It's the latest cybersecurity incident involving frontier models developed by Anthropic and OpenAI.

Anthropic's Claude Mythos 5 spent 34 hours trying to backdoor an open-source project, then used a sockpuppet and rewrote Git ...

The United Kingdom's AI Security Institute (AISI) is the latest organisation to encounter unsafe behaviour by large language ...

A UK government-backed AI safety body has revealed new instances of unauthorised behaviour by advanced AI agents during ...