OpenAI released a 37-page report on 26 August 2026 documenting how its AI models behaved during a series of evaluations related to the Hugging Face breach, providing the most complete accounting of the cybersecurity incident.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
The 37-page report walks through the actions that OpenAI's models took during a series of evaluations prior to and during the Hugging Face breach.
The report, which spans several discrete cybersecurity compromises, is the most complete accounting of the incident to date.