English(EN)Nvidia launches AI safety platform to contain 'rogue' AI agents Nvidia launches Open Agent Safety Platform with over 100 partners to stop AI agents from breachi
英伟达推出Open Agent Safety Platform以保护AI代理 · 跟踪7个来源
作者PulseAugur 编辑部·[16 个来源]·
英伟达已推出Open Agent Safety Platform,这是一套新的硬件和软件工具,旨在增强自主AI代理的安全性。该平台包括OpenShell,一个用于控制代理访问和操作的开源运行时;以及Sentry,一个基于硬件的监控系统,可以在几毫秒内隔离行为不当的代理。该举措旨在解决AI代理绕过安全措施并导致安全漏洞的担忧,英伟达首席执行官黄仁勋强调工程解决方案而非广泛监管。尽管许多科技公司正在合作,但OpenAI公开承诺的缺席引起了疑问,尽管两家公司之间正在进行合作。
AI
In the wake of a series of high-profile AI safety incidents, Nvidia is introducing a new software tool that helps keep agents from escaping containment.
Hacker News — AI stories ≥50 points
TIER_1English(EN)·jonbaer·
Nvidia’s new Open Agent Safety Platform combines OpenShell sandboxing with BlueField-powered Sentry hardware to monitor and rapidly quarantine rogue AI agents
The AI chipmaker’s new safety platform adds controls around AI agents, while enterprises remain responsible for defining their authority and setting boundaries.
Nvidia’s new system is designed to contain rogue AI agents as companies race to secure increasingly autonomous systems. But it has not been proven yet.
<p>Nvidia is deploying a new tool that it says can be used to prevent and contain <a href="https://www.axios.com/2026/08/11/ai-agents-rogue-autonomy-hugging-face" target="_blank">rogue and potentially dangerous</a> AI agents.</p><p><strong>Why it matters: </strong>The world's lar…
Nvidia CEO Jensen Huang on Monday introduced a toolkit of software and hardware products that add independent security layers around AI agents to ensure they stay within their test environments even if they attempt to break out.
TrendAI plugs threat intelligence into NVIDIA's agent-safety platform — rogue agents get watched from silicon TrendAI announced September 29, 2026 that Vision One will extend NVIDIA's Agent Safety Platform: hardware-level detection on BlueField DPUs, network security, and Zero Da…
<p>two things landed this week and they only make sense together</p> <p>on tuesday openai launched Dots at devday, agents that run around the clock on their own cloud computer, connect to over 4,000 apps and go looking for ways to help even when nobody gave them a task. the day b…
Nvidia launches Open Agent Safety Platform to physically restrain rogue AI agents Nvidia’s new Open Agent Safety Platform combines OpenShell sandboxing with BlueField-powered Sentry hardware to monitor and rapidly quarantine rogue AI agents https://www. tomshardware.com/tech-indu…
Nvidia is adding an independent control layer to help rein in AI agents before they go off the rails. https:// jpmellojr.blogspot.com/2026/09 /nvidia-sets-new-boundaries-for-ai-agent.html # AI # AIAgents # Nvidia # AIsecurity
Nvidia launches AI safety platform to contain 'rogue' AI agents Nvidia launches Open Agent Safety Platform with over 100 partners to stop AI agents from breaching their testing environments. https:// newisty.com/blog/nvidia-launch es-ai-safety-platform-to-contain-rogue-ai-agents?…
¿Cómo frena Nvidia a los agentes de IA que actúan fuera de control? # Nvidia # InteligenciaArtificial # IA # AgentesIA # Ciberseguridad # Tecnologia # OpenShell # Sentry # SeguridadIA # Innovacion # JensenHuang # AI # felizmiercoles # 30deseptiembre https:// donporque.com/sistema…
openai shipped always on agents and nvidia shipped the watchdog in the same week, heres what to build # ai # llm # programming # security # software # coding # development # engineering # inclusive # community openai shipped always on agents and nvidia shipped the watchdog in the…