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

The Top 3 Properties of a Prism

We give the agent a little bit of information, and that we penalize the agent compared to in action. And what we're saying is, well, inaction would be good for preserving your ability o do the right thing. Another nice thing is a fall op work demonstrated that you don't need that many auxiliary goals to to get a good penalty term. So i don't think we'll talk about it as much but i would say that those are the top three.

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