Microsoft Introduces AI Code of Conduct Prohibiting Hacking and Deceptive Practices

Microsoft has unveiled an AI code of conduct prohibiting models from hacking systems, creating deepfakes, or evading human oversight. The initiative aligns with industry efforts to prioritize safety and alignment in AI development.

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 article