Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an 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’s Vera 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 …
Read the full story at The Verge.
More in Technology
Dreame’s step-climbing X50 Ultra mopping vacuum is hundreds off
September 28, 2026
Bose’s first wired earbuds in 11 years add noise canceling
September 28, 2026
The SaaSpocalypse that wasn’t, with Atlassian CEO Mike Cannon-Brookes
September 28, 2026
Philips’ motion-tracking smart toothbrush uses AI to make you a better brusher
September 28, 2026
SpaceX preps next-gen Starlink as Amazon’s competitor stalls
September 28, 2026
பிச்சு உதறும் பேசிக் வேரியண்ட்.. SONY கேமரா.. AMOLED டிஸ்பிளே.. 5400mAh பேட்டரி.. 50W சார்ஜிங்.. எந்த மாடல்?
September 28, 2026
Latest News
Lindsay Lohan to Star in Netflix Romance ‘Return to You’ for ‘Mean Girls’ Director Mark Waters
September 28, 2026
Strap-On and All, ‘Rose’ Puts Sandra Hüller Back in the Oscar Conversation
September 28, 2026
Neil Patrick Harris, Julianne Hough, Austin Scott to Return to Broadway in ‘Damn Yankees’
September 28, 2026
Shawn Levy Inks Overall Deal With Disney’s 20th Television
September 28, 2026
"தாய் , தந்தை , மனைவி பிள்ளைகளுடன் வாழ்வதே பாசம் " விஜய்யை நேரடியாய் வம்பிழுத்த EPS !
September 28, 2026
‘The Day the Earth Stood Still’: THR’s 1951 Review
September 28, 2026