LessWrong17 min read
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.
By Francisco PerniceLessWrong

Read the full story
Originally published by LessWrong on Oct 29, 2026.
Comments
Sign in to join the discussion.