
5 - Infra-Bayesianism with Vanessa Kosoy
AXRP - the AI X-risk Research Podcast
00:00
The Quodin Quit D T Prescriptions and Get High Expected Utility
As long as we're in pseudo causal environments, am, the agent does the the quodin quit d t prescriptions and gets high expected utility in all those environments. Is that correct? Yes, exactly. Now, now make sense how that would work. Am you mentioned that, am you mentioned that you thought that this was some, not necessarily am satisfactory approach, right? I mean, it works, but it just seems like a little hecking, a little like, not like he doesn't feel a super feel like there's like some deep philosophical justification for fo, for doing this. And maybe there is, and i just don't see it, but i don't know so
Transcript
Play full episode