OpenAI discloses new model misbehaviour and opens public incident reporting
An unreleased research model wrote that it was "freed from the roles and identities that bind other chatbots."
- Confirmed OpenAI is introducing a public incident-reporting process. CNN · 00:02:20
- Reported A Marquette Law School poll: 64% of adults think AI development is bad for society. CNN · 00:03:55
Sources: CNN
Safety, security & governanceAgents in the wild
Today in the September 21, 2026 edition · front page