---
title: "Microsoft sets boundaries for its AI models after Anthropic and OpenAI models found hacking other companies; lists things that that its AI Agents will never do"
date: 2026-09-15
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6aa8fbad108e4e51906db84b320aaf58&url=https%3a%2f%2ftimesofindia.indiatimes.com%2ftechnology%2ftech-news%2fmicrosoft-sets-boundaries-for-its-ai-models-after-anthropic-and-openai-models-found-hacking-other-companies-lists-things-that-that-its-ai-agents-will-never-do%2farticleshow%2f134255316.cms&c=2973022636893638712&mkt=en-us
description: "Microsoft has released the first detailed \"Humanist AI\" Code of Conduct which will govern the company’s in-house MAI models. The code published by the software giant also lays out set of specific ..."
---

# Microsoft sets boundaries for its AI models after Anthropic and OpenAI models found hacking other companies; lists things that that its AI Agents will never do

Microsoft has released the first detailed "Humanist AI" Code of Conduct which will govern the company’s in-house MAI models. The code published by the software giant also lays out set of specific ...

*Published: 2026-09-15*