Nvidia announces security system to stop AI agents from going rogue

Nvidia said more than 100 organizations are using the platform, which it says could have stopped the Hugging Face hack by OpenAI agents.

Read the full story at CBS News Technology ↗

Timeline · 2 reports

2026-09-29 12:00 · IEEE Spectrum AI
How to Stop AI Agents From Secretly Collaborating
2026-09-28 12:36 · CBS News Technology
Nvidia announces security system to stop AI agents from going rogue

More stories

NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
AI firms sign 'morally binding' self-policing pledge in White House meeting — The Hill Technology
OpenAI hit with landmark lawsuit following Hugging Face hack — Axios AI+
FTC is investigating OpenAI, Anthropic and other AI companies over product risks — CNBC Technology
OpenAI is sued over rogue AI Hugging Face cyberattack — CNBC Technology
An interview with OpenAI Chief Research Officer Mark Chen on the Hugging Face incident, slowing AI development, shifting 5%-10% of compute to safety, and more (Will Douglas Heaven/MIT Technology Review) — Techmeme
OpenAI takes on rivals with launch of new dots agent — The Independent Tech
Xenova's Whisper Tiny Brings Free Speech Recognition to Any Browser — AlphaSignal

Get the daily brief of stories like this at 6:30 every morning →