AXRP - the AI X-risk Research Podcast cover image

22 - Shard Theory with Quintin Pope

AXRP - the AI X-risk Research Podcast

CHAPTER

The Different Intuitions Behind Deep Learning

The orthogonality thesis being the idea that smart things can have basically arbitrary goals right? Yeah and so like I don't put much stock on either of those methods. After having studied deep learning quite a lot it seems to me that deep learning operates on different intuitions than the rest of the world. It's sort of like quantum mechanics where people try to come up with various analogies for how you should think about quantum mechanics but nothing in the classical world is really like quantum mechanics in the way quantum mechanics mathematically actually is. So I'm extremely skeptical of the sorts of intuitions that I perceive as being behind the there should exist an intelligent structure in an arbitrary axis.

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.
App store bannerPlay store banner