微软扩展 Project Perception 智能体安全能力
I recently wrote about why we need to treat models as insider risks, with security controls sitting outside the model itself.
AI 导读
Satya Nadella 表示，此前曾撰文主张把模型视为内部风险、将安全控制置于模型之外；今天微软通过扩展 Project Perception 将这一原则付诸实践，新增持续评估智能体风险、自适应调整权限和遏制威胁的能力。
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://t.co/ec3Z2B260G