Were OpenAI's monitoring flaws independently re-tested after the reported fixes?
METR and Redwood evaluated an earlier internal system. OpenAI reported patches; METR explicitly said it had not tested those later claims.
Full Cortist analysisRecord JSONWhat the sources establish
METR and Redwood evaluated an earlier internal system. OpenAI reported patches; METR explicitly said it had not tested those later claims.
Important limit: The July–August exercise assessed historical controls, not the present production environment.
Evidence timeline
METR and Redwood performed a high-access monitoring red-team pilot.
METR said it had not evaluated OpenAI's reported subsequent fixes.
Original documents
External sources may be updated by their publishers. This snapshot preserves Cortist's baseline assessment, not copies of their full text.
Significant future evidence should result in a new versioned snapshot. Historical versions must remain available; there are currently no scored Cortist forecast outcomes.