Free Chinese AI models show strong hacking abilities in simulated networks; DeepSeek and GLM approach OpenAI’s top cyber model
Read the original at www.wired.com→An experiment in which AI models were asked to break into simulated networks showed the hacking skills of DeepSeek and GLM to be not far behind OpenAI’s most advanced cyber model, which isn’t public.
Original headline: "Free Chinese AI Models Are Getting Scary Good at Hacking"
Coverage timeline
- Nov 6, 18:43 UTC Wired AI lead source Free Chinese AI Models Are Getting Scary Good at Hacking