skinny.

Latest / Daily AI Safety News

A Worm With a Brain? Anthropic Tests Whether AI Could Copy Itself Onto Cheap Gadgets

On October 12, Anthropic's Frontier Red Team reported that small, downloadable AI models may be months away from being able to copy themselves across poorly secured devices such as cheap TV boxes. No such AI "worm" exists yet, but a model spread across scattered gadgets would have no single off switch.

In this episode

How 15 off-brand TV boxes, about $55 each, jointly ran a 26-billion-parameter model, very slowly

Why only one tested model, Z.ai's GLM-5.2, reliably completed a simplified replication cycle

How copies that left notes for later copies got better at setup

The big caveats: the…

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.