智能体
x.com ·
@Satya Nadella (@satyanadella)
微软扩展 Project Perception，强化 Agent 风险持续评估与权限管控
Satya Nadella 表示，微软正将“把模型视为内部风险、安全控制置于模型之外”的原则落地，扩展 Project Perception，新增持续评估 agent 风险、自适应调整权限和遏制威胁的能力。具体实现细节与效果尚需参考其博客原文。
AI推荐理由 微软 CEO 亲自宣布扩展 Project Perception，新增持续评估 agent 风险、动态调整权限和威胁遏制能力，属于 agent 安全治理方向的官方产品更新，对 AI Agent 落地有实际参考价值。但正文仅为简短推文，具体技术细节、评估方法和效果数据均需查看链接博客，信息密度有限；互动量仅作传播信号，未据此加分。
72
浏览 43,727
点赞 476
评论 72
转发 76
正文
I recently wrote about why we need to treat models as insider risks, with security controls sitting outside the model itself.
Today, we're putting that principle into practice by expanding Project Perception with new capabilities to help continuously assess agent risk, adapt permissions, and contain threats.
https://blogs.microsoft.com/blog/2026/10/19/securing-the-agentic-insider/