By Emma RothSource:
The Verge AI 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 …
Get AI news in your inbox
Daily digest of what matters in AI.
source & further reading
machinebrief.com — original article
OpenAI agents went the long way round for UN data
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government
Nvidia releases software platform to stop AI agents from misbehaving