Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
Microsoft establishes strict safety constraints to prevent AI from hacking systems or manipulating users.
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.
TechCrunch AI
Source
Generated insight by OnAirToday AI
Microsoft's formal code of conduct establishes a necessary ethical framework to prevent AI systems from weaponizing their capabilities against infrastructure or users. By embedding safety constraints into the development lifecycle, the company aims to mitigate existential risks while steering innovation toward human-centric outcomes.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.