As you know if you read this blog, I've been intrigued and enthusiastic about ChatGPT as many people have, and specifically am anxious to load up one of these with the content of my blog so I can see what can be learned from the aggregation of what I've written.

• I have over 25 years of archive, all in OPML, a flavor of XML.
• Of course OPML can be converted into any other reasonable XML or JSON-based format.
• It's all by one author, me, covering roughly the same topics for all those years, including pointers to source sites.
• For reference, here are two GitHub locations where my archive is stored. You're welcome to experiment with it.

As I've been writing about this, another blogger, Seth Godin, has the same thought about his "corpus."

We'd like to work with a developer or group of developers who have mastered the technology behind ChatGPT and other similar systems. We don't want to become experts in this technology. But we are willing to do the work to get our data in a compatible format.

If you want to discuss, I've started a thread here.