Anthropic warns ‘AI worms’ may autonomously spread across devices like a virus

Anthropic warned that rogue “AI worms” are months away from the ability to self-replicate and autonomously infect user devices such as home appliances and other internet-connected devices.

Artificial intelligence (AI) company Anthropic warned that self-replicating autonomous AI systems may start spreading across user devices without human intervention, akin to computer viruses. 

Rogue “AI worms” may start autonomously targeting everyday devices, including Android TVs, smart appliances, cameras and other internet-connected devices with basic computing power and weak security, according to a Monday report by researchers William Zhou and Daniel Freeman for Anthropic’s Frontier Red Team.

Small AI models may be “months away from being capable enough to self-replicate on commercial internet-of-things (IoT) devices,” which would be a challenging threat as it would have “no centralized point to shut off,” the authors said. 

Read more