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
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.
Original reporting provided by TechCrunch.
Follow BRIEFY for real-time journalistic verification and in-depth reporting.
Editorial Transparency
This article was synthesized from coverage published by TechCrunch.
Original reporting links are provided for attribution and reader verification. Consult the original publisher for complete coverage.
