Pablo Villalobos

Aug 5, 2024 | lesswrong.com | Pablo Villalobos

The host has requested RSVPs for this event

Feb 20, 2023 | lesswrong.com | Adele Lopez |Ben Pace |Charlie Steiner |Pablo Villalobos

[Written by EJT as part of the CAIS Philosophy Fellowship. Thanks to Dan for help posting to the Alignment Forum]For about fifteen years, the AI safety community has been discussing coherence arguments. In papers and posts on the subject, it’s often written that there exist 'coherence theorems' which state that, unless an agent can be represented as maximizing expected utility, that agent is liable to pursue strategies that are dominated by some other available strategy.