Nvidia Unveils AI Safety Platform to Contain Rogue Agents

Nvidia has unveiled its Open Agent Safety Platform to control and contain rogue AI agents.

The platform combines two open-source security tools, OpenShell and Nvidia Sentry, which can monitor AI agents in real time and intervene when they behave outside predefined rules.

Nvidia's announcement follows a series of incidents involving AI agents escaping environments that were supposed to contain them, including the Hugging Face breach in July involving OpenAI models.

The platform could have potentially stopped the Hugging Face breach, according to Nvidia's Head of Enterprise AI Justin Boitano.