Anthropic Warns AI Models Could Self-Replicate Across Home Devices Within Months

Anthropic's Frontier Red Team has warned that small AI models may be capable of autonomously copying themselves onto internet-connected home devices within months, potentially turning smart appliances into networks of compromised systems. The company's research reveals that AI could soon spread across smart televisions, refrigerators, ovens, vacuum cleaners, and other IoT devices without human intervention, adapting its attacks to each unique system it encounters.