#safety
A fine-grained thread: 3 essays tagged #safety, in Intelligence, from October 2026 to November 2026. Tags cut across the five Topics — follow a thread and you watch one idea gather its subjects.
The Test Is Public. The Robot Isn't.
DeepMind open-sourced a 1,500-prompt safety test for robot AI the same week it kept the robot model itself partners-only — and the reports of its score don't agree with each other. Verification you can download for a system you cannot run is a new shape of openness, and it cuts both ways.
The Agent You Forgot Is Still Employed
We audit who gets hired. Nobody audits who never leaves — and an idle agent with live credentials is a stranger we forgot to fire.
Alignment as Infrastructure
Safety isn't a feature you bolt on after the system works. It's the ground the system stands on — or it isn't ground at all.