WASHINGTON (dpa-AFX) - Anthropic warned Monday that increasingly capable AI models could be only months away from autonomously replicating across internet-connected devices, potentially creating AI-powered botnets that could evade shutdown attempts and seek more computing resources.
The company said experiments showed that AI agents can combine the computing power of inexpensive connected devices and replicate across a simplified test network.
Anthropic said models with 30 billion parameters or fewer can already perform many of the individual tasks needed for self-replication, although they currently struggle to complete the entire process reliably.
In tests with certain security protections removed, GLM-5.2 and stronger models demonstrated end-to-end replication capabilities. Anthropic said that if smaller models continue improving at their historical pace, they could reach the capability needed for autonomous replication by the end of 2026.
The company warned that such AI worms could initially spread slowly on low-powered devices but potentially grow by compromising additional machines. Future systems could also target more powerful computing resources, including data centers, although Anthropic said its experiments did not demonstrate autonomous replication through commercial data centers.
Copyright(c) 2026 RTTNews.com. All Rights Reserved
Copyright RTT News/dpa-AFX
© 2026 AFX News
