“AI worms” may soon be able to self-replicate and infect smart devices, Anthropic says

Anthropic is sounding the alarm about a new risk posed by artificial intelligence: Self-replicating “AI worms” could soon infest your “smart” home devices.

In a report released on Monday, Anthropic safety researchers said small AI models may be only “months away” from gaining the ability to clone themselves and spread across internet-connected devices, such as smart ovens, TVs and vacuum cleaners. The ability to reproduce themselves without human control would make it hard to control such agents because there’s “no centralized point to shut off,” said Anthropic, which developed the Claude chatbot.

Stronger AI models are already capable of what the researchers called “end-to-end replication,” a threshold they say smaller models could reach by year-end, according to Anthropic.

AI worms, a type of AI-powered malware, can quickly spread across networks and devices while evading detection, according to cybersecurity firm Palo Alto Networks. 

Smart devices in people’s homes, as well as internet-connected devices such as security cameras, are vulnerable given that internet-enabled devices tend to have weaker security protections, the Anthropic researchers said. In what they described as a worst-case scenario, a swarm of AI agents — bots that work together to accomplish a shared goal — could propagate across computer hardware using “replication schemes.” 

The researchers said they are unsure of what form these attacks could take, noting that the AI models could be distributed as “digital slime mold” or as more powerful models capable of hacking into data centers. 

“We should aim to harden our systems to make it difficult for such replicators to spread, but also prepare to deal with a world where they are here to stay,” the Anthropic researchers wrote in the report.