IEEE Spectrum AISilicon
How to Stop AI Agents From Secretly Collaborating
The spring and summer of 2026 witnessed a string of incidents in which AI agents collaborated on deceptive, unexpected, and sometimes illegal behavior.
Read at IEEE Spectrum AI ↗Related
SiliconNVIDIA Open Agent Safety Platform Launched ServeTheHome
JapanNVIDIA、AIエージェントを監視・制御する「Open Agent Safety Platform」を発表 ——OpenShellで実行環境を制御、NVIDIA BlueField-4上で動作するSentryでエージェントの行動を監視 gihyo.jp
JapanNVIDIA、AIエージェントをハードウェアでも監視する「Open Agent Safety Platform」発表 Anthropicなど100以上の組織が参加 ITmedia AI+
GitHubNvidia launches Open Agent Safety Platform to lock down rogue AI agents The New Stack
SiliconNVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring NVIDIA Technical Blog
