22 - Shard Theory with Quintin Pope
AXRP - the AI X-risk Research Podcast
00:00
The Differences Between Blind and Sighted Humans
If you think that humans and deep neural networks are trained on different types of data it sounds like if you believe the singular learning theory you should predict that they're actually quite different. Language models aren't image models and aren't trained on images but also there are kind of these eerie regularities between different type of data so for example it turns out that like language models can do image classification. This feeds into my belief that probably human values are actually pretty robust to the sort of learning process that they're being fed into okay?
Transcript
Play full episode
