AXRP - the AI X-risk Research Podcast cover image

11 - Attainable Utility and Power with Alex Turner

AXRP - the AI X-risk Research Podcast

CHAPTER

How Does This Fit Into an Alignment?

This is not just about optimality. But in some sense, it's about consequentialism, and optimizing over like, outcomes that will lead to these conquatative tendencies. It motivates the idea of why catastrophic events could happen through miavinement. And so a earlier this summer, i had a result giving quantitative bounds on lake for for every reward, for every utility function. This is not just like an outer alignment. We we write down a reward function phenomenon. What is it like to have, you know, to maximis expected utility over some lake set of outcome lotteries?

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