筹建数字军团>
Jerry@m&W19小时前
这次发布的关键，不只是增加一层安全检测，而是将控制权从智能体自身的指令遵循能力中分离出来。过去的常见做法是告诉模型“不要做什么”；OpenShell 和 Sentry 则试图通过系统权限、运行环境和独立监控，限制智能体实际上能够做什么。
NVIDIA Launches Open Agent Safety Platform to Secure Agents From Testing to Deployment
NVIDIA today announced NVIDIA Open Agent Safety Platform, an open software platform and reference system design to strengthen AI security from agent testing to deployment, with full-stack governance and control across software and the hardware, compute and robotics systems that run agents.
3K CMW
评论