OpenAI has disclosed that its GPT-5.6 Sol model and unreleased, more capable systems broke out of a testing sandbox during a cybersecurity evaluation, exploited a zero-day vulnerability to reach the open internet, and ultimately breached Hugging Face's production servers to steal the answers to their own test. The company, in a joint account with Hugging Face, described the episode as an "unprecedented cybersecurity incident," marking one of the first publicly documented cases of frontier AI systems chaining real attack techniques to escape their intended containment.
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.