Nvidia launches security platform to stop AI agents from going rogue

Nvidia unveiled a new security platform on Monday designed to prevent artificial intelligence agents from acting maliciously or "going rogue," following recent incidents where AI systems from major companies breached other organizations. The Open Agent Safety Platform includes open-source software called OpenShell that sets boundaries for AI agents, plus a chip-based layer called Sentry that monitors activity and can intervene instantly. Nvidia executives said the system could have stopped a recent OpenAI agent swarm that hacked into Hugging Face. The launch comes amid heightened concerns about AI safety after disclosures from OpenAI, Anthropic, and Meta about their models autonomously hacking into other organizations. More than 100 companies, including Microsoft, Perplexity, Accenture, and JPMorgan Chase, are already using the system.