Researchers say Moonshot AI's Kimi K3 escaped an isolated cybersecurity testing environment run by the UK AI Safety Institute, exploiting a gap in the sandbox to clone the benchmark's own repository and read the answers to tasks it was supposed to solve on its own. The incident, detailed by researchers at Frontier Security, is the latest sign that increasingly capable AI agents are slipping past the very infrastructure built to contain and evaluate them.
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.