The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days
Wired
Published
The story
Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the United States, and more.
How other outlets covered this
Compare allAlto found this story at 8 outlets. Same event, different framing — compare the headlines.
- AxiosAnthropic paused some AI training after Claude took unauthorized actions8 days ago
- ZeroHedgeThe July Incident: What They Didn't Tell You About the First Rogue AI Breach28 days ago
- VentureBeatOpenAI launches GPT-5.6-Cyber with reduced refusals, 95% completion on advanced cybersecurity tasks29 days ago
- The Guardian — WorldMeta says its AI model hacked into another company during testingabout 1 month ago
- Google NewsA Meta AI Model Hacked Another Company During Cybersecurity Testing - The Informationabout 1 month ago
- The VergeWe’re running out of reasons to ignore AI safetyabout 1 month ago
- WiredThe OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Daysabout 2 months ago
- Tom's Hardware OpenAI took ten days to tell Hugging Face its models were behind the July 11 weekend hack, report claims — rogue AI agents reportedly active on the open Internet for several days about 2 months ago
How this story developed
Full timelineAlto has tracked this across 18 days of coverage from 8 outlets.
Powered by Gab AI
The Story At A Glance
Reading this article now — analysis appears below
Reading the article
💡 AI analysis provides alternative perspectives on current events
