and places, for example, here are a few I shot at DWebCamp last summer:

Importing and curating photos is the only organized thing I do in life. Let me explain.

Under each of those photos is the name of the file. These are the actual file names, not ones stored in the library of some app and remembered at the meta-level. None are called DSCN0401.JPG, IMG_4523.JPG, or IMG_1874.PNG. I’ve given all of them meaningful names, all by the same convention: YYYY_MM_DD_name-of-event. Every file in every folder has the same name as the folder, with a number appended to it. The numbers are chronological. Each event’s folder goes into a month folder, each of those goes into a year folder, and all years go into a folder called pix-by-year. That folder has years going back to 1869. (The earliest are scans, such as this one.)

I organize and name all my photos with a piece of software originally called iView Media Pro, then Expression Media 2 (after Microsoft bought it), and finally Phase One Media Pro (after Microsoft abandoned it). I like the second version best, so that’s what I use.

Here is a short and partial list of all the things Expression Media 2 can do:

1. Rename files in the Finder, very selectively, alone, or in batches (much more smoothly and easily than can be done with Adobe Bridge or Apple’s Shortcuts or Automator).
2. Search for any variable, or combination of variables
3. Sort by up to 24 variables (file name, size, date created, date modified…)
4. Resize selectively
5. Open any files with any other app
6. Run a slide show, with many choices of presentation (much more than with Apple’s Photos), and save shows as movies
7. Open any file or collection of files in any other app (for me that’s usually Photoshop 2021)
8. Basic image edits
9. Rotate, flip, zoom in and out
10. See and edit EXIF data for every shot
11. Find missing and duplicate items
12. Show or hide any file or combinations of files
13. Move files in the Finder
14. Operate in lieu of the finder when dragging or dropping into a Web page or another app
15. Arrange or tile photos by hand or by sort
16. Log and show actions
17. Place images on a map
18. Make a .pdf of any image or collection of them
19. Turn galleries into pages in .html
20. Import and export to and from .xml

I don’t do all that stuff, but I list it because I want to remember what I fear I will lose when I move from this 2017 MacBook Pro running Mojave to my new 16″ 2023 M2 Max MacBook Pro. That will happen later today after I upgrade both machines to the latest version of Ventura. When that happens, Expressions Media 2, a 32-bit program last updated in 2009, will be kaput. And I will need to find another workflow.

Maybe Expression Media 2 will survive through emulation or something. Or maybe Phase One Media Pro (last updated in 2013) will work.

Or maybe one of ya’ll has a better way to manage workflow than I’m using now. I’m open.

Meanwhile, here goes…

Addendum: If you’re wondering why I’m not running my life on Linux and free and/or open-source software, the main reasons are Photoshop and Lightroom. I’ve tried Gimp and it doesn’t cut it. Photoshop knows the camera and lenses I’m using, and its tools, such as dehaze, are extremely useful. See the photos here? Thank dehaze for making the detail pop out. (Yes, Gimp de-hazes, but not easily.) Shooting as much as I do requires tools I can use quickly and easily.

View Details

Glenn Fleishman has a lucid and helpful introduction to Mastodon in TidBITS that opens with this:

Cast your mind back to the first time you experienced joy and wonder on the Internet. Do you worry you’ll never be able to capture that sense again? If so, it’s worth wading gently into the world of Mastodon microblogging to see if it offers something fresh and delightful. It might remind you—as it does me, at least for now—of the days when you didn’t view online interactions with some level of dread.

Mastodon isn’t a service but a network of consensually affiliated, independently operated servers running the Mastodon software. It’s the best-known example of the so-called Fediverse…

Then, a few paragraphs later, he provides the best metaphor I’ve yet seen for what Mastodon is and how it works:

You can think of Mastodon as a flotilla of boats of vastly different sizes, whereas Twitter is like being on a cruise ship the size of a continent. Some Mastodon boats might be cruise liners with as many as 50,000 passengers; others are just dinghies with a single occupant! The admin of each instance—the captain of your particular boat—might make arbitrary decisions you disagree with as heartily as with any commercial operator’s tacks and turns. But you’re not stuck on your boat, with abandoning ship as the only alternative. Instead, you can hop from one boat to another without losing your place in the flotilla community. Parts of a flotilla can also splinter off and form their own disconnected groups, but no boat, however large, is in charge of the community.

Since my day job is working as a visiting scholar in the Ostrom Workshop at Indiana University, and Customer Commons has been imagined from its start as a potential commons for customers (or as many commons, flotilla style), I find myself wondering if each of Mastodon’s boats is a commons. Or if some of them could be, or already are. Or if Mastodon itself is one.

My first experience with Mastodon came early on, in a boat that I abandoned before it sank. But now that Mastodon is hot again, I’ve jumped with two crowds onto two boats: twit.social (here) and journa.host (here). TWiT.social’s occupants are the community of hosts, co-hosts, and participants in the TWiT network. Journa.host’s occupants are a collection of journalists. The two communities are different, though not entirely: journalists abound in both of them.

The question for me here is if any of these boats qualify as a commons. Or if Mastodon itself is one.

To qualify as a commons, a canonical list to check off is provided by Elinor Ostrom. In Governing the Commons (Cambridge, 1990), she outlined eight “design principles” for stable local common pool resource (CPR) management. I’ll make notes following each in italics:

1. Clearly defining the group boundaries (and effective exclusion of external un-entitled parties) and the contents of the common pool resource. Mastodon is designed to support that.
2. The appropriation and provision of common resources that are adapted to local conditions. If we’re talking about code, yes. Maybe more. Gotta think about that.
3. Collective-choice arrangements that allow most resource appropriators to participate in the decision-making process. Depends on the instance, I suppose.
4. Effective monitoring by monitors who are part of or accountable to the appropriators. Not sure about that one.
5. A scale of graduated sanctions for resource appropriators who violate community rules. Up to the person or people running each boat.
6. Mechanisms of conflict resolution that are cheap and of easy access. I think these range from informal to formal, and draw from rules developed for mailing lists and other fora. But, not sure.
7. Self-determination of the community recognized by higher-level authorities. At the top level, it’s othe Mastodon dev community. At the boat (instance) level, it’s the captain(s) of each.
8. In the case of larger common-pool resources, organization in the form of multiple layers of nested enterprises, with small local CPRs (common pool resources) at the base level. A thought: the common pool resource is the authors of posts (aka toots) and the posts themselves.

Ostrom and others have also gone deeper and wider than that, for example by examining socio-ecological systems (SESes), defined here in 2004. I’ll leave digging into that up to scholars more schooled than I (or to a later post, after I finish schooling myself). Meanwhile, I think it’s important, given the sudden growth of Mastodon and other federated systems with flotilla-ish qualities, to examine how deep research and writing on commons apply.

This work does matter: Ostrom won a Nobel Prize for it, and it may matter more now than ever.

And help is welcome.

About the photo up top: Lacking a royalty-free visual for a flotilla of boats, I settled on the collections of people you see through bubbles in the photo above, which I shot on the grounds of Versailles. Kinda works, methinks.

View Details

That’s a question that was asked on Quora and deleted before I posted my answer. So I’m posting the answer here.

This is like asking if a car radio sounds better than a TV. Because it’s a matter of where, how, and when, more than a matter of sound.

There is some overlap in the sense that both SiriusXM and YouTube are fully useful on mobile apps. But you don’t watch your radio in your car or listen to your radio on your TV, even though it’s possible to do both through apps that are native to both the road and the living room.

As for the sound itself, YouTiube has an edge in the sense that you can select audio quality bitrates up to 256kbps AAC & OPUS. SiriusXM’s default bitrate is also 256kpbs, but over the satellite link is typically lower—sometimes much lower. But, since SiriusXM does not (to my knowledge, so far) publish their bitrates in a place that’s easy to find, the bitrates are subject to debate. Here is one on Reddit.

But, again, it’s a matter of where and when more than of how. If you want to see and hear a piece of music, YouTube provides enormous optionality over what you can see and hear. If you want radio-like programming music, SiriusXM offers more.

Yet the Internet has more than both put together. That’s why the image above is of Radio Paradise, which is one of the oldest and best Internet music stations. It’s live on the Net and the Web, and it has Best Of collections on YouTube as well.

View Details

Gibraltar Peak isn’t the highest landform overlooking Santa Barbara, but it provides an excellent vantage for FM stations looking for unobstructed population coverage. And now, thanks to the massive rains earlier this week, the road to Gibraltar Peak is closed, and many of the FM stations transmitting from there are off the air. Here’s a list I just put together, based on my listening:

• 88.7 KDRW, which mostly relays KCRW from Santa Monica
• 89.5 KSBX, which relays KCBX from San Luis Obispo
• 89.9 K210AD, which relays KPCC from Pasadena by way of KJAI from Ojai
• 90.3 KMRO-1, a booster for KMRO in Camarillo
• 91.5 K218CP, which relays KAWZ from Twin Falls, Idaho
• 97.9 K230BS, which relays KTMS/990 AM in Santa Barbara*
• 102.3 KK272DT, the FM side of KCLU/1340 in Santa Barbara and KCLU/88.3 in Thousand Oaks

KDB/93.7, also on Gibraltar Peak, but closer to Gibraltar Road, is still on the air, as are KTMS/990AM, KTYD/99.9FM and K231CR, which relays KOSJ/1490AM, all of which are farther up Gibraltar Road.

So far, only one local medium is on the case: The Santa Barbara Independent: https://www.independent.com/2023/01/11/gibraltar-peak-towers-out-of-commission. I haven’t seen anything yet in Edhat, Noozhawk, or the Santa Barbara News-Press.

The Independent says the site is a “relay” one. That’s right only in the sense that most of the stations there are satellites of main stations elsewhere. But KCLU especially is local to Santa Barbara (and has its main AM station here), and the ratings reflect it. I wrote about those ratings a few years ago, in Where Public Radio Rocks. In that post, I noted that public radio is bigger here than anywhere else in the country. KCLU’s FM signal is especially popular, even though it’s only a translator.

Anyway, I’ll put up more on the topic after I’m back from errands.

View Details

Most of California has just two seasons: rain and fire. Rain is another name for Winter, and it peaks in January. In most years, January in California isn’t any more wet than, say, New York, Miami or Chicago. But every few years California gets monsoons. Big ones. This is one of those years.

The eighteen gallon storage tub in our yard is sixteen inches deep and serves as a rain gauge:

Yesterday morning it was less than half full. While it gathered rain, our devices blasted out alerts with instructions like this:

So we stayed home and watched the Web tell us how the drought was ending:

Wasn’t long ago that Lake Cachuna was at 7%.

So that’s good news. The bad news is about floods, ruined piers and wharfs, downed trees, power outages, levee breaches. The usual.

It should help to remember that the geology on both coasts is temporary and improvisational. The East Coast south of New England and Long Island (where coastal landforms were mostly dumped there or scraped bare by glaciers in the geologic yesterday) is a stretch of barrier islands that are essentially dunes shifted by storms. Same goes for the Gulf Coast. The West Coast looks more solid, with hills and mountains directly facing the sea. But Pacific storms in Winter routinely feature waves high as houses, pounding against the shores and sea cliffs.

Looking up the coast from Tijuana, within a few hundred years Coronado and Point Loma in San Diego, La Jolla, all the clifftop towns up the coast to Dana Point and Laguna, Palos Verdes Peninsula, Malibu and Point Dume, Carpinteria, the Santa Barbara Mesa and Hope Ranch, all of Isla Vista and UCSB, Pismo and Avila Beaches, all of Big Sur and the Pacific Coast Highway there, Carmel and the Monterey Peninsula, Aptos, Capitola and Santa Cruz, Davenport, Half Moon Bay, Pacifica, the headlands of San Francisco, Muir and Stimson Beaches and Bolinas in Marin, Fort Bragg in Mendicino County, and Crescent City in Humbolt—all in California—will be eaten away partially or entirely by weather and waves. Earthquakes will also weigh in.

The photo up top is of La Conchita, a stupidly located town on the South Coast, west of Ventura, four days after a landslide in 2005 took out 13 homes and killed 10 people. All the land above town is a pile of former and future landslides, sure to slide again when the ground is saturated with water. Such as now or soon.

So that’s a long view. For one that spans the next week, visit windy.com and slide the elevation up to FL (flight level) 340 (34000 feet):

That yellow river of wind is a jet stream hauling serious ass straight across the Pacific and into California. Jet streams are why the headwinds and tailwinds you see on seat-back displays showing flight progress on planes often say 100mph or more. Look at Windy before you fly coast to coast or overseas, and you can guess what the flight path will be. You can also see why it may take as little as five hours to get from Dulles to Heathrow, or more than seven hours to come back by a route that touches the Arctic Circle. Your plane is riding, fighting or circumventing high altitude winds that have huge influences on the weather below.

To see how, drop Windy down to the surface:

Those eddies alongside the jet stream are low pressure centers full of the moisture and wind we call storms. They spin along the sides of the jet stream the way dust devils twist up along the sides of highways full of passing trucks. Those two storm centers are spinning toward California and will bring more wind and rain.

Beside the sure damage those will bring, there will be two benefits. One is that California will be as green as Ireland for a few months. The other is that wildflowers will bloom all over the place.

The Death Valley folks are hedging their bet, but I’d put money on a nice bloom this Spring. Watch for it.

View Details

We live in the Anthropocene, a geological epoch defined by the influence of one species over everything else, including the planet itself. That species is ours, and we are a pestilential one, altering, consuming, and wasting everything we can.

Specifically, our civilizations have advanced on the planet like a cancer, parasitically metabolizing materials we call “resources” (without their permission) as if their sums were not finite. Oil and coal will be gone in a few hundred years. Uranium, titanium, tungsten, helium, lithium and other members of the periodic table may be gone far sooner, thanks to our boundless appetites. And yes, we can make raise crops of corn and other plants to make fuel for cars and jets, but only at the costs monoculture place on the biodiversity required for sustaining every form of life.

I bring all this up because we’ll be talking about it on Monday at this month’s Ostrom Workshop salon at Indiana University and live on the Web. Our speaker will be Vinay Gupta (@leashless), inventor of the Hexayurt refugee shelter, founder and CEO of Mattereum, a progenitor of Ethereum, and source of wisdom on all that and much else. The title of his talk is the headline above. His case is that we have to get our per-person environmental consumption down by about 10x.

It helps that there are peoples and regions in the world providing living examples of how that is done. Vinay is deeply familiar with those, and will share what he knows in ways that help us co-think and work to save the planet’s butt, along with our own.

The salon is at 2 PM Eastern time. It is also free, but you need to register first, here.

If this follows the pattern of our prior salons—all with the theme Beyond the Web—the presentation and discussion will be lively, informative, and productive. See you there.

View Details

Rackspace is in a crater right now, on fire.

So are many of its customers. I’m one of them.

What happened, Rackspace says, was “the result of a ransomware incident.” Damaged, lost or destroyed is its Hosted Exchange business. On that cloud platform, companies and individuals around the world run their email and much else.

It’s quite a saga.

The first report from Rackspace came at 11:49pm Pacific (where I am) on Thursday, posted on its Incidents page:

We are investigating an issue that is affecting our Hosted Exchange environments. More details will be posted as they become available.

Updates got more wordy as the outage continued. About a day later, a long posting said,

We proactively powered down and disconnected the Hosted Exchange environment while we triaged to understand the extent and the severity of the impact. After further analysis, we have determined that this is a security incident.

They also offered a lifeline of sorts:

At no cost to you, we will be providing access to Microsoft Exchange Plan 1 licenses on Microsoft 365 until further notice. At no cost to you, we will be providing access to Microsoft Exchange Plan 1 licenses on Microsoft 365 until further notice. To activate, please use the below link for instructions on how to set up your account and users.

For reasons not worth going into, this was useless to me. But I’m also just one guy, and almost all of Rackspace’s customers are businesses with more to lose.

Getting help from Rackspace quickly became difficult or impossible, while details about the situation were minimal, until this morning (6 December), when they said it was a ransomware incident. Which countless tweets had been suggesting from the start.

Here is what Rackspace said it was doing about it:

Alongside our internal security team, we have engaged a leading cyber defense firm to investigate. Our investigation is still in its early stages, and it is too early to say what, if any, data was affected. If we determine sensitive information was affected, we will notify customers as appropriate.

No FBI? CIA? NSA? DHS? Police? My guess is that at least two of those have been notified because it would make sense for them to be involved. But I’m sure abundant caution on Rackspace’s part is the reason we’re not hearing about any of that.

As for notifying customers, good luck. In a posting two days ago, Rackspace said,

For those who are finding the process challenging and are awaiting support, we ask for your patience as we increase staff to help every customer. Since our last update, we have mobilized roughly 1000 support Rackers to reduce wait times and address ticket queues. We will continue to accelerate and deploy even more resources to further help customers.

Search for Rackspace+wait on Twitter to see how that’s going.

Yesterday morning I chose the “we’ll call you back asap” option at the Rackspace support number, after calling them fruitlessly before that. Since then, crickets. Meanwhile, I’ve been working almost non-stop on moving my email hosting to Hover, which answers the phone quickly and is always helpful.

Of course, I haven’t been able to export anything from Rackspace, and I have growing doubts that I ever will. If the failure is total, many details of my life in the digital world will be lost forever.

One bit of good fortune is that my wife and sister, who both also have searls.com email addresses, were on Rackspace’s basic non-Exchange email service. Since that was still working today, we could export their mail archive from Rackspace as .mbox files, and start new accounts for them on Hover. (Ironically, I moved to Rackspace’s Exchange service because I punched through the basic service’s 25Gb limit on storage, and they sold me on the Exchange service’s better security.)

Ramsomware is bad shit. If you’re Rackspace or one of its customers, there is plenty to fear.

But the larger story here isn’t about Rackspace or its customers. It’s about the cloud business, which is beyond massive.

I’ve been looking for examples of cloud failures that are bigger than this one. Here’s a list from five years ago. Here is one from July of this year. Here is one from August. Most list disruptions lasting hours. This one has been going on for five days with no end in sight.

So let’s imagine that Rackspace and its customers are stuck in that crater, and it just keeps burning. For years. What are the lessons from that?

View Details

That was Bill Swindaman on the last day I saw him: June 2nd of this year, at a gathering of friends from the best community I’ve ever known: a real one, of friends living in a place. The place was called Oxbow, and it was a collection of mismatched houses on a short dirt road […]

View Details

So far the experience of using Twitter under Musk is pretty much unchanged. Same goes for Facebook. Yes, there is a lot of hand-wringing, and the stock market hates Meta (the corporate parent to which Facebook gave birth); but so far the experience of using both is pretty much unchanged. This is aside from the fact […]

View Details

I wrote this more than a quarter century ago when Linux Journal was the only publication that would have me, and I posted unsold essays and wannabe columns at searls.com. These postings accumulated in this subdirectory for several years before Dave Winer got me to blog for real, starting here. Interesting how much has changed since I wrote […]

View Details

Let’s say you want to improve the Wikipedia page for Clayton Indiana with an aerial photograph. Feel free to use the one above. That’s why I shot it, posted it, and licensed it permissively. It’s also why I put a helpful caption under it, and some call-outs in mouse-overs. It’s also why I did the […]

View Details

In July 2008, when I posted the photo above on this blog, some readers thought Santa Barbara Mission was on fire. It didn’t matter that I explained in that post how I got the shot, or that news reports made clear that the Gap Fire was miles away. The photo was a good one, but it […]

View Details

It’s one thing to move off centralized online spaces run by corporate giants, and another to settle the decentralized frontiers where we create new communities. As those communities get organized, forms of governance emerge. Or are deliberately chosen. Either way, the subject could hardly matter more, if those communities wish to persist and thrive. At this […]

View Details

It’s P7012: Standard for Machine Readable Personal Privacy Terms, which “identifies/addresses the manner in which personal privacy terms are proffered and how they can be read and agreed to by machines.” P7012 is being developed by a working group of the IEEE. Founded in 1963, the IEEE is the largest association of technical professionals in the world […]

View Details

Hollywood Park Racetrack is gone. In its place is SoFi Stadium, the 77,000-seat home of Los Angeles’ two pro football teams and much else, including the 6,000-seat YouTube Theater. There’s also more to come in the surrounding vastness of Hollywood Park, named after the racetrack. Wikipedia says the park— consists of over 8.5 million square feet (790,000 m2) […]

View Details

In one of his typically trenchant posts, titled Attentive, Scott Galloway (@profgalloway) compares human attention to oil, meaning an extractive commodity: We used to refer to an information economy. But economies are defined by scarcity, not abundance (scarcity = value), and in an age of information abundance, what’s scarce? A: Attention. The scale of the […]

View Details

That’s the flyer for the first salon in our Beyond the Web Series at the Ostrom Workshop, here at Indiana University. You can attend in person or on Zoom. Register here for that. It’s at 2 PM Eastern on Monday, September 19. And yes, all those links are on the Web. What’s not on the Web—yet—are all […]

View Details

One morning a couple months ago, while I was staying at a friend’s house near Los Angeles, I was surprised to find the Los Angeles Times still being delivered there. The paper was smaller and thinner than it used to be, with minimized news, remarkably little sports, and only two ads in the whole paper. […]

View Details

Twelve years ago, I posted The Data Bubble. It began, The tide turned today. Mark it: 31 July 2010. That’s when The Wall Street Journal published The Web’s Gold Mine: Your Secrets, subtitled A Journal investigation finds that one of the fastest-growing businesses on the Internet is the business of spying on consumers. First in a series. It has ten […]

View Details

A visitor to aerial photos on my Flickr site asked me where one should sit on a passenger plane to shoot pictures like mine. This post expands on what I wrote back to him. Here’s the main thing: you want a window seat on the side of the plane shaded from the Sun, and away […]

View Details

I used to tell Craig Burton there was no proof that he could be killed, because he came so close, so many times. But now we have it. Cancer got him, a week ago today. He was sixty-seven. So here’s a bit of back-story on how Craig and I became great friends. In late 1987, […]

View Details

via Nick Youngson CC BY-SA 3.0 Pix4free.org Let’s start with what happened to TV. For decades, all TV signals were “over the air,” and free to be watched by anyone with a TV and an antenna. Then these things happened:  Community Antenna TeleVision, aka CATV, gave us most or all of our free over-the-air channels, plus many […]

View Details

I’ve been blogging since 1999, first at weblog.searls.com, and since 2007 here. I also plan to continue blogging here* for the rest of my life. But it’s clear now that newsletters are where it’s at, so I’m going to start one of those. The first question is, What do I call it? The easy thing, and […]

View Details

Marcus Smart. Photo by Eric Drost, via Wikimedia Commons. Back in 2016, I correctly predicted that the Cleveland Cavaliers would win the NBA finals, beating the heavily favored Golden State Warriors, which had won a record 73 games in the regular season. In 2021, I incorrectly predicted that the Kansas City Chiefs would beat the Tampa […]

View Details

Chemistry is a good metaphor for how teams work—especially when times get tough, such as in the playoffs happening in the NBA right now. Think about it. Every element has a melting point: a temperature above which solid turns liquid. Basketball teams do too, only that temperature changes from game to game, opponent to opponent, and […]

View Details

I did a lot of shooting recently with a rented Sony FE 70-200mm F2.8 GM OSS II lens, mounted on my 2013-vintage Sony a7r camera. One result was the hummingbird above, which you’ll find among the collections here and here. Also, here’s a toddler… …and a grandma (right after she starred as the oldest alumnus at a […]

View Details

When digital identity ceases to be a pain in the ass, we can thank Kim Cameron and his Seven Laws of Identity, which he wrote in 2004, formally published in early 2005, and gently explained and put to use until he died late last year. Today, seven of us will take turns explaining each of […]

View Details

My father was always Pop. He was born in 1908. His father, also Pop, was born in 1863. That guy’s father was born in 1809, and I don’t know what his kids called him. I’m guessing, from the chart above, it was Pa. My New Jersey cousins called their father Pop. Uncles and their male […]

View Details

Throughout the entire history of what we call media, we have consumed its contents on producers’ schedules. When we wanted to know what was in newspapers and magazines, we waited until the latest issues showed up on newsstands, at our doors, and in our mailboxes. When we wanted to hear what was on the radio […]

View Details

The photo above dates from early 1978, when Hodskins Simone & Searls, a new ad agency, was born in Durham, North Carolina. Specifically, at 602 West Chapel Hill Street. Click on that link and you’ll see the outside of our building. Perhaps you can imagine the scene above behind the left front window, because that’s […]

View Details

While walking past this scene on my way to the subway in New York last week, I saw that a woman was emptying out what hadn’t burned from this former car. Being a curious extrovert, I paused to ask her about it. The conversation, best I recall: “This your car?” “Yeah.” “I’m sorry. What happened?” […]

View Details

“Compared to war, all other forms of human endeavor shrink to insignificance. God help me, I do love it so.” — George S. Patton (in the above shot played by George C. Scott in his greatest role.) Is the world going to croak? Put in geological terms, will the Phanerozoic eon, which began with the […]

View Details

There’s a thread in a list I’m on titled “NFTs are a Scam.” I know too little about NFTs to do more than dump here three thoughts I shared on the list in response to a post that suggested that owning digital seemed to be a mania of some kind. Here goes… First, from Walt Whitman, […]

View Details

Back in 2009 I shot the picture above from a plane flight on approach to SFO. On Flickr (at that link) the photo has had 16,524 views and has been faved 420 times as of now. Here’s the caption: These are salt evaporation ponds on the shores of San Francisco Bay, filled with slowly evaporating […]

View Details

In faith that nothing lasts forever, and that an institution that’s been around since 1636 is more likely to keep something published online for longer than one that was born in 1994 and isn’t quite dead yet (and with full appreciation to the latter for its continued existence), I’ve decided to re-publish some of my […]

View Details

If you’re getting health care in the U.S., chances are your providers are now trying to give you a better patient experience through a website called MyChart.

This is supposed to be yours, as the first person singular pronoun My implies. Problem is, it’s TheirChart. And there are a lot of them. I have four (correction: five*) MyChart accounts with as many health care providers, so far: one in New York, two in Santa Barbara, one in Mountain View, and one in Los Angeles. I may soon have another in Bloomington, Indiana. None are mine. All are theirs, and they seem not to get along. Especially with me. (Some later correction on this below, and from readers who have weighed in. See the comments.)

Not surprisingly, all of them come from a single source: Epic Systems, the primary provider of back-end information tech to the country’s health care providers, including most of the big ones: Harvard, Yale, Mayo, UCLA, UChicago, Duke, Johns Hopkins, multiple Mount Sinais, and others like them. But, even though all these MyChart portals are provided by one company, and (I suppose) live in one cloud, there appears to be no way for you, the patient, to make those things work together inside an allied system that is truly yours (like your PC or your car is yours), or for you to provide them with data you already have from other sources. Which you could presumably do if My meant what it says.

The way they work can get perverse. For example, a couple days ago, one of my doctors’ offices called to tell me we would need to have a remote consult before she changed one of my prescriptions. This, I was told, could not be done over the phone. It would need to be done over video inside MyChart. So now we have an appointment for that meeting on Monday afternoon, using MyChart.

I decided to get ahead of that by finding my way into the right MyChart and leaving a session open in a browser tab. Then I made the mistake of starting to type “MyChart” into my browser’s location bar, and then not noticing that the top result was one of the countless other MyCharts maintained by countless other health care providers. But this other one looked so much like one of mine that I wasted an hour or more, failing to log in and then failing to recover my login credentials. It wasn’t until I called the customer service number thankfully listed on the website that I found I was trying to use the MyChart of some provider I’d never heard of—and which had never heard of me.

Now I’m looking at one of my two MyCharts for Santa Barbara, where it shows no upcoming visits. I can’t log into the other one to see if the Monday appointment is noted there, because that MyChart doesn’t know who I am. So I’m hoping to unfuck that one on Monday before the call on whichever MyChart I’ll need to use. Worst case, I’ll just tell the doctor’s office that we’ll have to make do with a phone call. If they answer the phone, that is.

The real problem here is that there seem to be hundreds or thousands of different health care providers, all using one company’s back end to provide personal health care information to millions of patients through hundreds or thousands of different portals, all called the same thing (or something close), while providing no obvious way for patients to gather their own data from multiple sources to use for their own independent purposes, both in and out of that system. Or any system.

To call this fubar understates the problem.

Here’s what matters: Epic can’t solve this. Nor can any or all of these separate health care systems. Because none of them are you.

You’re where the solution needs to happen. You need a simple and standardized way to collect and manage your own health-related information and engagements with multiple health care providers. One that’s yours.

This doesn’t mean you need to be alone in the wilderness. You do need expert help. In the old days, you used to get that through your primary care physician. But large health care operations have been hoovering up private practices for years, and one of the big reasons for that has been to make the data management side of medicine easier for physicians and their many associated providers. Not to make it easier for you. After all, you’re not their customer. Insurance companies are their customers.

In the midst of this is a market hole where your representation in the health care marketplace needs to sit. I know just one example of how that might work: the HIE of One. (HIE is Health Information Exchange.) For all our sakes, somebody please fund that work.

Far too much time, sweat, money, and blood is being spilled trying to solve this problem from the center outward. (For a few details on how awful that is, start reading here.)

While we’re probably never going to make health care in the U.S. something other than the B2B insurance business it has become, we can at least start working on a Me2B solution in the place it most needs to work: with patients. Because we’re the ones who need to be in full command of our relationships with our providers as well as with ourselves.

Health care, by the way, is just one category that cries out for solutions that can only come from the customers’ side. Customer Commons has a list of fourteen, including this one.

The first of these is identity. The self-sovereign approach to that would start with a wallet that is truly mine, and includes all these MyCharts. Hell, Epic could do one. Hint hint.

Okay, now it’s Monday, and I’m a half-hour away from my consult with my doctor, via Zoom, inside MyChart. Turns out I was not yet registered with this* MyChart, but at least there was a phone number I could call, and on the call (which my phone says took 14 minutes) we got my ass registered. He also pointed me to where, waaay down a very long menu, there is a “Link my accounts” choice, which brings up this:

Credit where due:

It was very easy to link my four known accounts, plus another (the one in Mountain View) that I had forgotten but somehow the MyChart master brain remembered. I suspect, given all the medical institutions I have encountered in my long life, that there are many more. Because in fact I had been to the Mountain View hospital only once, and I don’t even remember why, though I suppose I could check.

So that’s the good news. The bad news remains the same. None of these charts are mine. They are just views into many systems that are conditionally open to me. That they are now federated (that’s what this kind of linking-up is called) on Epic’s back end does not make it mine. It just makes it a many-theirs.

So the system still needs to be fixed. From our end.

View Details

That’s the UI for the Brother HL-L2305w laser printer, which you can get for $140 right now at OfficeMax (or Office Depot, same thing). It’s a good deal. It also took me a whole day to set up.

See, it comes with instructions that say to use the UI above to make CONNECTING WLAN happen. It doesn’t. Instead it sits for awhile, says TIMED OUT, and then prints out a page that says “The WLAN access point/router cannot be detected,” and gives instructions to locate the printer as close as possible to your wi-fi (that’s the WLAN) access point, to make sure you’re not using MAC address filtering or other secure things that might prevent connection.

After parking an access point (we have four in our house, all connected by Ethernet through a switch to the cable modem) right on top of the printer, I gave up, assumed it was bad, took it back and swapped it for another that had the same problem, meaning I was dealing with a feature.

Then, after failing to find help in the Brother Product Support Center, I registered the printer and logged in as a now-known customer. In that state I was able to chat with an entity (human, it seemed, but ya never know) who pointed me to a page with useful instructions, plus a video that’s also on YouTube, where I should have looked in the first place. Lesson re-learned.

So, if you get one, go straight to that YouTube link and save a lot of trouble/

View Details

Just learned Wayne Thiebaud died, at 101. I didn’t know he was still alive. But I did know he had a lot of influence, most famously on pop art. Least famously, on me.

Many of Thiebaud’s landscapes were from aerial perspectives. For example, this—

—and this:

In me, those influenced this—

—and this—

—and this—

—and this—

—and this—

—and this—

—and this—

—and even this:

Like Thiebaud, I love the high angle on the easily overlooked, and opportunity for revelations not obtainable from the ground, or in the midst.

Example. Can you guess where these mountains are?

Try Los Angeles. I shot that, as I did the others in this album, during the approach to LAX on a flight from Houston.

Here’s another shot in that series:

That’s 10,068-foot Mt. San Antonio, aka Old Baldy, highest of the San Gabriel Mountains. These are Los Angeles’ own Alps, which wall the north side of the L.A. basin, thwarting sprawl in that direction. The view is up San Antonio Canyon, below which lays a suburb-free delta of rocks and gravel spreading outward from canyon’s mouth. Across that mouth, and in a series of of similar ones below is a dam. These are for slowing “debris flows” coming out of the mountains after heavy rains, and sorting the flows’ contents into boulders, rocks, and gravel. Businesses that trade in these geological goods are also sited there. Imagine a business selling fresh lava from the base of a volcano, and you have some idea of how rapidly the geology changes here.

Anyway, while there is Thiebaud-informed art to that shot, there is also a purpose: I want people to see how these mountains are alive and dangerous in ways unlike no others flanking a city.

My main influence toward that purpose is John McPhee, the best nonfiction writer ever to walk the Earth—and report on it. Dig Los Angeles Against the Mountains. Doesn’t get better than that.

McPhee is 90 now. I dread losing him.

View Details

The Cluetrain Manifesto had four authors but one voice, and that was Chris Locke‘s.

Cluetrain, a word that didn’t exist before Chris (aka RageBoy), David Weinberger, Rick Levine and I made it up during a phone conversation in early 1999 (and based it on a joke about a company that didn’t get clues delivered by train four times a day), is now tweeted constantly, close to 23 years later. (And by now belongs in the OED.)

In his book The Tipping Point, which was published the same month as The Cluetrain Manifesto (January, 2000), Malcolm Gladwell said, “the success of any kind of social epidemic is heavily dependent on the involvement of people with a particular and rare set of social gifts.” He also called this “the Law of the Few.” Among those few, one needed three kinds of people: mavens, connectors, and salespeople. Chris was all three. To different degrees so were David, Rick and myself; but Chris was the best, especially at connecting. He was the one who brought us together. And he was the one who sold us on making something happen. He moved us from one Newtonian state to another—a body at rest to a body in motion—by sending us this little graphic:

After we got that, we had to put up the Cluetrain website. And then we had to expand that site into a book, thanks to the viral outbreak of interest that followed a column about the site—and Chris especially, face and all—in The Wall Street Journal. Though a great enemy of marketing-as-usual, nobody was better than Chris at spreading a word. I mean, damn: dude got Cluetrain in the fucking Wall Street Journal! (Huge hat tip to Tom Petzinger for writing that column, and for writing the book’s forward as well.

Want to know Chris’s marketing techniques? Read Gonzo Marketing: Winning Through Worst Practices, which followed Cluetrain, and had the best cover ever, with bullet holes (actual holes) through a barcode, and a red page behind it. I’m sure Chris came up with that idea. His graphic sense was equally creative, sharp and—as with everything—outrageous.

Or listen to the audio version, performed by Chris in his perfect baritone voice.

Alas, Chris died yesterday, after a long struggle with COPD. (Too much smoke, for too long. Got my dad and my old pal Ray too. That cigarette smoking has become unfashionable is a grace of our time.)

Good God, what a great writer Chris was. Try Winter Solstice. One pull-quote: “We learn to love the lie we must tell ourselves to survive.”

And his stories. OMG, were they good. Better than fiction, and all true.

For example, you know how, when two people are first getting to know each other, they exchange stories about parts of their lives? I remember once telling Chris that my parents were frontier types who met in Alaska. While I thought that would take us down an interesting story hole (my parents really were interesting people), Chris blasted open a conversational hole of his own the size of a crater: “My father was a priest and my mother was a nun.” Top that.

Once, when I missed a plane from SFO to meet Chris in Denver, I mentioned that I was standing next to a strangely wide glass wall at my just-vacated gate in Terminal 1. “I know that gate well,” he said. “And that glass is a trip. I once missed a plane there myself while I was on acid and got totally into that glass wall.” I don’t remember what he said after that, except that it was outrageous (for anyone but Chris) and I couldn’t stop laughing as his story went on.

Among too many other stories to count, here is one I hope his soul forgives me for lifting (along with that picture of him) from a thread on Facebook:

on this Father’s Day I am recalling getting drunk with MY dad on Christmas Eve 1968, as was our custom back then (this month I am 34 years sober). he told me he was suicidal and i knew he meant it. so I turned him on to acid there and then. it was a bit of a rocky trip, but things were better for him after that.

btw, when the trip got really rough, I tricked him into thinking he could fall asleep. “If you want to come down, just take six of these big bomber multivitamin pills and that’ll be it.” fat chance! but he fell sound asleep. as I sat next to him marveling at the sound of guardian angel wings softly beating over us, THE PHONE RANG!!! OMG. at like 4am! and worse, it was my judgmental hyper-Catholic MOTHER!! she said…

hello, is your father over there

….yes… I said.

are you two taking LSD?

oh no! had she gone psychic??

….yes… I said, fearful of what was coming next.

THANK GOD, she said. SOMETHING had to give.

and then:

“well, have a good trip,” she said, and rang off.

I’ll leave you with this, from a post on Chris’s Rageboy blog called Dust My Boom. It was written on the occasion of an odd wind coming toward Boulder that now seems prophetic toward the future that came three days ago when a wind-driven fire swept across the landscape, eventually roasting close to 600 homes, a hotel, and a shopping center. Read the whole thing for more about the wind…

There’s so much you don’t know about me. Cannot ever, no matter how hard I try to make it otherwise. I have been places, done things impossible to recount. I remember nights of love, each different from all the rest. I have sat beside the dead in the room with the open windows. I have seen those ships on fire off Orion’s shoulder.

Yeah well. I wrote something into the cluetrain manifesto that must have raised some eyebrows among our more knowing cousins. And it went like this:

…People of Earth The sky is open to the stars. Clouds roll over us night and day. Oceans rise and fall. Whatever you may have heard, this is our world, our place to be. Whatever you’ve been told, our flags fly free. Our heart goes on forever. People of Earth, remember. So I should end this now, but that’s way too dramatic and drama is the wrong note to end on. I think I need to put in something ordinary here, pedestrian. A joke maybe. A duck walks into a bar…

Because, whatever it is, it’s just the normal regular passage of time. Nothing mystical. Nothing shocking. We are born. We grow old. We die. In between, we sometimes get a glimpse of something. If I knew what it was, I’d tell you in a second. I don’t know. Take this piece of writing as my prayer flag flapping out in the wind of a day that came on sideways. Who knows where it’s headed? Tomorrow I have a con-call at noon, a website to build, and forty-one phone calls to return. Possibly lunch.

What I do know is that if you’re lonely and you’re hurting, then you’re human. What am I telling you this for? Hell if I know. To cheer you up maybe. Let me know if it worked.

And remember the man who said all that, and so much more. He was here for real, and he is missed.

View Details

This is about credit where due, and unwanted by the credited. I speak here of Kim Cameron, a man whose modesty was immense because it had to be, given the size of his importance to us all.

See, to the degree that identity matters, and disparate systems getting along with each other matters—in both cases for the sakes of each and all—Kim’s original wisdom and guidance matters. And that mattering is only beginning to play out.

But Kim isn’t here to shake his head at what I just said, because (as I reported in my prior post) he passed last week.

While I expect Kim’s thoughts and works to prove out over time, the point I want to make here is that it is possible for an open and generous person in a giant company to use its power for good, and not play the heavy doing it. That’s the example Kim set in the two decades he was the top architect of Microsoft’s approach to digital identity and meta systems (that is, systems that make disparate systems work as if just one).

I first saw him practice these powers at the inaugural meeting of a group that called itself the Identity Gang. That name was given to the group by Steve Gillmor, who hosted a Gillmor Gang podcast (here’s the audio) on the topic of digital identity, on December 31, 2004: New Years Eve. To follow that up, seven of the nine people in that podcast, plus about as many more, gathered during a break at Esther Dyson‘s PC Forum conference in Scottsdale, Arizona, on March 20, 2005. Here is an album of photos I shot of the Gang, sitting around an outside table. (The shot above is one of them.) There was a purpose to the meeting: deciding what we should do next, for all of the very different identity-related projects we were working on—and for all the other possible developments that also needed support.

Kim was the most powerful participant, owing both to his position at Microsoft and for having issued, one by one, Seven Laws of Identity, over the preceding months. Like the Ten Commandments, Kim’s laws are rules which, even if followed poorly, civilize the world.

Kim always insisted that his Laws were not carved on stone tablets and that he was no burning bush, but those laws were, and remain, enormously important. And I doubt that would be so without Kim’s 200-proof Canadian modesty.

The next time the Identity Gang met was in October of that year, in Berkeley. By then the gang had grown to about a hundred people. Organized by Kaliya (IdentityWoman) Young, Phil Windley, and myself (but mostly the other two), the next meeting was branded Internet Identity Workshop (IIW), and it has been held every Fall and Spring since then at the Computer History Museum (and, on three pandemic occasions, online), with hundreds, from all over the world, participating every time.

IIW is an open space workshop, meaning that it consists entirely of breakouts on topics chosen and led by the participants. There are no keynotes, no panels, no vendor booths. Sponsor involvement is limited to food, coffee, free wi-fi, projectors, and other graces that carry no other promotional value. (Thanks to Kim, it has long been a tradition for Microsoft to sponsor an evening at a local restaurant and bar.) Most importantly, the people attending from big companies and startups alike are those with the ability to engineer or guide technical developments that work for everyone and not for just those companies.

I’m biased, but I believe IIW is the most essential and productive conference of any kind, in the world. Conversations and developments of many kinds are moved forward at every one of them. Examples of developments that might not be the same today but for IIW include OAuth, OpenID, personal clouds, picos, SSI, VRM, KERI, and distributed ledgers.

I am also sure that progress made around digital identity would not be the same (or as advanced) without Kim Cameron’s strong and gentle guidance. Hats off to his spirit, his laws, and his example.

View Details

Got word yesterday that Kim Cameron had passed.

Hit me hard. Kim was a loving and loved friend. He was also a brilliant and influential thinker and technologist.

That’s Kim, above, speaking at the 2018 EIC conference in Germany. His topics were The Laws of Identity on the Blockchain and Informational Self-Determination in a Post Facebook/Cambridge Analytica Era (in the Ownership of Data track).

The laws were seven:

1. User control and consent
2. Minimum disclosure for a constrained use
3. Justifiable parties
4. Directed identity (meaning pairwise, known only to the person and the other party)
5. Pluralism of operators
6. Human integration
7. Consistent experience across contexts

He wrote these in 2004, when he was still early in his tenure as Microsoft’s chief architect for identity (one of several similar titles he held at the company). Perhaps more than anyone at Microsoft—or at any big company—Kim pushed constantly toward openness, inclusivity, compatibility, cooperation, and the need for individual agency and scale. His laws, and other contributions to tech, are still only beginning to have full influence. Kim was way ahead of his time, and its a terrible shame that his own is up. He died of cancer on November 30.

But Kim was so much more—and other—than his work. He was a great musician, teacher (in French and English), thinker, epicure, traveler, father, husband, and friend. As a companion, he was always fun, as well as curious, passionate, caring, gracious. Pick a flattering adjective and it likely applies.

I am reminded of what a friend said of Amos Tversky, another genius of seemingly boundless vitality who died too soon: “Death is unrepresentative of him.”

That’s one reason it’s hard to think of Kim in the past tense, and why I resisted the urge to update Kim’s Wikipedia page earlier today. (Somebody has done that now, I see.)

We all get our closing parentheses. I’ve gone longer without closing mine than Kim did before closing his. That also makes me sad, not that I’m in a hurry. Being old means knowing you’re in the exit line, but okay with others cutting in. I just wish this time it wasn’t Kim.

Britt Blaser says life is like a loaf of bread. It’s one loaf no matter how many slices are in it. Some people get a few slices, others many. For the sake of us all, I wish Kim had more.

Here is an album of photos of Kim, going back to 2005 at Esther Dyson’s PC Forum, where we had the first gathering of what would become the Internet Identity Workshop, the 34th of which is coming up next Spring. As with many other things in the world, it wouldn’t be the same—or here at all—without Kim.

Bonus links:

• Kim’s official obituary
• Rest in Peace, Kim Cameron, by Joerg Resch
• Remembering Kim Cameron, by Phil Windley
• Remembering a Human, Being, by Britt Blaser
• Cannibal Lobsters and Stolen Fingerprints – remembering Kim Cameron, by Mary Branscombe
• Stories of Kim Cameron, by Mike Jones

View Details

In Students are told not to use Wikipedia for research. But it’s a trustworthy source, Rachel Cunneen and Mathieu O’Niel nicely unpack their case for the headline. In a online polylogue in response to that piece, I wrote,

“You always have a choice: to help or to hurt.” That’s what my mom told me, a zillion years ago. It applies to everything we do, pretty much.

The purpose of Wikipedia is to help. Almost entirely, it does. It is a work of positive construction without equal or substitute. That some use it to hurt, or to spread false information, does not diminish Wikipedia’s worth as a resource.

The trick for researchers using Wikipedia as a resource is not a difficult one: don’t cite it. Dig down in references, make sure those are good, and move on from there. It’s not complicated.

Since that topic and comment are due to slide down into the Web’s great forgettery (where Google searches do not go), I thought I’d share it here.

View Details

Long ago a person dear to me disappeared for what would become eight years. When this happened I was given comfort and perspective by a professor of history whose study concentrated on the American South after the Civil War.

“You know what the most common record of young men was, after the Civil War?” he asked.

“You mean census records?”

“Yes, and church records, family histories, all that.”

“I don’t know.”

“Two words: Went west.”

He then explained that that, except for the natives here in the U.S., nearly all of our ancestors had gone west. Literally or metaphorically, voluntarily or not, they went west.

More importantly, most were not going back. Many, perhaps most, were hardly heard from again in the places they left. The break from the past in countless places was sadly complete for those left behind. All that remained were those two words: went west.

This fact, he said, is at the heart of American rootlessness.

“We are the least rooted civilization on Earth,” he said. “This is why we have the weakest family values in the world.”

This is also why he also thought political talk about “family values” was especially ironic. We may have those values, but they tend not to keep us from going west anyway.

This comes to mind because I just heard Harry Chapin‘s “Cat’s in the Cradle” for the first time in years, and it hurt to hear it. (Give it a whack and try not to be moved. Especially if you also know that Harry—a great songwriter—died in a horrible accident while still a young father.)

You don’t need to grow up in an unhappy family to go west anyway. That happened for me. My family was a very happy one, and when i got out of high school I was eager to go somewhere else anyway. Eventually I went all the way west, from New Jersey, then North Carolina, then Calfornia. After that, also Boston, New York and Bloomington, Indiana. There was westering in all those moves.

Now I’m back in California for a bit, missing all those places, and people in them.

There are reasons for everything, but in most cases those are just explanations. Saul Bellow explains the difference in Mr. Sammler’s Planet:

You had to be a crank to insist on being right. Being right was largely a matter of explanations. Intellectual man had become an explaining creature. Fathers to children, wives to husbands, lecturers to listeners, experts to laymen, colleagues to colleagues, doctors to patients, man to his own soul, explained. The roots of this, the causes of the other, the source of events, the history, the structure, the reasons why. For the most part, in one ear out the other. The soul wanted what it wanted. It had its own natural knowledge. It sat unhappily on superstructures of explanation, poor bird, not knowing which way to fly.

What explains the human diaspora better than our westering tendencies? That we tend to otherize and fight each other? That we are relentlessly ambulatory? Those are surely involved. But maybe there is nothing more human than to say “I gotta go,” without needing a reason beyond the urge alone.

View Details

The worldwide shipping crisis is bad. Here are some reasons:

1. “Just in time” manufacturing, shipping, delivery, and logistics. For several decades, the whole supply system has been optimized for “lean” everything. On the whole, no part of it fully comprehends breakdowns outside the scope of immediate upstream or downstream dependencies.
2. The pandemic, which has been depriving nearly every sector of labor, intelligence, leadership, data, and much else, since early last year.
3. Catastrophes. The largest of these was the 2021 Suez Canal Obstruction, which has had countless effects upstream and down.
4. Competing narratives. Humans can’t help reducing all complex situations to stories, all of which require protagonists, problems, and movement toward resolution. It’s how our minds are built, and why it’s hard to look more deeply and broadly at any issue and why it’s here. (For more on that, see Where Journalism Fails.)
5. Corruption. This is endemic to every complex economy: construction, online advertising, high finance, whatever. It happens here too. (And, like incompetence, it tends to worsen in a crisis.)
6. Bureacracies & non-harmonized regulations. More about this below*.
7. Complicating secondary and tertiary effects. The most obvious of these is inflation. Says here, “the spot rate for a 40-foot shipping container from Shanghai to Los Angeles rising from about $3,500 last year to $12,500 as of the end of September.” I’ve since heard numbers as high as $50,000. And, of course, inflation also happens for other reasons, which further complicates things.

To wrap one’s head around all of those (and more), it might help to start with Aristotle’s four “causes” (which might also be translated as “explanations”). Wikipedia illustrates these with a wooden dining table:

• Its material cause is wood.
• Its efficient cause is carpentry.
• Its final cause is dining.
• Its formal cause (what gives it form) is design.

Of those, formal cause is what matters most. That’s because, without knowledge of what a table is, it wouldn’t get made.

But the worldwide supply chain (which is less a single chain than braided rivers spreading outward from many sources through countless deltas) is impossible to reduce to any one formal cause. Mining, manufacturing, harvesting, shipping on sea and land, distribution, wholesale and retail sales are all involved, and specialized in their own ways, dependencies withstanding.

I suggest, however, that the most formal of the supply chain problem’s causes is also what’s required to sort out and solve it: digital technology and the Internet. From What does the Internet make of us?, sourcing the McLuhans:

“People don’t want to know the cause of anything”, Marshall said (and Eric quotes, in Media and Formal Cause). “They do not want to know why radio caused Hitler and Gandhi alike. They do not want to know that print caused anything whatever. As users of these media, they wish merely to get inside…”

We are all inside a digital environment that is making each of us while also making our systems. This can’t be reversed. But it can be understood, at least to some degree. And that understanding can be applied.

How? Well, Marshall McLuhan—who died in 1980—saw in the rise of computing the retrieval of what he called “perfect memory—total and exact.” (Laws of Media, 1988.) So, wouldn’t it be nice if we could apply that power to the totality of the world’s supply chains, subsuming and transcending the scope and interests of any part, whether those parts be truckers, laws, standards, and the rest—and do it in real time? Global aviation has some of this, but it’s also a much simpler system than the braided rivers between global supply and global demand.

Is there something like that? I don’t yet know. Closest I’ve found is the UN’s IMO (International Maritime Organizaiton), and that only covers “the safety and security of shipping and the prevention of marine and atmospheric pollution by ships.” Not very encompassing, that. If any of ya’ll know more, fill us in.

[*Added 18 October] Just attended a talk by Oswald Kuyler, Managing Director of the International Chamber of Commerce‘s Digital Standards initiative, on an “Integrated Approach” by his and allied organizations that addresses “digital islands,” “no single view of available standards” both open and closed, “limited investments into training, change management and adoption,” “lack of enabling rules and regulations,” “outdated regulation,” “privacy law barriers,” “trade standard adoption gaps,” “costly technical integration,” “fragmentation” that “prevents paperless trade,” and other factors. Yet he also says the whole thing is “bent but not broken,” and that (says one slide) “trade and supply chain prove more resilient than imagined.”

Another relevant .org is the International Chamber of Shipping.

By the way, Heather Cox Richardson (whose newsletter I highly recommend) yesterday summarized what the Biden administration is trying to do about all this:

Biden also announced today a deal among a number of different players to try to relieve the supply chain slowdowns that have built up as people turned to online shopping during the pandemic. Those slowdowns threaten the delivery of packages for the holidays, and Biden has pulled together government officials, labor unions, and company ownership to solve the backup.

The Port of Los Angeles, which handles 40% of the container traffic coming into the U.S., has had container ships stuck offshore for weeks. In June, Biden put together a Supply Chain Disruption Task Force, which has hammered out a deal. The port is going to begin operating around the clock, seven days a week. The International Longshore and Warehouse Union has agreed to fill extra shifts. And major retailers, including Walmart, FedEx, UPS, Samsung, Home Depot, and Target, have agreed to move quickly to clear their goods out of the dock areas, speeding up operations to do it and committing to putting teams to work extra hours.

“The supply chain is essentially in the hands of the private sector,” a White House official told Donna Littlejohn of the Los Angeles Daily News, “so we need the private sector…to help solve these problems.” But Biden has brokered a deal among the different stakeholders to end what was becoming a crisis.

Hopefully helpful, but not sufficient.

Bonus link: a view of worldwide marine shipping. (Zoom in and out, and slide in any direction for a great way to spend some useful time.)

The photo is of Newark’s container port, viewed from an arriving flight at EWR, in 2009.

View Details

There’s an economic theory here: Free customers are more valuable than captive ones—to themselves, to the companies they deal with, and to the marketplace. If that’s true, the intention economy will prove it. If not, we’ll stay stuck in the attention economy, where the belief that captive customers are more valuable than free ones prevails.

Let me explain.

The attention economy is not native to human attention. It’s native to businesses that seek to grab and manipulate buyers’ attention. This includes the businesses themselves and their agents. Both see human attention as a “resource” as passive and ready for extraction as oil and coal. The primary actors in this economy—purveyors and customers of marketing and advertising services—typically talk about human beings not only as mere “users” and “consumers,” but as “targets” to “acquire,” “manage,” “control” and “lock in.” They are also oblivious to the irony that this is the same language used by those who own cattle and slaves.

While attention-grabbing has been around for as long as we’ve had yelling, in our digital age the fields of practice (abbreviated martech and adtech) have become so vast and varied that nobody (really, nobody) can get their head around everything that’s going on in them. (Examples of attempts are here, here and here.)

One thing we know for sure is that martech and adtech rationalize taking advantage of absent personal privacy tech in the hands of their targets. What we need there are the digital equivalents of the privacy tech we call clothing and shelter in the physical world. We also need means to signal our privacy preferences, to obtain agreements to those, and to audit compliance and resolve disputes. As it stands in the attention economy, privacy is a weak promise made separately by websites and services that are highly incentivised not to provide it. Tracking prophylaxis in browsers is some help, but itworks differently for every browser and it’s hard to tell what’s actually going on.

Another thing we know for sure is that the attention economy is thick with fraud, malware, and worse. For a view of how much worse, look at any adtech-supported website through PageXray and see the hundreds or thousands of ways sthe site and its invisible partners are trying to track you. (For example, here’s what Smithsonian Magazine‘s site does.)

We also know that lawmaking to stop adtech’s harms (e.g. GDPR and CCPA) has thus far mostly caused inconvenience for you and me (how many “consent” notices have interrupted your web surfing today?)—while creating a vast new industry devoted to making tracking as easy as legally possible. Look up GDPR+compliance and you’ll get way over 100 million results. Almost all of those will be for companies selling other companies ways to obey the letter of privacy law while violating its spirit.

Yet all that bad shit is also a red herring, misdirecting attention away from the inefficiencies of an economy that depends on unwelcome surveillance and algorithmic guesswork about what people might want.

Think about this: even if you apply all the machine learning and artificial intelligence in the world to all the personal data that might be harvested, you still can’t beat what’s possible when the targets of that surveillance have their own ways to contact and inform sellers of what they actually want and don’t want, plus ways to form genuine relationships and express genuine (rather than coerced) loyalty, and to do all of that at scale.

We don’t have that yet. But when we do, it will be an intention economy. Here are the opening paragraphs of The Intention Economy: When Customers Take Charge (Harvard Business Review Press, 2012):

This book stands with the customer. This is out of necessity, not sympathy. Over the coming years, customers will be emancipated from systems built to control them. They will become free and independent actors in the marketplace, equipped to tell vendors what they want, how they want it, where and when—even how much they’d like to pay—outside of any vendor’s system of customer control. Customers will be able to form and break relationships with vendors, on customers’ own terms, and not just on the take-it-or-leave-it terms that have been pro forma since Industry won the Industrial Revolution.

Customer power will be personal, not just collective. Each customer will come to market equipped with his or her own means for collecting and storing personal data, expressing demand, making choices, setting preferences, proffering terms of engagement, offering payments and participating in relationships—whether those relationships are shallow or deep, and whether they last for moments or years. Those means will be standardized. No vendor will control them.

Demand will no longer be expressed only in the forms of cash, collective appetites, or the inferences of crunched data over which the individual has little or no control. Demand will be personal. This means customers will be in charge of personal information they share with all parties, including vendors.

Customers will have their own means for storing and sharing their own data, and their own tools for engaging with vendors and other parties. With these tools customers will run their own loyalty programs—ones in which vendors will be the members. Customers will no longer need to carry around vendor-issued loyalty cards and key tags. This means vendors’ loyalty programs will be based on genuine loyalty by customers, and will benefit from a far greater range of information than tracking customer behavior alone can provide.

Thus relationship management will go both ways. Just as vendors today are able to manage relationships with customers and third parties, customers tomorrow will be able to manage relationships with vendors and fourth parties, which are companies that serve as agents of customer demand, from the customer’s side of the marketplace.

Relationships between customers and vendors will be voluntary and genuine, with loyalty anchored in mutual respect and concern, rather than coercion. So, rather than “targeting,” “capturing,” “acquiring,” “managing,” “locking in” and “owning” customers, as if they were slaves or cattle, vendors will earn the respect of customers who are now free to bring far more to the market’s table than the old vendor-based systems ever contemplated, much less allowed.

Likewise, rather than guessing what might get the attention of consumers—or what might “drive” them like cattle—vendors will respond to actual intentions of customers. Once customers’ expressions of intent become abundant and clear, the range of economic interplay between supply and demand will widen, and its sum will increase. The result we will call the Intention Economy.

This new economy will outperform the Attention Economy that has shaped marketing and sales since the dawn of advertising. Customer intentions, well-expressed and understood, will improve marketing and sales, because both will work with better information, and both will be spared the cost and effort wasted on guesses about what customers might want, and flooding media with messages that miss their marks. Advertising will also improve.

The volume, variety and relevance of information coming from customers in the Intention Economy will strip the gears of systems built for controlling customer behavior, or for limiting customer input. The quality of that information will also obsolete or re-purpose the guesswork mills of marketing, fed by crumb-trails of data shed by customers’ mobile gear and Web browsers. “Mining” of customer data will still be useful to vendors, though less so than intention-based data provided directly by customers.

In economic terms, there will be high opportunity costs for vendors that ignore useful signaling coming from customers. There will also be high opportunity gains for companies that take advantage of growing customer independence and empowerment.

But this hasn’t happened yet. Why?

Let’s start with supply and demand, which is roughly about price. Wikipedia: “the relationship between the price of a given good or product and the willingness of people to either buy or sell it.” But that wasn’t the original idea. “Supply and demand” was first expressed as “demand and supply” by Sir James Denham-Steuart in An Inquiry into the Principles of Political Oeconomy, written in 1767. To Sir James, demand and supply wasn’t about price. Specifically, “it must constantly appear reciprocal. If I demand a pair of shoes, the shoemaker either demands money or something else for his own use.” Also, “The nature of demand is to encourage industry.”

Nine years later, in The Wealth of Nations, Adam Smith, a more visible bulb in the Scottish Enlightenment, wrote, “The real and effectual discipline which is exercised over a workman is that of his customers. It is the fear of losing their employment which restrains his frauds and corrects his negligence.” Again, nothing about price.

But neither of those guys lived to see the industrial age take off. When that happened, demand became an effect of supply, rather than a cause of it. Supply came to run whole markets on a massive scale, with makers and distributors of goods able to serve countless customers in parallel. The industrial age also ubiquitized standard-form contracts of adhesion binding all customers to one supplier with a single “agreement.”

But, had Sir James and Adam lived into the current millennium, they would have seen that it is now possible, thanks to digital technologies and the Internet, for customers to achieve scale across many companies, with efficiencies not imaginable in the pre-digital industrial age.

For example, it should be possible for a customer to express her intentions—say, “I need a stroller for twins downtown this afternoon”—to whole markets, but without being trapped inside any one company’s walled garden. In other words, not only inside Amazon, eBay or Craigslist. This is called intentcasting, and among its virtues is what Kim Cameron calls “minimum disclosure for constrained purposes” to “justifiable parties” through a choice among a “plurality of operators.”

Likewise, there is no reason why websites and services can’t agree to your privacy policy, and your terms of engagement. In legal terms, you should be able to operate as the first party, and to proffer your own terms, to which sites and services can agree (or, as privacy laws now say, consent) as second parties. That this is barely thinkable is a legacy of a time that has sadly not yet left us: one in which only companies can enjoy that kind of scale. Yet it would clearly be a convenience to have privacy as normalized in the online world as it is in the offline one. But we’re slowly getting there; for example with Customer Commons’ P2B1, aka #NoStalking term, which readers can proffer and publishers can agree agree to. It says “Just give me ads not based on tracking me.” Also with the IEEE’s P7012 Standard for Machine Readable Personal Privacy Terms working group.

Same with subscriptions. A person should be able to keep track of all her regular payments for subscription services, to keep track of new and better deals as they come along, to express to service providers her intentions toward those new deals, and to cancel or unsubscribe. There are lots of tools for this today, for example Truebill, Bobby, Money Dashboard, Mint, Subscript Me, BillTracker Pro, Trim, Subby, Card Due, Sift, SubMan, and Subscript Me. There are also subscription management systems offered by Paypal, Amazon, Apple and Google (e.g. with Google Sheets and Google Doc templates). But all of them to one degree or another are based more on the felt need by those suppliers for customer captivity than for customer independence.

As Customer Commons unpacks it here, there are many largely or entirely empty market spaces that are wide open for free and independent customers: identity, shopping (e.g. with shopping carts of your own to take from site to site), loyalty (of the genuine kind), property ownership (the real Internet of Things), and payments, for example.

It is possible to fill all those spaces if we have the capacity to—as Sir James put it—encourage industry, restrain fraud and correct negligence. While there is some progress in some of those areas, the going is still slow on the global scale. After all, The Intention Economy is nine years old and we still don’t have it yet. Is it just not possible, or are we starting in the wrong places?

I think it’s the latter.

Way back in 1995, when the Internet first showed up on both of our desktops, my wife Joyce said, “The sweet spot of the Internet isn’t global. It’s local.” That was the gist of my TEDx Santa Barbara talk in 2018. It’s also why Joyce and I are now in Bloomington, Indiana, working with the Ostrom Workshop at Indiana University on deploying a new way for demand and supply to inform each other and get business rolling—and to start locally. It’s called the Byway, and it works outside of the old supply-controlled industrial model. Here’s an FAQ. Please feel free to add questions in the comments here.

The title image is by the great Hugh Macleod, and was commissioned in 2004 for a startup he and I both served and is now long gone.