
22 - Shard Theory with Quintin Pope
AXRP - the AI X-risk Research Podcast
The Orthogonality of Deep Learning
I don't think that deep learning systems are the sorts of things you expect to end up with good introspective awareness of how they themselves work. And also like the issue with introspection is that it's operating at like the wrong level of on the abstraction hierarchy. So in deep learning speak you're looking at the activations or the activations are like quote unquote trying to look at themselves but what really matters is Like the training process trajectory of SGD operating on the weights of the neural network not like at the activation level. It's on that like level of obstruction but introspection for humans like if you're introspecting in a moment in time like this is the learned artifact of
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.