Microsoft’s new AI ‘code of conduct’ 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.
Read original: https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/
原文：https://www.a8q9.cn/en/article/en-microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-s.html