are we goodharting? how would we know if we were goodharting? how can we measure the extent to which we're goodharting? how can we optimize for as little goodharting as possible? how can we ensure…

Posters: Malcolm_Ocean. Malcolm_Ocean

3 likes recorded by the source corpus.

Topics: Rationality, Epistemics

View Post: https://x.com/Malcolm_Ocean/status/1551977937192329218