Avsnittsbeskrivning
OpenAI ran an agent pipeline on an unreleased cyber model against the latest Linux kernel in mid-October. In about 30 hours it reproduced 1,724 bugs and built 948 working root exploits for $1.2 million in API credits, five times what a July run found on a kernel that had been hardened since. OpenAI's own warning to defenders is blunt. A low-privilege account on a machine that is behind on patches should now count as root. If your agents run code or hold shell access, patch fast and put each one in a real sandbox like gVisor or Firecracker.
Webbplats: ai-nate.com

