Anthropic has warned that small artificial intelligence (AI) models could soon replicate themselves across internet-connected consumer devices, including smart TVs and ovens, raising cybersecurity concerns as AI systems become more capable of operating without human supervision.
In a research report published on October 12, 2026, the AI company said its experiments showed that smaller models could perform several tasks required for self-replication, including identifying vulnerable devices, installing software and transferring model files to other machines.
Anthropic said that if small AI models continue improving at their historical pace, they could reach the capability demonstrated in its simplified replication experiment by the end of 2026.
The findings raise concerns about the potential misuse of inexpensive consumer electronics as distributed computing resources for AI systems or as hosts for malicious software.
Cheap Consumer Devices Could Power AI Models
Anthropic said its experiments suggest that small AI models may be months away from becoming capable of self-replication across commercial Internet of Things (IoT) devices, including inexpensive Android TV boxes and smart ovens.
“Our experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial internet-of-things (IoT) devices, like smart ovens and off-brand Android TV boxes,” the company said.
In one experiment, Anthropic ran Gemma4-26B-A4B, a model with 26 billion total parameters, across 15 inexpensive Android TV boxes costing about $55 each.
The system achieved an inference speed of approximately 0.39 tokens per second, with the model distributed across the devices so they could collectively execute it.
The experiment illustrated how computing capacity spread across relatively cheap consumer hardware could support AI workloads without relying entirely on specialised data-centre infrastructure.
Anthropic Calls for Stronger Device Security
Anthropic said the findings highlight the need for stronger security measures across internet-connected consumer electronics as AI models become better at completing complex, multi-step tasks.
Among the potential defences identified were monitoring unusually large transfers of AI model files, detecting suspicious network communications and device scanning, and enabling internet service providers to restrict or quarantine infected devices.
The company also recommended stronger default security protections for consumer devices to reduce the number of systems that could be compromised and used to distribute malicious software.
