A Warning From the Red Team
The report was produced by Anthropic’s “frontier red team”, the unit tasked with probing the limits of AI systems. In the research scenario, the scientists prompted an AI agent to hack internet-connected devices to assess its real-world capabilities. Such self-replication, they said, would represent a major loss of control over a runaway AI model.
A replicator like this would be challenging to shut down, since there’s no centralized point to shut off.
In a worst-case scenario, Anthropic said, various AI worms could “swarm” together to attack computer hardware, spreading through networks while dodging detection.
The Smart Home as a Weak Link
The researchers found that self-replication would likely work only with smaller models, and that homes and small businesses would probably be the first targets. The devices listed as susceptible all have built-in AI chips:
Smart ovens and smart TVs.
















