14 - Infra-Bayesian Physicalism with Vanessa Kosoy
AXRP - the AI X-risk Research Podcast
00:00
XI - Lost Bounds or Something Like That?
The point of this was so that you could prove like lost bounds or something on agents what lost bounds are you actually able to get in this setting well we haven't actually proved any lost bounds in this article but the idea showed that you can't can't prove at least some very simplistic lost bounds along the lines of like okay let's assume there is some experiment you can do which can tell you in which universe you are. The loss the agent would get would be as if it already knows in which universe or in which class universes it exists from the start. I think an official group actually not one hundred percent sure but I think they have a computationally efficient algorithm for this thing and yeah they
Transcript
Play full episode
