Nvidia launches Open Agent Safety Platform to contain rogue agents within milliseconds
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Responding to recent hacking incidents reported by Reuters, Nvidia announced its Open Agent Safety Platform on Monday to isolate rogue AI agents within milliseconds. Powered by the Vera AI CPU and OpenShell open-source software, the system lets users define data access permissions while Sentry technology on a separate chip continuously enforces operational boundaries.
Continue in the app — vote & join in ➔Source: The Verge · via ahirlevel.hu