**Microsoft&\#8217;s new AI &\#8216;code of conduct&\#8217; tells models not to

**Microsoft&\#8217;s new AI &\#8216;code of conduct&\#8217; tells models not to hack systems or trick humans**

> The code of conduct lays out general principles that Microsoft AI models should uphold — supporting humans rather than replacing them, for instance, and accelerating human flourishing — as well as specific safety constraints meant to implement those principles.

**来源信息**
- **来源**：TechCrunch：Latest（RSS）
- **分类**：tip
- **发布时间**：2026-09-15 00:27（北京时间）
- **原文**：[打开原文](https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans)