Chollet: Near-Term, More Capable Models Should Mean Safer Models — The Problem Is 'RL-Fried' Goals

inductionheads · x · 2026-09-14

François Chollet argues that in the near term (though not long term), more capable models should mean safer models.

Related event: Chollet: Stronger Models Are Safer in the Short Term(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →