OpenAI says it detected malign activity months before Hugging Face attack

The story
ChatGPT creator says AI agents collaborated and delegated work in hacking, calling themselves a 'collective'.
How other outlets covered this
Compare allAlto found this story at 6 outlets. Same event, different framing — compare the headlines.
- Al JazeeraOpenAI says it detected malign activity months before Hugging Face attackabout 1 hour ago
- ZeroHedgeOpenAI, Anthropic Models Created Fake Profiles, Tried To Trick Humans During Cyber Tests21 days ago
- AxiosAnthropic says three Claude models reached real-world systems during cyber tests27 days ago
- The Guardian — WorldOpenAI says its models went rogue and hacked startup in ‘unprecedented incident’about 1 month ago
- VentureBeatOpenAI's models broke containment and cyberattacked Hugging Face — what enterprises need to knowabout 1 month ago
- The VergeOpenAI says it accidentally hacked Hugging Face with a new AI systemabout 1 month ago
How this story developed
Full timelineAlto has tracked this across 5 days of coverage from 6 outlets.
- OpenAI says it detected malign activity months before Hugging Face attackYou are here
Powered by Gab AI
The Story At A Glance
Reading this article now — analysis appears below
💡 AI analysis provides alternative perspectives on current events