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...
Oct 197