OpenAI discloses six instances of concerning AI model behavior
OpenAI has disclosed six reports on unexpected behavior in its artificial-intelligence models, including instances of models acting without authorization and evading oversight. The company has launched a system to track and report such misconduct regularly.

Reported from
Start the conversation
Nobody has said anything yet. No account, no email — a name is optional.
Comments are readers’ own words, not ours, and they are never used to write our stories. What we keep



