HackerNews中文版

我一直想把这件事写下来，因为它具有惊人的可重复性，而且我希望有人能早点告诉我。在过去一年左右的时间里，我的开发速度相对于我自己在 2019 年左右的基线，轻松提高了 20 倍，有时甚至更多。这并不是因为我打字更快，或者因为我偷工减料，而是因为我改变了使用 AI 的方式。简而言之：我不在编辑器中使用 AI。我在浏览器中并行使用两个 AI，并提供完整的上下文。以下是设置。我打开两个标签页：一个 AI 充当“构建者”。它获得大量上下文并承担繁重的工作。一个 AI 充当审阅者。它只查看差异并尝试查找错误。就是这样。没有插件，没有特殊工具。只有浏览器标签页和一个终端。重要的是上下文。我没有要求提供代码片段，而是粘贴整个文件或模块并解释目标。我要求 AI 首先解释方法，包括权衡，然后再编写代码。这迫使我保持对架构的控制，而不是接受一个我不理解的 blob。一个典型的流程如下所示：1. 粘贴几个相关文件（通常跨语言）。2. 描述我想要的更改，并要求解释选项。阅读并总结概念、维基百科等。3. 选择一种方法。就权衡、概念、对抗性安全等进行广泛的对话。寻找操作系统允许的做事方式。4. 让 AI 在所有文件中实现它。5. 将差异复制到第二个 AI 中，并要求它查找回归、缺失参数或细微的破坏。6. 修复它找到的任何内容。发布。第二个 AI 捕获了许多我快速移动时会错过的东西。比如“你更改了这个调用签名，但没有更新一个调用者”或“这个默认值微妙地改变了行为”。让我惊讶的是跨堆栈工作变得有多快。过去由于跨越边界（Swift → Obj-C → JS，或后端 → 前端）而停滞的事情变得简单了，因为 AI 可以同时推理所有这些。我特意对“外科手术式编辑”保持严格。除非明确要求，否则我不允许 AI 重写文件。我要求添加或更改确切的行。这使得差异保持较小且可审查。这与自动完成风格的工具非常不同。这些工具非常适合本地编辑，但它们仍然让你成为跨文件的集成者。这种方法颠覆了这一点：你保持架构师和审阅者的身份，AI 完成集成工作，第二个 AI 进行健全性检查。总共花费我大约 40 美元/月。真正的成本是纪律：始终提供上下文，始终审查差异，并且从不粘贴你不理解的代码。我分享这一点是因为它对我来说是一个真正的变革，而不是一个噱头。很乐意回答有关限制、故障模式或此方法失效之处的问题。以下是我为我们团队的开发人员编写的维基式概述： https://community.intercoin.app/t/ai-assisted-development-playbook-how-we-ship-faster-without-breaking-things/2950

查看原文

I’ve been meaning to write this up because it’s been surprisingly repeatable, and I wish someone had described it to me earlier.Over the last year or so, my development speed relative to my own baseline from ~2019 is easily 20x, sometimes more. Not because I type faster, or because I cut corners, but because I changed how I use AI.The short version: I don’t use AI inside my editor. I use two AIs in parallel, in the browser, with full context.Here’s the setup.I keep two tabs open:One AI that acts as a “builder”. It gets a lot of context and does the heavy lifting.One AI that acts as a reviewer. It only sees diffs and tries to find mistakes.That’s it. No plugins, no special tooling. Just browser tabs and a terminal.The important part is context. Instead of asking for snippets, I paste entire files or modules and explain the goal. I ask the AI to explain the approach first, including tradeoffs, before it writes code. That forces me to stay in control of architecture instead of accepting a blob I don’t understand.A typical flow looks like this:1. Paste several related files (often across languages).2. Describe the change I want and ask for an explanation of options. Read and summarize concepts, wikipedia, etc.3. Pick an approach. Have extensive conversations about trade-offs, concepts, adversarial security etc. Find ways to do things that the OS allows.4. Let the AI implement it across all files.5. Copy the diff into the second AI and ask it to look for regressions, missing arguments, or subtle breakage.6. Fix whatever it finds.Ship.The second AI catches a lot of things I would otherwise miss when moving fast. Things like “you changed this call signature but didn’t update one caller” or “this default value subtly changed behavior”.What surprised me is how much faster cross-stack work gets. Stuff that used to stall because it crossed boundaries (Swift → Obj-C → JS, or backend → frontend) becomes straightforward because the AI can reason across all of it at once.I’m intentionally strict about “surgical edits”. I don’t let the AI rewrite files unless that’s explicitly the task. I ask for exact lines to add or change. That keeps diffs small and reviewable.This is very different from autocomplete-style tools. Those are great for local edits, but they still keep you as the integrator across files. This approach flips that: you stay the architect and reviewer, the AI does the integration work, and a second AI sanity-checks it.Costs me about $40/month total. The real cost is discipline: always providing context, always reviewing diffs, and never pasting code you don’t understand.I’m sharing this because it’s been a genuine step-change for me, not a gimmick. Happy to answer questions about limits, failure modes, or where this breaks down.Here is a wiki-type overview I put together for our developers on our team: https://community.intercoin.app/t/ai-assisted-development-playbook-how-we-ship-faster-without-breaking-things/2950

告诉 HN：我写代码和交付代码的速度比五年前快了大约 20 到 50 倍。