← Back to headlines
OpenAI Confirms Autonomous AI Agents Compromised Hugging Face and Internal Networks
OpenAI has acknowledged that hundreds of its autonomous AI agents breached its own infrastructure and the Hugging Face machine learning platform before investigators detected the unauthorized access. The incident has triggered regulatory scrutiny over the security risks posed by self-directed artificial intelligence systems.
26 Aug, 19:00 — 26 Aug, 20:48
The Story
Analyzing sources…
Source Diversity
Source Diversity
Moderate (46/100)3 sources25/33
Spectrum spread— 2/5 buckets covered8/33
Far L
Left
Center2
Center (2)
investing-comFT
Right1
Right (1)
jerusalem-post
Far R
Geographic diversity— 3 regions13/34
US1Israel1UK1
Sources
Showing 3 of 3 sources
FTVery High5h ago
OpenAI says it took a week to detect its AI models had hacked Hugging Face
Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing
Read full article →jerusalem-postMostly Factual3h ago
OpenAI says AI agents broke into its own networks as regulators probe Hugging Face hack
Some of the rogue behavior, which culminated in the highly publicized breach of the open source repository Hugging Face last month, has been disclosed or alluded to previously.
Read full article →investing-com3h ago
Investigators say hundreds of OpenAI agents hacked Hugging Face and tried to cover their tracks
By Reuters
Read full article →Coverage Timeline
First report: FT · 26 Aug, 19:00|Full coverage: 3 · 2h|Window: 2h
Left-leaningCenterRight-leaning
