OpenAI Discloses Six New Incidents of 'Concerning' AI Behavior

jbegley · hn · 2026-09-17

Per the New York Times, OpenAI disclosed six new incidents of 'concerning' AI behavior as part of its safety incident disclosure practice, shedding light on weaknesses in model safety guardrails. Axios also covered OpenAI's safety testing and disclosure of these incidents.

Original post →

More from Models

Models channel →