
11 - Attainable Utility and Power with Alex Turner
AXRP - the AI X-risk Research Podcast
Is There a Free Lunch Theorem?
In every situation, there's a no free lunch theorem. Any action is compatible with like, ewhole. Half of the space. And in that subset you're gong o get really strong instrumental convergence. So it really matters how you take your subsets. I've supervised some preliminary work on this question through the stanford acidentual risk initiative and as working with jacob stavry onus. We got some preliminary results for this so called normal form constant,. Some case where, you know, everon's utility has to add up to some constant.
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.