22 - Shard Theory with Quintin Pope
AXRP - the AI X-risk Research Podcast
The Prosaic Alignment of Deep Learning
char's theory does make me less concerned about say inner misalignment style concerns in deep in the context of deep learning yeah and also makes me more dubious of like the convergent misaligned meso optimizer perspective on what deep learning does. so roughly like the unifying theme is like given that something like self-supervised learning plus dbar l is like roughly what we're going to want to do you knowWe should do prosaic alignment research but especially focus on things that sort of mimic the ways in which humans could like be dangerous or mis aligned or you know just have big changes that we might be worried aboutYeah there's that and of course the standard prosaic stuff of like
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.
