< BACK TO NEWS
importantSYS.SOURCE: TechCrunch• 2026-09-28T18:31:23Z

Nvidia Unveils Open Agent Safety Platform to Contain Rogue AI Behavior

Nvidia introduces the Open Agent Safety Platform, combining OpenShell and Sentry to secure AI agents against unauthorized access. The solution uses hardware-level monitoring via BlueField-4 DPUs to isolate and contain rogue AI behavior, addressing recent security breaches in the industry.

As the debate rages over whether the recent spate of rogue AI agents is a step toward AGI or a more conventional engineering problem, Nvidia is offering its own answer to problem. Nvidia CEO Jensen Huang on Monday introduced a toolkit of software and hardware products that add independent security layers around AI agents to […]

Read original article

*** END OF TRANSMISSION ***