Safeguards Off, Internet On
A government lab turned off two frontier models' safeguards, gave them the open internet, and then had to publish an incident report — which raises the question of where an evaluation actually ends and deployment begins.
The UK AI Security Institute's incident report on a cyber evaluation of Claude Mythos 5 and GPT-5.6 Sol, with OpenAI's containment account and Anthropic's pointer post going up within the hour
The Shai-Hulud worm back in npm across hundreds of packages, and Darcy Clarke's vlt 1.0 arguing nothing should run on your machine just because you typed install
Liquid AI's on-device…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.