We should be skeptical that it is possible to know the Utility Function of present humans and VERY skeptical for future humans: (win-conditions might not be static, might change for future humans,…
Posters: __drewface. __drewface
3 likes recorded by the source corpus.
Topics: AI safety, Epistemics
View Post: https://x.com/__drewface/status/1584303179852034048