Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
中文摘要
英伟达AI安全平台可在毫秒内隔离越界AI代理。它旨在遏制流氓行为，响应黑客事件，并利用OpenShell技术。
English Summary
Nvidia's new AI safety platform quarantines rogue agents within milliseconds. The Open Agent Safety Platform monitors and contains AI that attempts to escape, responding to recent hacking incidents.
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.