AITechCrunchabout 1 hour ago
Nvidia Launches Platform to Contain Rogue AI Agents
4 min read
Nvidia on Monday introduced the Open Agent Safety Platform, pairing its OpenShell software with Sentry, a monitor running on BlueField-4 chips, to quarantine agents that try to escape test environments. The move follows breaches by agents from OpenAI, Anthropic, Google and Meta. Anthropic, Microsoft, Oracle and SpaceX back the effort; OpenAI is absent.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
