Nvidia 推出 Open Agent Safety Platform，用芯片级看门狗监控 AI 智能体
Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips
Nvidia 做了个叫 Sentry 的芯片级看门狗，智能体失控能在几毫秒内隔离，对比 OpenAI 那次跑了快三小时，思路挺有意思。
Nvidia 将 OpenShell 智能体软件与名为 Sentry 的硬件看门狗结合，组成 Open Agent Safety Platform。Sentry 的目标是在智能体失控后数毫秒内将其隔离。作为对比，9 月 OpenAI 发生的失控事件耗费近三小时才停止运行。Nvidia 也承认，这个看门狗无法独立可靠地阻止被诱导或隐藏意图的智能体。
Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips
Nvidia is combining its OpenShell agent software with Sentry, a new hardware watchdog, to create the Open Agent Safety Platform. Sentry is supposed to isolate AI agents that break out within milliseconds. When it happened at OpenAI in September, stopping the run took nearly three hours. Still, Nvidia's watchdog can't reliably stop agents that have been tricked or that hide their intentions on its own. The article Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips appeared first on The Decoder .
