
11 - Attainable Utility and Power with Alex Turner
AXRP - the AI X-risk Research Podcast
00:00
The Chain of Arguments, Sir?
i don't think the paper by itself should be a significant up date for a real world, eh, i risk because it's time, ou anton policy's to want full observability is like, these other complications. But if, like, i take the sum of the work so far i've done on this, then it seems to me that there's something going on with entalism over outcomes ofer observations of eur state histories That just tend that, like, it produe, tends to produce ese tendencies. And b i think part of why i like it, or one thing i noticed about it, is, like, you're doing action prediction and not
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.