Nvidia 推出 Open Agent Safety Platform，称可在毫秒级隔离失控 AI 智能体
Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
Nvidia 发布 Open Agent Safety Platform，称能在"毫秒级"内隔离试图越界的 AI 智能体。该平台基于开源软件 OpenShell，运行于 Nvidia 的 Vera AI CPU，用户可限定智能体可访问的信息，OpenShell 会在任务执行前和执行中检查这些限制。平台还包含 Nvidia 的 Sentry 技术。
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 …
来源：The Verge：AI（RSS） · theverge.com