Nvidia Debuts System Designed to Stop AI Agents From Going Awry

· Bloomberg ·

1 min read Original article ↗
Nvidia Rolls Out New Tools to Keep AI Agents in Line

Takeaways by Bloomberg AI

Nvidia Corp. introduced a new double-layered artificial intelligence security system that it says would have prevented the recent high-profile breach of Hugging Face by OpenAI’s AI models.

The semiconductor giant, which has been rapidly expanding its product lineup beyond chips, is rolling out two open-source software security tools that can be run on its hardware. They’re designed to control what AI agents can access in real time and shut them down when they break the rules.