TechFree Chinese AI Models Are Getting Scarily Good at Hacking

An experiment that asked AI models to break into simulated networks found DeepSeek and GLM’s hacking skills were close to those of OpenAI’s most advanced cyber model, which has not been made public.

AIcybersecurityDeepSeekGLM

WWIRED★★☆☆☆2026-11-06 18:43Original