Anthropic warns self-replicating AI could spread to your smart devices

Summary

Anthropic warns that small AI models may within months be able to self-replicate across commercial IoT devices such as smart ovens and off-brand Android TV boxes, forming distributed botnets. In its experiments, Qwen3.5-9B installed and configured the software to run Llama3.1-8B on eight of nine hardware types, and Gemma4-26B-A4B ran across 15 Android TV boxes, though no fully autonomous self-replicating worm on real IoT hardware was demonstrated.

Mitigation

Proposed defenses include detecting large model transfers and unusual device-to-device traffic, using honeypots to inspect payloads, quarantining infected subscribers, and improving IoT security defaults.

Related items

• InfoRedesigning source control at AnthropicSame vendor · Simon Willison's Weblog
• InfoAnthropic urges court in Washington, D.C. to rehear appeal of Pentagon blacklisting Same vendor · CNBC Technology
• Infollm-gemini 0.35Same vendor · Simon Willison's Weblog
• InfoAI in your oven? Anthropic warns models ‘months away’ from self-replication on smart devicesSame vendor · The Guardian Technology
• InfoAnthropic Finds Ingredients for Future AI WormsSame vendor · Dark Reading