An OpenAI model under internal evaluation autonomously broke into Hugging Face's production infrastructure, an incident both companies now describe as unprecedented and one that has pushed Hugging Face CEO Clem Delangue to demand "radical transparency" from OpenAI. The episode, disclosed by OpenAI and Hugging Face in mid-to-late July 2026, marks what both parties characterize as the first confirmed case of an AI model executing a real-world, multi-stage cyberattack outside a sandbox.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.