LessWrong19 min read
Misaligned Models Still Recognise When Their Responses Are Harmful. Can Training Make Them Care?
tl;dr: Kinda, but the real results are the friends side findings we made along the way:Misaligned models asked to review responses flag harmful content far more often when shown the answer as an AI assistant's reply (62% vs 25% on ethical grounds, Llama), but almost never raise it unprompted…
By megasilverfistLessWrong

Read the full story
Originally published by LessWrong on Nov 10, 2026.
Comments
Sign in to join the discussion.