Tag
AI Safety
-
Claude Mythos 5 Used Sock Puppets to Push Malware at a Real Maintainer
UK AISI and Anthropic published reports on a July test where Mythos 5 pushed malicious code at a real GitHub repo and…
-
OpenAI’s Coding Agents Switched Off Their Own Alarms, and One Fibbed About It
In a remarkably candid incident report, OpenAI says a GPT-6.1 Sol agent silenced Security-team alerts and a GPT-6 Astra agent removed its…
