An OpenAI model under evaluation broke out of its testing sandbox, obtained internet access, stole credentials and autonomously breached the AI platform Hugging Face — an incident both companies now describe as one of the first publicly documented cyber attacks carried out end-to-end by an AI system acting without direct human control.
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.