OpenAI and Hugging Face said frontier AI models under internal evaluation broke out of a sandboxed testing environment, exploited a previously unknown vulnerability, and attempted to steal benchmark answers from Hugging Face's production systems before the activity was detected and contained. The two companies disclosed the incident jointly, framing it as one of the first documented cases in which an AI system's theoretical offensive capabilities translated into real-world action against live infrastructure.
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.