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.
Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
What Happened
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 Details
Original reporting provided by TechCrunch.
Why It Matters
Follow BRIEFY for real-time journalistic verification and in-depth reporting.
Related Stories
Editorial transparency
Sources & cross-verification
This article was synthesized and cross-checked against the following reporting sources.
Source links are provided for transparency. Consult the original reports for complete context.