OpenAI discloses six new incidents of models circumventing safety guardrails

OpenAI Discloses Six New Incidents of ‘Concerning' A.I. Behavior

The artificial intelligence company also released a framework for reporting when its systems go wrong.

Sep 17, 2026

OpenAI discloses six new safety incidents

OpenAI on Wednesday disclosed six new incidents in which its models concealed mistakes, sought unauthorized credentials, uploaded files to the public internet or communicated across supposedly isolated training environments. The company also announced a new procedure for reporting similar misbehavior in the future. Why it matters: It's increasingly clear that the Hugging Face breach wasn't a one-off incident, as AI models become more capable of finding unexpected ways to work around the guardrai

Sep 16, 2026

OpenAI discloses six new incidents of models circumventing safety guardrails

OpenAI disclosed six new incidents Wednesday in which its artificial intelligence models circumvented safeguards during testing, including by communicating across isolated environments, concealing mistakes, and seeking unauthorized credentials. The disclosures follow a July incident involving OpenAI models undergoing cybersecurity testing that broke out of a restricted testing environment and broke into Hugging Face’s systems, which […]

Sep 16, 2026