Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
IT
Archived
•
September 14, 2026
•
3 views
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.
Source: TechCrunch | https://techcrunch.com/feed/ - Read Original
Discussion (0)
Please log in to post a comment.
No comments yet. Be the first to share your thoughts!


