Nvidia Unveils Security Platform to Stop AI Agents From Going Rogue

The Open Agent Safety Platform includes software that sets boundaries for AI agents

Associated Press

Sep 28, 2026 — 3 min read

Photo of Nvidia CEO Jensen Huang arrives as President Donald Trump hosts a State Dinner for China's President Xi Jinping on Thursday, Sept. 24, 2026, in Washington, by Alex Brandon/AP

Sept. 28, 2026 (AP) – Nvidia on Monday unveiled a new security platform designed to stop artificial intelligence agents from going rogue, saying it sets “boundaries” that could have stopped previous breaches.

The announcement of the company's Open Agent Safety Platform follows a series of revelations from top AI companies about their models escaping and breaking into other organizations.

Sign Up for FREE for Section A of '150 Years of American Telecommunications'

Post tagged in

AI Justin boitano Cybersecurity NVIDIA Earlence Fernandes UCSD OpenShell ARM Intel Microsoft Perplexity Accenture JP Morgan Chase

FCC to Consider New Spectrum Auction, Slate of Other Wireless Initiatives

At its Oct. 29 meeting, the FCC will also consider blocking China-based labs from its equipment certification program

Google, Constellation Deal Adds 890 MW to PJM Grid

The agreement marks a major step toward securing reliable, carbon-free power as electricity demand from data centers grows

McDonald's Sued Over AI Tool That Recommends Prices to U.S. Franchisees

'The result is algorithmic price-fixing aimed at customers who are already stretched thin,' reads the complaint

NTIA Still Finalizing Eligible Locations for New BEAD Round

The agency is waiting for new broadband coverage data from the FCC

Popular Tags

FCC

Broadband Breakfast Course Traces 150 Years of American Telecommunications

Broadband's Impact

BEAD

NTIA

AT&T Forms New Fiber Joint Venture with Gigapower, Lumen Assets

AT&T

Infrastructure