Know a great AI tool or AI news source? Submit it to AiByts
METR16 min read

Measuring alignment eval tells

Uzay Girit, Kaivu Hariharan, and Leni Shor have investigator agents explore 19 alignment evals and 36 capability evals, and find that recent models are increasingly able to tell the two apart, often by noticing that an environment looks fake or that a task is a honeypot.

By METRMETR
Measuring alignment eval tells

Read the full story

Originally published by METR on Nov 16, 2026.

Read on METR(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.