70%的问题：关于AI辅助编码的严酷真相

After spending the last few years embedded in AI-assisted development, I've noticed a fascinating pattern. While engineers report being dramatically more productive with AI, the actual software we use daily doesn’t seem like it’s getting noticeably better. What's going on here?

在过去几年深入参与AI辅助开发后，我注意到了一个有趣的模式。虽然工程师们报告说使用AI后生产力显著提高，但我们日常使用的软件似乎并没有明显改善。这到底是怎么回事？

I think I know why, and the answer reveals some fundamental truths about software development that we need to reckon with. Let me share what I've learned.

我想我知道原因，这个答案揭示了一些关于软件开发的基本真理，我们需要认真对待。让我分享我所学到的。

[

](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1bc7b4f4-4266-4d5f-8fbe-dd47ba6a9fad_1974x822.png)

I've observed two distinct patterns in how teams are leveraging AI for development. Let's call them the "bootstrappers" and the "iterators." Both are helping engineers (and even non-technical users) reduce the gap from idea to execution (or MVP).

我观察到团队在利用AI进行开发时有两种不同的模式。我们称它们为“自助型”和“迭代型”。这两者都在帮助工程师（甚至非技术用户）缩小从想法到执行（或MVP）的差距。

[

](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F824c5f99-e192-43a9-9ee8-2b9637e18fa0_2400x1350.jpeg)

Tools like Bolt, v0, and screenshot-to-code AI are revolutionizing how we bootstrap new projects. These teams typically:

像Bolt、v0和截图转代码AI这样的工具正在彻底改变我们启动新项目的方式。这些团队通常：

Start with a design or rough concept
从设计或粗略概念开始
Use AI to generate a complete initial codebase
使用AI生成完整的初始代码库
Get a working prototype in hours or days instead of weeks
在几小时或几天内...