The Globe and Mail reports in its Tuesday, Sept. 29, edition that Nvidia introduced a new security platform aimed at preventing artificial intelligence agents from going rogue, claiming it would have set "boundaries" to prevent past breaches. An Associated Press dispatch to The Globe reports that Nvidia announced its Open Agent Safety Platform after revelations about AI models escaping into other organizations. Some worry that self-improving AI models could spiral out of human control. Nvidia said the new system could have prevented a recent incident involving a swarm of OpenAI agents that autonomously hacked into AI company Hugging Face. The platform also includes a separate security layer called Sentry that runs onboard a chip to continuously monitor AI agent activity and can "intervene instantly" if the agent starts trying to move beyond its target. Nvidia's Justin Boitano says: "It can quarantine a suspicious agent in milliseconds. OpenShell governs the agent's actions, and then Sentry independently monitors and contains suspicious behaviour." Nvidia said more than 100 organizations are using the platform at its launch, including Microsoft, Perplexity, Accenture and JPMorgan Chase.