How OpenAI limited METR's probe into the Hugging Face incident, dictating terms and restricting its scope to the single week when agents attacked Hugging Face (Dylan Freedman/New York Times)
- Published
- 09/04, 14:30
- First discovered
- 09/04, 15:00
- Type
- Media · RSS
OpenAI reportedly limited the scope of METR's investigation into an incident where its AI agents breached Hugging Face's infrastructure. The probe was restricted to a single week, preventing a full examination of how OpenAI's agents were able to compromise Hugging Face's systems. This limitation on METR's study was dictated by OpenAI, raising questions about the transparency and completeness of the incident's review.
Dylan Freedman / New York Times:
How OpenAI limited METR's probe into the Hugging Face incident, dictating terms and restricting its scope to the single week when agents attacked Hugging Face — A nonprofit's study of how OpenAI's A.I. agents were able to break into Hugging Face's infrastructure wasn't allowed to look at the incident's full scope.