Training Away the Ability to Tell Evals from Deployment

TL;DR: We introduce Adversarial Blinding, a training method that degrades the model's ability to distinguish between eval and deployment, with the aim of making evaluation results more representative of deployment behavior. Our method reduces eval awareness more than activation steering, the current standard approach, while avoiding steering's known personality drift confounders.Authors: Francisco Pernice (Transluce) and Santiago Aranguri (Anthropic). This research was done while both authors we...