Verified sources.
Clear updates.
PBS NewsHour reports: Your support keeps PBS News free and accessible. Kelvin Chan, Associated Press Kelvin Chan, Associated Press Anne D'Innocenzio, Associated Press Anne D'Innocenzio, Associated Press 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.
Missing media or need the complete publisher report? Open PBS NewsHour
Media link supplied by the Scoop Newsroom app.
The text below was supplied by the Scoop Newsroom app. Third-party reporting is attributed in the source panel.
No additional independently verified detail is available beyond the summary above. The original reporting remains linked in the source panel.
Breaking news moves fast. Follow WilluChill News on X for breaking news alerts. Follow on X →
Dated changes to this report are shown here as they are published.
PBS NewsHour reports: Your support keeps PBS News free and accessible. Kelvin Chan, Associated Press Kelvin Chan, Associated Press Anne D'Innocenzio, Associated Press Anne D'Innocenzio, Associated Press 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.
