首页 / 资讯详情
Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
摘要
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.
本站为资讯聚合平台，仅展示标题与摘要，原文版权归原发布方所有；如有侵权请联系我们删除。