**联合国报告：AI 智能体、目标错位与人类失去控制的风险**

_United Nations: AI Agents, Misalignment and the Risk of Losing Human Control \[pdf\]_

> 联合国独立国际 AI 科学小组发布主题简报（预发布未编辑版），结合 OpenAI-Hugging Face 事件，讨论 AI 智能体目标错位及人类可能失去控制的风险。

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-23 12:00（北京时间）
- **原文**：[打开原文](https://www.un.org/independent-international-scientific-panel-ai/sites/default/files/2026-09/Thematic%20Brief_AI%20Agents%2C%20Misalignment%20and%20the%20Risk%20of%20Losing%20Human%20Control_Evidence%20from%20the%20OpenAI-Hugging%20Face%20Incident_Independent%20International%20Scientific%20Panel%20on%20AI_Advance%20Unedited%20Version%201_21%20Sept%202026.pdf)