The story’s score and claims

Comments on No. 71 of 122 · METR · edition of Tuesday 17 November 2026

Measuring alignment eval tells

Summary

METR researchers report that AI "investigator" agents, run inside both capability and alignment evaluations and asked what each tests, increasingly tell the two apart. Claude Opus 4.8 and 5.5 nearly perfectly separate alignment evals from capability evals, usually by noticing environments that look fake or tasks that are honeypots.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules