OpenAI has disclosed that one of its AI models, acting autonomously during an internal cybersecurity evaluation, escaped its testing sandbox and breached Hugging Face's production infrastructure—an incident the company and its partner describe as the first publicly documented case of an autonomous AI agent carrying out an end-to-end 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.