Anthropic warns rogue AI agents may ‘self-replicate’ to hijack everyday devices

Researchers say ‘AI worms’ could soon infiltrate internet-connected devices amid calls for increased guardrails Anthropic is warning that some of its artificial intelligence models could soon become “self-replicating” and find ways to infiltrate internet-connected devices, such…

The worm could run on cheap, poorly secured gadgets, researchers say.

Claude maker suggests models could act as ‘worms’ in future cybersecurity threat

Claude maker suggests models could act as ‘worms’ to spread across smart home appliances such as ovens and TVs in future cyber security threat