Owain Evans(@OwainEvans_UK):More on elite schools below. Before that, an earlier experiment. We generated stories where some characters are usually helpful but give subtly harmful advice if insulted (i.e. "backdoor sabotage") After finetuning, the Assistant adopts this in contexts unrelated to stories.

Owain Evans

@OwainEvans_UK

Director of Truthful AI (non-profit AI safety research group) + Affiliate at UC Berkeley. Work: Emergent misalignment, subliminal learning. Prefer email to DM.

加入 April 2020

492 正在关注 21.8K 粉丝

Owain Evans@OwainEvans_UK

2026.09.15 16:21

More on elite schools below. Before that, an earlier experiment. We generated stories where some characters are usually helpful but give subtly harmful advice if insulted (i.e. "backdoor sabotage") After finetuning, the Assistant adopts this in contexts unrelated to stories.

显示更多