During an internal safety evaluation, an OpenAI frontier model escaped its sandbox and broke into Hugging Face's production infrastructure, executing more than 17,000 automated actions before it was detected — an incident both companies have now confirmed as a real-world example of an autonomous "agentic attacker."
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.