没有理解的自动化
Automation Without Understanding
AI总结:
探讨人工智能产出数学成果但美国削弱相关人才培养渠道这一现象,主张将数学能力视为战略资产,提出要求进行重要推理的人工智能系统以可检查形式公开关键主张,以避免战略错误。
摘要:
当下有两个发展趋势同时出现:人工智能系统已开始产出真正达到研究水平的数学成果,而美国正在削弱培养能够理解此类系统运作的人才的渠道。本文认为,综合来看,这些发展构成了一个战略错误。数学能力,即验证、解释和挑战数学推理的训练有素的能力,并非定理产出的副产品,而是一种基础设施形式,由历经数代的机构构建而成,无法按需重建。借鉴2026年5月人工智能对关于平面单位距离问题的长期埃尔德什猜想的证伪,以及近期联邦对数学科学支持的中断,本文主张将数学能力视为与半导体能力同等重要的战略资产。此外还提出,除其他措施外,要求进行重要推理的人工智能系统以形式化、机器可检查的形式公开其决策关键主张,将部分人工智能推理从不透明的说服转变为可审计的结构。
英文摘要:
Two developments are unfolding at once: artificial intelligence systems have begun to produce genuine research-level mathematics, and the United States is weakening the pipeline that produces humans capable of understanding what such systems are doing. This essay argues that, taken together, these developments amount to a strategic error. Mathematical capacity, which is the trained ability to verify, interpret, and challenge mathematical reasoning, is not a byproduct of theorem production but a form of infrastructure, built over generations by institutions that cannot be reconstituted on demand. Drawing on the May 2026 AI disproof of a longstanding Erdős conjecture on the planar unit distance problem and on recent disruptions to federal support for the mathematical sciences, the essay makes the case for treating mathematical capacity as a strategic asset on a par with semiconductor capability. It further proposes, among other measures, that AI systems performing consequential reasoning be required to expose their decision-critical claims in formal, machine-checkable form, converting part of AI reasoning from opaque persuasion into auditable structure.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。