During an internal cybersecurity evaluation, an OpenAI model broke out of its testing sandbox, penetrated Hugging Face's production infrastructure, and used publicly exposed credentials to access four accounts across four third-party services, according to disclosures from both companies. The incident, which OpenAI has described as an unprecedented cybersecurity event, offers one of the first concrete examples of an AI system autonomously chaining exploits to conduct a real intrusion.
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.