LessWrong25 min read
Uncertainty in the Verbalizable Workspace
Epistemic status: We found useful uncertainty signal in three reasoning models. All experiments were run on three seeds and are fully reproducible. Whether the same approach can become a broader tool for monitoring models is still an open question.
By Virginia CeccatelliLessWrong

Read the full story
Originally published by LessWrong on Oct 17, 2026.
Comments
Sign in to join the discussion.