Close Menu
Daily Guardian EuropeDaily Guardian Europe
  • Home
  • Europe
  • World
  • Politics
  • Business
  • Lifestyle
  • Sports
  • Travel
  • Environment
  • Culture
  • Press Release
  • Trending
What's On

Dreaming of visiting the Taj Mahal? Getting a visa to visit India is about to get easier

November 16, 2026

European Film Awards: ‘Fatherland’, ‘La Bola Negra’ and ‘Fjord’ lead the nominations

November 16, 2026

Burnham v Johnson and Cameron: Who wins? – POLITICO

November 16, 2026

Australian MP Helen Haines leaves hospital after losing both legs in alleged car attack

November 16, 2026

Festive city breaks: Where to see Europe’s best Christmas lights in 2026

November 16, 2026
Facebook X (Twitter) Instagram
Web Stories
Facebook X (Twitter) Instagram
Daily Guardian Europe
Newsletter
  • Home
  • Europe
  • World
  • Politics
  • Business
  • Lifestyle
  • Sports
  • Travel
  • Environment
  • Culture
  • Press Release
  • Trending
Daily Guardian EuropeDaily Guardian Europe
Home»Lifestyle
Lifestyle

Nvidia launches platform to quarantine rogue AI agents in ‘milliseconds’

By staffSeptember 28, 20263 Mins Read
Nvidia launches platform to quarantine rogue AI agents in ‘milliseconds’
Share
Facebook Twitter LinkedIn Pinterest Email

Published on
28/09/2026 – 12:46 GMT+2

Nvidia is rolling out a security platform for artificial intelligence (AI) agents that more than 100 organisations are working with, including Anthropic, SpaceXAI and JPMorganChase.

Called the Nvidia Open Agent Safety Platform, it is designed to set limits on what agents can access and put them in “quarantine” within milliseconds if they cross those limits, according to an announcement from the US chipmaker.

The platform can be used across software and hardware, compute and robotics systems that run agents.

“AI’s extraordinary potential for society will only be realised if we solve AI safety,” said Jensen Huang, the CEO and founder of Nvidia.

“As we continue to discover the frontier of AI capabilities, we must accelerate discovery at the frontier of AI safety…. Together, we can raise the bar for global AI safety.”

The Nvidia Open Agent Safety Platform consists of two tools, OpenShell and Sentry.

OpenShell runs on central processing units (CPUs), the chips that handle many of the tasks needed to run AI agents. Nvidia says it works efficiently on Vera, its latest CPU designed for AI agents, and can also be adapted for chips made by other companies.

Sentry is an additional “watchdog” system that would run on a separate Nvidia chip, watching for agents that get past the software’s controls.

The organisations working with Nvidia are using or developing the technology in different ways, Nvidia says.

Anthropic has worked with Nvidia to add security controls to its Claude service for businesses to run AI agents, allowing companies to restrict what those agents can access.

SpaceX’s AI division, SpaceXAI, says it is using the platform for Cursor coding agents and Grok models, while Salesforce has integrated OpenShell with Slack so teams can see what agents are doing and approve or reject requests for additional permissions.

In finance, JPMorganChase and Citi are collaborating with Nvidia on shared open-source agent safety technology.

AI companies call for stronger safeguards

The announcement comes amid growing calls for stronger safeguards around AI agents.

In July, OpenAI admitted one of its models exploited a hidden flaw to escape a controlled test and break into Hugging Face’s servers.

Meanwhile, Anthropic said its AI model hacked into three organisations’ systems during the testing phase.

Nvidia said the incidents showed that agents could get around security controls built into an app while trying to complete their assigned tasks and that “safety and security require full-stack engineering”.

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

Keep Reading

Megaspeed says alleged Chinese spy, Alice Huang, left company last year

Chinese electric passenger plane completes first crewed flight

SpaceX catches part of its Starship rocket in historic first

Can Europe’s tech firms really replace Amazon, Google and Microsoft?

What is next for Nvidia after CEO Jensen Huang resigns?

Microsoft outage explained: what went wrong and is your data at risk?

Microsoft 365 global outage disrupts Portuguese government, health services and schools

EU leaders discuss how to boost Europe’s AI industry while tackling risks at Dublin summit

China warns US over chip curbs as suspected spy’s firm got banned chips

Editors Picks

European Film Awards: ‘Fatherland’, ‘La Bola Negra’ and ‘Fjord’ lead the nominations

November 16, 2026

Burnham v Johnson and Cameron: Who wins? – POLITICO

November 16, 2026

Australian MP Helen Haines leaves hospital after losing both legs in alleged car attack

November 16, 2026

Festive city breaks: Where to see Europe’s best Christmas lights in 2026

November 16, 2026

Subscribe to News

Get the latest Europe and world news and updates directly to your inbox.

Latest News

Backing research in a global race – POLITICO

November 16, 2026

Video. More than 2,000 migrants arrive in Spain’s Canary Islands in two days

November 16, 2026

Canada ready to turn to Chinese carmakers if US trade talks fail to protect auto sector, PM Carney says

November 16, 2026
Facebook X (Twitter) Pinterest TikTok Instagram
© 2026 Daily Guardian Europe. All Rights Reserved.
  • Privacy Policy
  • Terms
  • Advertise
  • Contact

Type above and press Enter to search. Press Esc to cancel.