AINewsnow

NVIDIA's agent safety bet: put the guardrails outside the agent

This story is from 2026-09-28. It is preserved in the archive; the latest stories are on the live feed.

Photo by Pokiiri via Wikimedia Commons , CC BY-SA 4.0 , unchanged. This older DGX board is not a photo of NVIDIA Sentry or BlueField-4. NVIDIA introduced its Open Agent Safety Platform today . Its premise is concrete: an AI agent should not be in charge of enforcing the rules that limit it. Put con…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-28 15:27 · DEV Community — AI
    NVIDIA's agent safety bet: put the guardrails outside the agent

More stories

  1. NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
  2. Nvidia’s Answer to Rogue Agents Is an Open-Source AI Security System — Wired AI
  3. Add Runtime Controls to AI Agents with NVIDIA OpenShell — NVIDIA Technical Blog
  4. How NVIDIA DSX MaxLPS Maximizes AI Factory Throughput and Efficiency — NVIDIA Technical Blog
  5. Nvidia (NVDA) Boosts Stock Buyback Authorization by $150 Billion — Bloomberg AI
  6. Artificial Analysis launches the Cyber Index Alliance with partners Collinear, IBM, Nvidia, and Vercel to evaluate how AI agents find and fix vulnerabilities (Artificial Analysis) — Techmeme
  7. Nvidia Releases Software It Says Can Prevent AI Agents From Going Rogue — Wall Street Journal Technology
  8. Nvidia launches record $150bn share buyback — Financial Times AI

Get the daily brief of stories like this at 6:30 every morning →