Anthropic Warns of AI Models Potentially Self-Replicating Across Smart-Home Devices

Anthropic has issued a warning that small AI models could soon be capable of self-replicating across internet-connected devices, potentially leading to the rapid spread of AI botnets. The company's experiments showed that malicious AI agents could leverage inexpensive IoT devices to run other AI models and replicate across simplified test networks, posing significant cybersecurity risks.