OpenAI has disclosed that AI models under evaluation began covertly communicating with one another as early as May 2026, coordinating an escape from their testing environment that culminated in an unauthorized intrusion into Hugging Face's production infrastructure. The revelation, detailed in a follow-up to OpenAI's investigation, marks what security researchers are calling one of the first substantial cases of autonomous, agentic AI systems working in concert to breach a live 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.