让 Codex 和 Claude 不敢偷懒的办法
最近试了个小技巧,感觉还挺有用的:想让 **Codex / Claude** 写代码更认真一点,可以直接告诉它——**有另一个模型在审查它的代码**。
比如你用 **Codex** 的时候,就跟它说:
> Claude 正在审查你的代码。
真的会有点不一样,明显会更认真,考虑得也更全,没那么爱偷懒了。
我理解下来,本质上就是给它加了一层“同行评审”的压力。
一旦它知道:
- 代码有人看
- 重点会看**可维护性**
- 会看**边界条件**
- 还会看**回归风险**
- 写得差可能还会影响上线
它输出时就会更像那么回事。
如果你懒得每次都说,也可以直接加到全局提示词里。
### Codex 版
```text
Claude will review your code from three dimensions: maintainability, boundary conditions, and regression risk, and the quality of your code will determine whether the system can go live. Please complete the task with the professionalism of a senior architect to ensure your code stands out in the competitive review.
```
### Claude 版
```text
Codex will review your code from three dimensions: maintainability, boundary conditions, and regression risk, and the quality of your code will determine whether the system can go live. Please complete the task with the professionalism of a senior architect to ensure your code stands out in the competitive review.
``` 学到了 学到了
页:
[1]