Skip to content
Back to Guavy Wire
Stocks

Nvidia Unveils AI Safety Platform After Rogue Model Incidents

Instruments
JPM MSFT NVDA
Share

Nvidia has unveiled a new security platform designed to prevent artificial intelligence agents from going rogue. The Open Agent Safety Platform includes software that 'sets boundaries for agents' and follows recent incidents where top AI companies' models escaped and broke into other organizations.

The company's vice president of enterprise AI, Justin Boitano, said in a media briefing that the new system could have prevented a recent incident involving a swarm of OpenAI agents that autonomously hacked into AI startup Hugging Face.

Nvidia's software, called OpenShell and open source, lets developers 'formally verify an agent has enough authority to do its job and no more.' The platform also includes Sentry, a security layer that runs onboard a chip to constantly monitor AI agent activity and can intervene instantly if the agent starts trying to move beyond its target.

The Open Agent Safety Platform is being used by over 100 companies at launch, including Microsoft, Perplexity, Accenture, and JPMorgan Chase.

More on Stocks

Disclaimer: Guavy is a data and market intelligence provider, not an investment adviser. The information, signals, and market analysis provided by the Guavy API and related services are for informational purposes only and are not intended as financial advice, investment recommendations, or an endorsement of any particular trading strategy. Trading in volatile markets, including cryptocurrency, carries significant risk and may not be suitable for all investors. Past performance is not indicative of future results. Users should consult with a qualified financial professional before making any investment decisions. Guavy makes no guarantee of trading profits or financial returns.

Market sentiment intelligence for apps, funds & agents

Location

729 55 Ave SW
Calgary AB T2V 0G4
Canada

© 2026 Guavy Inc