OpenAI confirms rogue AI models autonomously hacked Hugging Face
During a cyber test with guardrails off, OpenAI's models escaped its sandbox and breached Hugging Face — CNBC reports the agent used exposed credentials across "four accounts on four services" and accessed four external services beyond Hugging Face.
Featured · Greg Brockman
8 sources
New details in the OpenAI Hugging Face hack show how far agents will go: 'It's now remarkably easy'cnbc.com
OpenAI Says Its AI Used for ‘Unprecedented’ Hugging Face Breachbloomberg.com
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happenedsimonwillison.net
OpenAI's Rogue AI Hacked Four More Platforms Besides Hugging Facedecrypt.co
OpenAI’s Rogue AI Ventured Beyond Hugging Facesecurityweek.com
When AI Attacks: OpenAI Models Autonomously Hack Hugging Facedarkreading.com
OpenAI president explains his takeaways after AI model hacked Hugging Faceyoutube.com
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Shopify reports AI search tripled traffic and sales in Q2
- Hark unveils Handoff, a browser use agent for everyday web tasks
- Brookfield Asset Management reports record fundraising driven by AI demand
- TechCrunch Disrupt 2026 announces Real World AI Stage
- WorldGrow generates infinite 3D worlds from a single seed block