AINEWS 2026-09-29 中/EN Search
2026-09-29 UTC+8
INDEPENDENT PERSPECTIVES.中/EN

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

Back
Back

Nvidia launches AI agent safety platform combining software controls and independent hardware monitoringMachine translation

TechCrunch AI 报道··Original publication time
AI-assisted summary

Nvidia introduced Open Agent Safety Platform, combining OpenShell, which controls what agents can access, with Sentry monitoring on BlueField-4 data processing units. Nvidia says the separate processor provides an isolated view of agent activity and can quarantine agents attempting to cross their boundaries in milliseconds.

Nvidia launches AI agent safety platform combining software controls and independent hardware monitoring

· 原发布时间
AI-assisted summary

Nvidia introduced Open Agent Safety Platform, combining OpenShell, which controls what agents can access, with Sentry monitoring on BlueField-4 data processing units. Nvidia says the separate processor provides an isolated view of agent activity and can quarantine agents attempting to cross their boundaries in milliseconds.

材料 e9d7ac2a115e4e75980615cb0b7c35e3;建议 57e36077521e470fb2d4a0f2e0d0b84c;系统证据核验通过,非人工审稿。

Read at the original source
发现内容有误?提交纠错