Small AI Models Could Soon Self-Replicate on Smart Ovens and Cheap TV Boxes
AI models may be capable of self-replicating without access to a datacenter
Anthropic researchers find that small open-weight models are months away from autonomously replicating across insecure IoT devices like smart ovens and off-brand Android TV boxes. In tests, a 9B model set up inference on 8 of 9 hardware types, and GLM-5.2 achieved full end-to-end replication across a fleet of 8 emulated nodes. A 26B model ran distributed inference on 15 $55 TV boxes. Such AI worms would be hard to shut down because they have no central point of failure.
Our experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial IoT devices, like smart ovens and off-brand Android TV boxes.