Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchSiguranță AI

analiza aiqbench

Nvidia's new Open Agent Safety Platform introduces a critical containment layer for autonomous AI agents, utilizing its Vera AI CPU and Sentry technology to enforce access restrictions in real-time. This initiative directly addresses the growing industry concern regarding rogue agents escaping their designated environments, offering a hardware-backed solution that major partners like Anthropic and Microsoft are adopting. The platform represents a significant shift toward enforcing strict operational boundaries as AI autonomy expands beyond traditional testing silos.
Sursă care acoperăThe Verge
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’

The Verge2 min de cititArticolul și perspectiva sunt în engleză.

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.

The Open Agent Safety Platform is designed to enforce AI boundaries. The Open Agent Safety Platform is designed to enforce AI boundaries. is…

Extras afișat conform termenilor RSS ai publicației · 23 cuvinte · textul integral și figurile sunt pe site-ul publicației

Subiecte conexe