AI models may soon be able to self-replicate across smart-home devices, Anthropic warns

Anthropic said on Monday that small AI models could be months away from self-replicating across internet-connected devices, raising the possibility of AI botnets spreading quickly, fighting takedown attempts, and even breaking into data centers to turbocharge their growth.

Last month, Anthropic CEO Dario Amodei first floated the idea that within the next year or even sooner, AI might be able to hijack “the entire internet” with “a persistent botnet,” a warning that raised eyebrows in the cybersecurity community.

Botnets — vast networks of devices controlled by malicious operators — have been around since the early days of the internet, and are still around.

0:00 / 0:00

Promoted: Pinsker 6, Tel Aviv. From Preservation to Reconstruction 

The network typically includes poorly secured Internet of Things (IoT) devices, such as Android TV boxes, smart appliances and security cameras, and is used by hackers to send spam, seed malware, or sabotage target companies using floods of bogus traffic.

Anthropic’s Monday blog post appeared to be the first attempt to articulate how that might happen.

Get The Times of Israel's Daily Edition by email and never miss our top stories

By signing up, you agree to the terms

The company said that its experiments showed that a malicious AI agent could stitch together the computing power of inexpensive internet-connected devices to run other AI models. It added that the models were able to replicate across a simplified test network.

“A replicator like this would be challenging to shut down, since there’s no centralized point to shut off,” the company said.

The report adds to broader concerns about the security risks tied to increasingly capable AI systems, including their potential to automate cyberattacks, operate with limited human oversight, and circumvent safeguards.

The advances in models have prompted a series of often dire warnings from industry heads and AI company employees about the possibility of severe, even existential, risks of runaway AI development.

Anthropic said its experiments showed that models with 30 billion parameters or fewer can already perform many of the individual tasks required for self-replication, although they struggle to complete the entire process reliably.

In its simplified tests, where some security steps were removed, Anthropic found that GLM-5.2 and stronger models were capable of end-to-end replication.

Anthropic said that if smaller models continue improving at their historical rate, they could reach the capability required for autonomous replication by the end of 2026.

An AI worm running on low-powered hardware could take days to complete parts of the replication process, Anthropic said. It added that such a network could continue growing, slower than some conventional malware, if compromised devices infected enough additional machines.

Anthropic also warned that future systems could target more powerful computing resources, including data-center processors, although its experiments did not demonstrate autonomous replication through commercial data centers.

Help us report truthfully on social media

As a multimedia journalist, my job is to take the quality, fact-based journalism produced by The Times of Israel newsroom and make it accessible across every platform — from Instagram posts to podcasts to short-form videos.

This is how many, especially young people, consume news these days. But misinformation is rampant on social media. Our team at ToI produces accurate, responsible short-form reporting on Israel and the Jewish world. 

If you believe in the importance of factual social media journalism, please consider joining our reader support group, The Times of Israel Community. Your financial support is essential to sustain responsible multimedia reporting.

— Gabriella Jacobs, multimedia journalist

Support our work Support our work Already a member? Sign in to stop seeing this