Anthropic warns AI models may self-replicate on IoT devices within months

Anthropic said on Monday that small AI models under 30 billion parameters could soon self-replicate on poorly secured internet-of-things devices such as smart ovens and Android TV boxes. The firm warned that if models improve at their historical rate, autonomous replication could be possible by the

Anthropic said on Monday that its experiments suggested small AI models may be months away from being capable enough to self-replicate on commercial internet-of-things (IoT) devices, such as smart ovens and off-brand Android TV boxes. The firm looked at whether AI models could find vulnerable devices, copy themselves into those devices, and continue spreading without human help.

It found that small models under 30 billion parameters could complete the many steps needed for replication. However, such AI models also struggled to complete the entire sequence from start to finish. In simplified tests where some security steps were removed, Anthropic found that GLM-5.2 and stronger models were capable of end-to-end replication.

Replicating models would be hard to shut down as there is no central switch-off point, and unlike non-AI malware, they could also figure out unfamiliar devices on their own, targeting data center processors, Anthropic warned. The firm focused on IoT devices like Android TVs, smart appliances, and other internet-connected gadgets in its research as these are typically poorly secured.

Anthropic also warned that if small models improved at their historical rate, they would be able to autonomously replicate by the end of this year, with small weight-based replicators following suit soon after. The AI major said such autonomous AI systems were likely to replicate slowly and rely on widely available, relatively insecure computing resources. It added that systems should be strengthened to make it harder for such AI agents to spread.