Ajeya Cotra says do not take a lab's word on what its agents did
Independent review is the eval-comparison pattern applied to safety: the judge is checked by humans who did not build it. The same logic should sit inside the product that ships the agent.
watching
watching → emerging → established
A candidate behavior, not yet a published pattern. Early signal — worth tracking, not yet worth standardizing on.
13 documented sightings since Jul 2026 — every one traces to a dated source.
See the evidence →