•1 min read•from TechCrunch
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.
Want to read more?
Check out the full article on the original site
Tagged with
#AI
#code of conduct
#Microsoft
#AI models
#AI safety
#AI principles
#safety constraints
#responsible AI
#ethical AI
#AI ethics
#human flourishing
#hacking
#human-centered AI
#trick humans
#system security
#AI governance
#generative AI
#algorithmic bias
#automation
#machine learning