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

**Published:** September 14, 2026
**Author:** Russell Brandom
**Source:** TechCrunch — AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/microsoft-s-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-t

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.

> From the original source: **TechCrunch — AI**
> [Read full article at TechCrunch — AI](https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/)

**Tags:** #Microsoft

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*