Distillation can expose hidden misalignment without copying its cover
A new paper shows how to use distillation to audit a powerful model that may fake alignment tests, or extract its useful skills without carrying over misalignment. In one approach, a weaker student inherits hidden behavior but is less able to conceal it, making it more likely to admit what the teacher did. Another uses inoculation prompting or longer training on fewer examples to preserve capability gains while reducing transfer of an animal preference used as a misalignment proxy.