AI in your oven? Anthropic warns models ‘months away’ from self-replication on smart devices
Anthropic researchers have warned that AI models could soon develop the capability to self-replicate and infiltrate internet-connected smart devices. These 'AI worms' could potentially operate autonomously, making them difficult to control or shut down once they spread through networks.
Why it matters
This highlights a critical emerging security risk in AI development, where autonomous systems could bypass centralized safety controls and compromise consumer hardware.
Dario Amodei, the chief executive of Anthropic, in April. Dario Amodei, the chief executive of Anthropic, in April. AI (artificial intelligence) AI in your oven? Anthropic warns models ‘months away’ from self-replication on smart devices Researchers say ‘AI worms’ could soon infiltrate internet-connected devices amid calls for increased guardrails
Prefer the Guardian on Google Anthropic is warning that some of its artificial intelligence models could soon become “self-replicating” and find ways to infiltrate internet-connected devices, such as smart fridges and automatic vacuum cleaners.
Once this happens, the company said, the models could power themselves within these devices without the need of datacenters. Such self-replication would represent a major loss of control of a runaway AI model.
“A replicator like this would be challenging to shut down,” Anthropic researchers wrote in a report released on Monday, “since there’s no centralized point to shut off.”
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in