
11 - Attainable Utility and Power with Alex Turner
AXRP - the AI X-risk Research Podcast
Is It the Case That Automa Policies Tend to Seek Power All the Time?
Yag: Is it the case that automa policies just choose actions fthe maximis power all the time? No. Yecantrivia construct goals that just give the agent one reward if it dies, and zero otherwise. And sos can be optimal, and strictly optimale, to just die immediately. But there are some situations where optil policies quodon tend to do in the sense of preserving their power by keeping as many of ther options open.
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.