# NVIDIA's Director just dropped an insane 11-page paper that breaks how everyo...
Canonical: https://social-archive.org/yena/sOUPVXnzhb
Original URL: https://x.com/Mnilax/status/2072005973678436712
Author: Mnimiy
Platform: x
## Content
NVIDIA's Director just dropped an insane 11-page paper that breaks how everyone is building AI agents. The shift: you stop trusting the model to be safe. You build a system around it that assumes it's already hijacked. Plan → Approve → Act → Enforce → Repeat if your agent reads email, the web, or a tool's output, a single hidden line can give it orders and no prompt will save you. so they wrap the model: an orchestrator plans, a policy approver checks every action, an enforcer kills it before it touches anything real. stop asking if the model is safe. build it so a hijacked one still can't do damage. read the paper first, then the article below.