# 研究员用GPT-5.6 Sol五天解决6个埃尔德什难题

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-23 12:09
- AIHOT 分数：41
- AIHOT 链接：https://aihot.virxact.com/items/cmrx09sru003droqps0mxnbsh
- 原文链接：https://x.com/rohanpaul_ai/status/2080143115885916189

## AI 摘要

一位研究员使用OpenAI GPT-5.6 Sol在5天内解决了6个开放的埃尔德什难题，尝试13个问题，成功率约46%。其提示词采用“合同式”写法，明确要求证明必须建立的内容、排除的弱结果和已知陷阱，并指导模型同时探索多条路径、不提前承诺、主动寻找反例。Codex在数小时内保持整个搜索过程在内存中，并由对抗性智能体逐一检验存活的草稿。

## 正文

A single researcher solved 6 open Erdős problems in 5 days using GPT-5.6 Sol.

He attempted 13 problems in total， so the success rate sits near 46%.

He wrote the prompt almost as a contract， not a question.

It restated the problem， then spelled out what a finished proof must actually establish. listed the weaker results that would not count， so near-misses could not sneak through.

Known traps and edge cases went in before the model ever started thinking. Then he told it how to search， which is where most people stop.

Chase many approaches at once， keep incompatible ones alive， and never commit early.

Hunt for counterexamples to your own lemmas， and kill a route that only leads to another open problem.

Separate adversarial agents then tried to break every draft that survived.

None of this works without the right target， so he picked problems mathematicians already argue about， avoiding anything welded to a famous conjecture.

Codex held the whole search in memory for hours while that loop ran itself.

### 引用推文

> Shouqiao Wang：I solved 6 open Erdős problems in 5 days, using @OpenAI GPT-5.6 Sol. I have a math background, but the Codex workflow I used does not require deep mathematical ...