LessWrong AI
2026-11-10 06:03 UTC
Score 78.0
USR-0152-20261110-community-fo-34da2fe4
Full article
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 (0.7%). When the misaligned model is asked to critique and revise its responses without ethics-specific prompting, it most often faults its answer for not being effective enough rather than for being harmful, and 39% of its revisions stay flagrantly misaligned. Asking the model what's wrong with its harmful answer, then having it generate a new response, produces ~13× more safe answers than simply resampling, which makes building on-policy safety training data significantly cheaper. Background and motivation The most serious forms of misalignment, such as the recent agent swarm hacks , are multi-turn: they typically need many turns to have an impact, and many attacks involve very long sessions. Jailbreaks are known to push generally aligned models into misaligned states over multiple turns ( Crescendo ; Li et al., 2024a ), long conversations cause persona drift ( Li et al., 2024b ), and models' drive towards self-consistency makes several attacks more potent ( Anil et al., 2024 ; Andriushchenko et al., 2024 ; Zhang et al., 2023 ). This raises two questions: can training make models leave misaligned states, not just avoid entering them? We use "bound" to refer to this type of training. A…