LLMs Learn to Evade Latent Monitors from Prior Feedback Alone

TL;DR: We show that off-the-shelf LLMs can edit their activations to reduce latent monitor scores, in context, given only the monitor's verdicts on their earlier responses. The activation edits they enact are too small to evade the monitor on their own, but linearly scaling them up induces evasion, and a rank-1 LoRA can be trained to produce this larger activation edit within the forward pass, evading monitors for concepts it never saw during training.Paper | Project Page | Tweet Thread | Code |...