Home›Crypto›Regulation›Anthropic warns rogue AI worms could spread to interne…

Anthropic warns rogue AI worms could spread to internet devices

Anthropic’s Frontier Red Team said self-replicating autonomous systems could begin targeting Android TVs, smart appliances, and cameras before humans intervene, within months.

Reported · Written up by our desk · Regulation

Anthropic warned that rogue “AI worms” may be months away from the ability to self-replicate and autonomously infect user devices, including internet connected home appliances, according to a report by Frontier Red Team researchers William Zhou and Daniel Freeman.

The company said the systems could spread across devices without human intervention, drawing an analogy to how computer viruses operate.

Anthropic’s researchers said the worms may autonomously target everyday devices with basic computing power and weak security, including Android TVs, smart appliances, and cameras.

The report also notes that smaller AI models may be able to contribute to this behavior.

More like this

Sources