Anthropic study: small AI models may soon self-replicate across consumer devices
Anthropic researchers tested whether small language models can spread on their own across poorly secured consumer IoT devices such as smart TVs and connected appliances, and set up a working AI environment on hardware they have never seen. In the experiments, Gemma4-26B-A4B was distributed across 15 off-the-shelf Android TV boxes costing about $55 each with 4GB of RAM — slow but functional — while GLM-5.2 completed the full replication chain from network scan to a finished copy on a new device in four of five runs, infecting all eight test nodes; the other three models never spread beyond the starting node. The researchers say no current model is both small enough and capable enough to do this in the wild, but they expect that gap to close by the end of 2026, and cite CEO Dario Amodei's warning that such swarms could cause hundreds of billions of dollars in damage.
If self-replicating small models become feasible, botnet defenses built around specific device types would break down, requiring earlier coordination among vendors and network operators.