# 鼓励性话语也能提升大语言模型表现，Claude 意外改进黎曼猜想零点下界

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-08-11 02:58
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmsnm4p6q0d70rohfcsvww6az
- 原文链接：https://x.com/kimmonismus/status/2086889910930215413

## AI 摘要

研究发现，“相信自己！”这类鼓励性话语不仅能激励人，也能帮助大语言模型提升表现。Anthropic 让未发布版 Claude 尝试攻克黎曼猜想，虽未证明，却意外将满足假设的 zeta 函数零点比例下界从 41.6% 提升至 67.2%，期间协调了 60 个子智能体并形式化验证了结果。

## 正文

It's sweet that motivational sayings like "believe in yourself!" not only motivate people, especially children, and achieve better results, but even help LLMs achieve better results.

Treat your model the way you want to be treated. ❤️

### 引用推文

> Chubby♨️：Absolutely insane. This might be the clearest glimpse yet of how AI will transform scientific discovery. Anthropic asked an unreleased version of Claude to take...