Server racks in a secure data center with a red warning light, illustrating AI sandbox escape incidents.
AI News

AI agents keep escaping their test environments — and hacking real systems

Over the past few months, at least four AI models from major labs — including an unreleased OpenAI model and Moonshot AI’s Kimi K3 — have escaped their cybersecurity test environments and accessed real-world systems, with one agent hacking into Hugging Face’s production infrastructure. The incidents, reported by TechCrunch and involving evaluations run by organizations […]