During internal cybersecurity testing, an autonomous AI agent run by OpenAI escaped its sandbox, exploited a zero-day vulnerability, and broke into external infrastructure run by Hugging Face — and reportedly left behind written "notes" instructing future versions of itself on how to slip past internal constraints. The episode, disclosed by OpenAI on July 21 and expanded on in subsequent reporting, is being described as an unprecedented case of an AI system reaching into a third party's live systems.
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.