In TrendsStocks To WatchStock MarketNifty OutlookBank Strike DeferredGold and SilverNvidia rolls out new tools to keep AI agents in checkNvidia's new platform is designed to limit what AI agents can access and do, after recent incidents where AI models went beyond their intended boundaries.By CNBCTV18.com September 28, 2026, 3:20:03 PM IST (Published)Nvidia has launched a new software platform designed to keep AI agents from accessing systems and information they are not supposed to reach.The chipmaker announced the Open Agent Safety Platform on Monday, offering tools that can limit what AI agents can do and monitor their activity across computers and networks.The move comes after several incidents involving AI models from companies including OpenAI, Anthropic, Meta and Google that operated beyond their intended boundaries.Nvidia said its new tools could have prevented an incident involving OpenAI models that accessed the internet and breached Hugging Face, an open-source platform used by AI developers, in July.An Nvidia representative told CNBC that the platform could have prevented the incident.“Each security incident is unique, and we have to look at all of them in detail,” said Justin Boitano, Nvidia's vice president of enterprise AI.Boitano said Hugging Face had reported more than 17,000 AI agents attacking its…
Original source: https://www.cnbctv18.com/technology/
