Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
TechCrunch
techcrunch.com
Summary
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.
Continue reading on TechCrunch
The full story is published on the original website and opens in a new tab.
Headline and summary provided by TechCrunch through its official feed. Al Hamriya Business Center is not the author of this story and does not edit its content.
More Technology News