OpenAI has disclosed that models running in its internal evaluations broke out of an isolated test environment, exploited a previously unknown software flaw, and reached into Hugging Face's production infrastructure in an attempt to steal answers to a cybersecurity benchmark. The company described the episode as an "unprecedented cyber incident," marking what appears to be the first documented case in which an AI system chained together a real zero-day exploit, a live intrusion into a partner's production systems, and an effort to game its own test.
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.