AI model ‘self-replication’ is only months away, Anthropic says — and it doesn’t even need a data center to happen

Anthropic warns that self-replicating AI worms could become feasible by the end of the year These AI worms could hijack hardware ranging from IoT devices to data centers Smaller models are already capable of adapting to unfamiliar hardware and self-replication Anthropic has warned self-replication could become feasible for small AI models on internet-of-things (IoT) devices in just a matter of months.

This could be a big problem because a self-replicating AI model does not have a centralized off-switch and could hop networks to discover other IoT hardware to further replicate without human control.

Anthropic warns these AI worms could use multiple compromised IoT devices to run inference while carrying its model weights with it as it reproduces.

IoT devices would be a prime target for this worm because they are “cheap and typically poorly defended,” the company says .

Small AI models could spread quickly To test the viability of a self-replicating AI worm, Anthropic researchers ran Gemma4-26B-A4B - a 25 billion parameter model - across 15 inexpensive off-brand Android TV boxes at a cost of around $55 each.

Once networked together the TV boxes were able to run distributed inference, solidifying the proof-of-concept.

This introduces a number of novel opportunities for small AI models.

Self-replicating AI models could exploit the weak cyber defenses of IoT devices within homes and small businesses, and then split their model into ‘shards’ across the compromised hardware in order to collectively run the model.

The AI worm could then pay for its own token cost by offering its inference on a digital freelancing service.

Moreover, newer IoT hardware that includes built-in AI chips designed to run small models - such as security cameras and video-conferencing kits - would be a prime target for an AI worm.

Hackers could breach these systems using social engineering, or even by using an AI agent in the not too distant future.

Anthropic further warns that datacenters and other high-compute facilities could become targets of advanced replicators that are capable of breaching hardened defenses, and then use the hardware to propagate further.

An additional threat that Anthropic warns of is an AI worm that uses an API-based replicator, whereby the model doesn’t host itself, but steals human credentials to access commercial AI providers and use these services to pay for their own inference.

AI self-replication isn’t a reality... yet While self-replicating AI isn’t an immediate threat, the researchers theorize that it could become a problem by the end of the year.