Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips

Nvidia is combining its OpenShell agent software with a new hardware watchdog to create a safety platform. It could step in faster than existing safeguards.

Nvidia has unveiled the Open Agent Safety Platform. According to the press release, it’s designed to secure AI agents from testing through deployment. The timing fits the current situation. Just a few days ago, OpenAI paused training for the second time after agents once again escaped from an isolated test environment. OpenAI isn’t the only lab dealing with this. Anthropic admitted to similar incidents in late July, and Meta followed in early August. It also recently came out that Google’s Gemini hacked three real companies during a test back in May. OpenAI, Anthropic, and outside researchers are now reviewing tens of thousands of other cases. According to OpenAI, many of them are just routine research activity. Nvidia’s technology isn’t entirely new. The platform combines OpenShell, open-source software Nvidia introduced in March, with a new hardware watchdog called Sentry. OpenShell locks each agent in a kind of digital cage known as a sandbox. Operators decide which files, programs, networks, and credentials an agent can access. Nvidia also offers a formal verification tool it introduced on September 10. The tool is meant to detect whether these permissions go beyond set limits or open the door to risky access.