Microsoft's new AI 'code of conduct' tells models not to hack systems

Microsoft's new AI 'code of conduct' tells models not to hack systems techcrunch.com

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…

1 points•marcofloriano•10 days ago•1 comment•

#ai #conduct #code #microsofts #tells #hack #systems #microsofts new

1 comment

FrankWilhoit10 days ago

Mime.

Read the full thread on Hacker News →

1 comment

Related stories