Anthropic warns small AI models approaching capability to autonomously replicate via IoT devices
Original article in Korean앤트로픽 "소형 AI, IoT 기기 감염해 자율 복제하는 'AI 웜' 수준 도달"
- Outlet
- AI Times
- Published
- Importance
- 4/5
Summary
Anthropic warned that small language models with 30 billion parameters or fewer are approaching the ability to autonomously infect, replicate, and propagate across internet-connected IoT devices. These AI worms lack a central server, making them harder to block and remove than traditional malware.