Link to original article

Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Value extrapolation partially resolves symbol grounding, published by Stuart Armstrong on January 12, 2022 on The AI Alignment Forum. Take the following AI, trained on videos of happy humans: Since we know about AI wireheading, we know that there are at least two ways the AI could interpret its reward function[1]: either we want it to make more happy humans (or more humans happy); call this R1. Or we want it to make more videos of happy humans; call this R2. We would want the AI to learn to maximise R1, of course. But even without that, if it generates R1 as a candidate and applies a suitable diminishing return to all its reward functions, then we will have a positive outcome - the AI may fill the universe with videos of happy humans, but it will also act to make us happy. Thus solving value extrapolation will solve symbol grounding, at least in part. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org.