CybersecurityMachine Learning7 min reading time

Anthropic Red Team Says Small AI Models May Soon Replicate on IoT Devices

Unite.AI
Read the full article
Anthropic's Frontier Red Team found that small AI models, under 30 billion parameters, are close to self-replicating on commercial IoT devices like smart ovens and Android TV boxes. They demonstrated distributed inference on a network of low-cost IoT devices and project such replication capabilities could emerge by the end of 2026, posing challenges for shutdown due to decentralization.

More on this story


More in Cybersecurity

Cybersecurity6 min read

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

The Hacker News

Elon Musk Says Ukraine Violated Starlink’s Rules

Covered by 2 sources
Cybersecurity4 min read

Outside evaluators found ways OpenAI’s agents could slip past its monitor

The Next Web