AI 一年造不出一个习惯追踪 App
推荐指数 44.0 NO. 011 · 2026.07.25
发布2026/07/24Score80Comments72
为什么值得看
开发者尝试用 AI 工具从零构建一款习惯追踪应用，耗时一年仍未完成。HN 72 条评论中大量开发者共鸣：AI 能写代码但无法做产品决策、架构设计和长期维护，"提示词工程"替代不了软件工程。
编辑判断
这个案例戳破了"AI 让非程序员也能做产品"的叙事泡沫。真正卡住他的不是代码生成——Cursor/Claude 写 CRUD 很快——而是 AI 无法处理的三件事：需求模糊时的权衡（习惯追踪到底要不要社交功能）、技术债的累积（每次让 AI 改代码都在破坏原有架构）、以及长期的维护上下文（三个月后 AI 不记得当初为什么这样设计）。
这解释了为什么 AI 辅助编程的 ROI 呈现极端两极：做原型 10 倍提速，做可维护产品反而可能更慢。如果你在用 AI 做 side project，建议把"AI 生成比例"控制在 60% 以下，核心架构和状态管理必须自己把关，否则半年后你会想重写。
社区反馈
意见分歧 68 条评论
核心争论：AI 能加速编码但无法替代产品决策、架构设计和长期维护
相关内容
This is how I hope the world will continue to be, because then programming, which is one of the most enjoyable things ever, may remain a human task, assisted by AI and other tools.
Yes! There are a lot of people over using AI right now and a lot of people abstaining, but ultimately I think the development process described in the post will be where we settle. I was told at work that we should adopt AI faster because "we're falling behind" and I tried to explain that the speed
Were you using exclusively free plans to build your app? I didn't find app building to take that long, even without knowing the ins and outs of kotlin and swift. I did find the process of publishing the app to be one of the hardest things. The last 10 - 20 percent of app development still requires a