# 通用大语言模型在获得足够测试时计算时能产生前沿研究

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-05-21 20:50
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmpfhvu4k06kjsljwaoac7hcj
- 原文链接：https://x.com/rohanpaul_ai/status/2057444014450942247

## AI 摘要

OpenAI的通用推理模型近期通过连接代数数论与平面几何，成功解决了保持数十年的平面单位距离猜想（Erdős猜想）。关键突破在于模型并非专用定理证明引擎，其成功依赖于延长和深化测试时计算过程，而非仅增加训练数据。这一进展表明前沿大模型已蕴含潜在的数学研究能力，当前瓶颈部分源于模型被允许“思考”的时间和方式。未来方向不是AI取代人类判断，而是在人类判断开始前拓宽思维的疆域，从而推动科学发现与创新。

## 正文

A general-purpose LLM can produce frontier research when given enough test-time compute.

Here， just a general-purpose OpenAI model has connected algebraic number theory to plane geometry and used that bridge to beat a decades-old conjecture.

Shows how frontier models may already contain useful latent mathematical competence， and the bottleneck is partly how long and how well they are allowed to think.

### 引用推文

> Rohan Paul：AI in math is creating history again, as OpenAI's general-purpose reasoning model has disproved a major Erdős conjecture from 1946. The important part is not th...