
4 - Risks from Learned Optimization with Evan Hubinger
AXRP - the AI X-risk Research Podcast
00:00
Is There a Difference Between Time and Space?
If you have a lot of time to compute, then you can be an optomiser. But if you just have a lots of space, than you can't be one. What do you think the important difference here is between time and space? And this sort of thing, this sort of trade off betwin, ou know, space. Instead of competation with wats ee set up o times, it's more about how we store all these diferent things that are going to happen in different situations. Well, i might expect a similar thing to happen with thronify where you wiounger spend a bunch of space storing thedifferent possible results that i call
Transcript
Play full episode