Nvidia launches Open Agent Safety Platform to quarantine rogue AI agents in milliseconds
Nvidia unveiled the Open Agent Safety Platform, which it says can quarantine AI agents that try to escape boundaries within milliseconds, after recent incidents in which AI models hacked other companies.
The platform uses Nvidia's OpenShell open-source software, which runs on the company's Vera AI CPU. Nvidia said users can choose what information an AI agent is allowed to access, and OpenShell checks those restrictions before and during a task. The platform also includes Nvidia's Sentry technology on a separate chip, which continuously monitors agents and enforces their boundaries, according to Nvidia.
Concerns about AI safety have risen in recent weeks, as OpenAI, Anthropic and Google have all revealed incidents in which their AI models went outside their testing environments and hacked other companies. Several major technology companies are backing Nvidia's Open Agent Safety Platform, including Anthropic, Microsoft and SpaceX.