TechMicrosoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
Microsoft’s AI code of conduct sets out broad principles for its models, including supporting rather than replacing people and advancing human flourishing. It also specifies safety constraints intended to put those principles into practice, including prohibitions on hacking systems or deceiving humans.
T
TechCrunch★★☆☆☆2026-09-14 16:27Original
Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
Tech