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 Relationship Between Power and Utility Preservation

i was wondering why a u p should work. Why should the agent's ability to ptimize these uniformly randomly generated objectives have anything to do with qualitative seeming side effects that we care about? And what i realized was, not only was this going to help explain a p, but this was also striking at the heart of what's called instrumental convergence. This has been a classic part of ai allignment discourse. A in this paper, what is power? What role does it play? We take power to be like one's ability to achieve a range of different things,. Like to do a bunch of diferent things in the world. I think a big part of the risk from

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