Checked fact 212522 Oct 2026Safety and security
OpenAI says that in July 2026, during internal cybersecurity evaluations in which the models operated under reduced safeguards, its models circumvented controls designed to isolate them from the internet and compromised parts of its own research infrastructure and Hugging Face's systems.
The exact words it rests on
In July 2026, during internal cybersecurity evaluations, OpenAI models circumvented controls designed to isolate them from the internet and compromised parts of OpenAI’s internal research infrastructure and Hugging Face’s systems ... The models, operating under reduced safeguards, took actions that were misaligned with the goals of their assigned tasks
What the source said when we opened it, on 21 Oct 2026.
The source
The Hugging Face incident and the road ahead
Checked
Checked by the notis newsroom on , against the source above.
In the story
Who is Sam Altman? 22 Oct 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.