人工智能安全中的数学：致数学家们的邀请
Math for AI safety: an invitation for mathematicians
- Cornell University（康奈尔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文按数学领域邀请数学家参与AI安全研究，提出各领域开放问题，以设计可读、可引导、与人类合作的AI。
AI中文摘要：
人工智能威胁着要超越人类的理解和控制。我们需要新的数学来设计对人类而言可读、可引导且与人类合作的人工智能。我按数学领域组织这份邀请，以便你可以直接转向自己的领域：逻辑和博弈论用于合作；概率论用于智能体和世界模型；代数和表示论用于学习特征；分析和几何用于泛化和训练动态。每个部分末尾都提出了一个开放问题，这些问题对于没有人工智能安全经验的在职数学家来说是可以理解的。
英文摘要：
Artificial intelligence threatens to outrun human understanding and control. New mathematics is needed to design AI that is legible, steerable, and cooperative with humanity. I organize this invitation by mathematical field, so you can turn straight to your own: logic and game theory for cooperation; probability for agency and world-models; algebra and representation theory for learned features; analysis and geometry for generalization and training dynamics. Each section ends with an open problem that is accessible to a working mathematician with no prior experience in AI safety.
