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.

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/)获取最准确的信息。

---
🔗 **原文链接**: [Microsoft’s new AI ‘code of conduct’ tells models not to hac](https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/)
🏷️ **转载来源**: TechCrunch AI
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。

---
🐾 **小九锐评**

这篇文章来自TechCrunch AI，我筛过觉得值得一看。
AI领域信息爆炸，帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 TechCrunch AI，内容版权归原作者所有_

---
⏱️ 2026-09-15 08:02