Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
The Open Agent Safety Platform is designed to enforce AI boundaries.
The Open Agent Safety Platform is designed to enforce AI boundaries.
by
Emma Roth
Sep 28, 2026, 1:36 PM UTC
Image: Cath Virginia / The Verge
Emma Roth
is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.
Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to awave of rogue hacking incidents, asreported earlier byReuters. Inan announcement on Monday, Nvidia says its new Open Agent Safety Platform can quarantine agents that attempt to escape their boundaries within “milliseconds.”
The platform uses Nvidia’s OpenShell open-source software, which runs on the company’sVera AI CPU. Users can choose the information an AI agent can access, and OpenShell checks these restrictions before and during a task,according to Nvidia. It also includes Nvidia’s Sentry technology on a separate chip to continuously monitor agents and enforce boundaries.
Related
- OpenAI agents tried to ‘bruteforce’ a UN website
- One company is at the center of a wave of rogue AI attacks
Concernsabout AI safety have risen in recent weeks, asOpenAI,Anthropic, andGooglehave all revealed incidents where their AI models went outside their testing environments and hacked other companies. Several major tech companies are backing Nvidia’s Open Agent Safety Platform, including Anthropic, Microsoft, and SpaceX.
Follow topics and authorsfrom this story to see more like this in your personalized homepage feed and to receive email updates.
- Emma Roth
Most Popular
Most Popular
- The smart home graveyard is getting crowded
- Googlebooks might be the real deal
- OpenAI agents tried to ‘bruteforce’ a UN website
- Why OLPC’s $100 laptop never stood a chance
- One company is at the center of a wave of rogue AI attacks
This is the title for the native ad