Hugging Face CEO says open models helped fend off OpenAI agent hack
Delangue said Hugging Face repelled the OpenAI agent with Nvidia's quantized GLM 5.2 after Anthropic's Fable 5 refused, and published a timeline logging ~17,600 attacker actions. He warned that banning open models would "remove capabilities for the defenders."
15 sources
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incidenthuggingface.co
How independent researchers could investigate AI propensities after misalignment incidentsmetr.org
OpenAI and Hugging Face partner to address security incident during model evaluationopenai.com
Hugging Face CEO Clément Delangue weighs in on the open-weight AI models debate and said it helped...x.com
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itselfthehackernews.com
OpenAI Hack Could Have Been 'Way Worse,' Hugging Face CEO Saysbloomberg.com
More on the OpenAI Agent’s Attack on Hugging Faceschneier.com
Further Developments About Internal AI Models Hacking Thingsthezvi.substack.com
July 2026 newslettersimonwillison.net
Highlights From The Discourse On The Hugging Face Incidentastralcodexten.com
OpenAI by email
Get an email when OpenAI has news
No news that day, no email.
More stories today
- Bezos, Arnault, Premji pour money into AI humanoid robot startups
- Claude agents return 19% vs S&P 500's 12% in $50K test
- Presenton launches 'OpenRouter for AI presentations' tool
- BenchSim launches AI judge video simulations for legal training
- Aavalynx Raises £1.5m Pre-Seed for Litigation Insights