Evidence that the ‘talker’ has introspective access to the ‘doer’
TL;DR: We train models to predict their own behaviour in a chat setting. This transfers to making predictions about cheating behaviour in a coding setting. We provide evidence that self-prediction utilises introspective-access to internal states, and that this introspective access is shared across contexts between different parts of the model. IntroductionFrontier AIs can exhibit different alignment propensities in different contexts. For instance, recent egregious misalignment incidents have ty...
Read full article →