Hacker News new | ask | show | jobs
by samus 843 days ago
Nobody is considering giving AI unrestricted access to anything yet. Code written by AI is reviewed by humans, and I would be shocked to hear that sysadmins are considering letting AI agents execute arbitrary commands.
1 comments
singularity2001 843 days ago
I gave GPT root access, so far without regrets

admittedly I recently added a soft barrier "for dangerous commands please ask for confirmation"

link
ofrzeta 843 days ago
Does it "know" what's "dangerous"?
link
samus 843 days ago
Username checks out!
link