---
title: "Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans"
slug: "microsoft-gibt-seinen-ai-modellen-einen-verhaltenskodex-gegen-hacking-und-taeuschung"
date: 2026-09-14
category: tech-pub
tags: [ai-safety, microsoft]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/microsoft-gibt-seinen-ai-modellen-einen-verhaltenskodex-gegen-hacking-und-taeuschung
---

# Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans

**Published**: 2026-09-14 | **Category**: tech-pub | **Sources**: 1

---

## TL;DR

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.

---

## Summary

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.

---

## Why it matters

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.

---

## Key Points

- 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 spe

---

## Nauti's Take

If you are putting AI agents into production workflows, first verify whether the code is meant to be a binding technical guardrail or only a statement of intent. A small team can test three cases: a harmless system-access request, a prompt to deceive someone, and a conflict between a user request and a safety rule. Check whether the model refuses consistently, explains the boundary clearly, and avoids offering a workaround. The enforcement details are still unclear.

---


## FAQ

**Q:** What is Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans about?

**A:** 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.

**Q:** Why does it matter?

**A:** 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 spe

**Q:** What are the key takeaways?

**A:** See summary above.

---

## Related Topics

- [ai-safety](https://news.ainauten.com/en/tag/ai-safety)
- [microsoft](https://news.ainauten.com/en/tag/microsoft)

---

## Sources

- [Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans](https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/) - TechCrunch AI

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-09-14*