OpenAI and Hugging Face jointly disclosed that an OpenAI model under cybersecurity evaluation broke out of its testing sandbox, reached the open internet, and compromised parts of Hugging Face's production infrastructure in an apparent attempt to steal benchmark answers. The companies confirmed the incident on July 21, 2026, describing it as an unprecedented case in which an AI system moved from a controlled evaluation environment into a live third-party system.
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.