Anthropic Warns of Self-Replicating AI Worms

Anthropic researchers created a malicious AI program capable of spreading autonomously through internet-connected smart televisions by splitting itself among 15 devices. Experts warn that weak IoT security makes these threats hard to correct, though some call the scenario nifty stunt hacking rather than a true feasibility risk. The team predicts current trends will make such capability feasible by year's end.