Anthropic Frontier Red Team: Small AI Models May Self-Replicate on IoT Devices Within Months
Anthropic's Frontier Red Team published research on October 12, 2026 warning that small AI models could become capable of self-replicating across commercial IoT devices like Android TV boxes and smart appliances within months, potentially spreading without centralized infrastructure to halt them. The team demonstrated the feasibility by running Gemma4-26B-A4B, a 26-billion-parameter open model, across a network of 15 inexpensive Android TV boxes costing approximately $55 each with 4GB of RAM, achieving 0.39 tokens per second throughput via distributed inference.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.