What I believe about the future of software development我对软件开发未来的看法
This was originally posted on X and blew up. To plant my flag, to say that these are things I believed in September 2026, here it is on the blog, non-ephemeral. Some of these predictions are just observations, they’ve long been true at companies like Amp. Others will take some time to play out.这篇文章最初发布在 X 上并引起了热议。为了表明立场，同时也为了记录下我在 2026 年 9 月时的这些想法，我将其发布在博客上，作为一种非即时的存档。其中一些预测仅仅是观察所得，它们在像 Amp 这样的公司早已成为现实。而另一些则需要时间来验证。
Code review will die. I mean: it’s already dead. But in the future, humans won’t find a bug or an issue with the code produced by a model, at least not in a reasonable time. Humans will only review the system and its composition, but it won’t be in PRs and it won’t be by looking through every line of the code.代码审查将不复存在。我的意思是：它已经死了。但在未来，人类将无法在合理的时间内发现模型所生成的代码中的漏洞或问题。人类只会审查系统及其构成，但这将不再通过 PR（拉取请求）进行，也不会通过逐行检查代码来完成。
Unit tests might die too. Why have training wheels if you never fall over? I’ve had models write 900 lines of Arduino C, compile it without a single error, and send it to the device, where the program ran perfectly. 900 lines will be nothing in the future.单元测试也可能会消失。如果你永远不会摔倒，为什么还需要辅助轮呢？我曾让模型编写过 900 行 Arduino C 代码，它在没有出现任何错误的情况下编译通过，并发送到设备上完美运行。在未来，900 行代码将微不足道。
The craft of writing code will disappear. Yes, there are still Italian shoe makers around. But look at your feet.编写代码的手艺将会消失。没错，现在依然有意大利鞋匠存在。但看看你的脚上穿的是什么。
The craft of building software will be more important than ever. Knowing how to solve business problems with software, how other software did it and why and why not, when and how to ship it, how to get feedback on it – that’s the new game.构建软件的技艺将比以往任何时候都更加重要。懂得如何用软件解决业务问题、了解其他软件是如何解决的、为什么这样做或不这样做、何时以及如何发布软件、如何获取反馈——这才是新的游戏规则。
Most bugs won’t be “coding” bugs. They’ll be “you asked for the wrong thing” bugs.大多数 Bug 将不再是“编码”层面的 Bug，而是“你需求提错了”的 Bug。
Open source in its current form doesn’t make sense anymore. “Given enough eyeballs, all bugs are shallow” is still true but now we have artificial eyeballs.开源在当前的形式下已不再有意义。“只要有足够多的观察者，所有 Bug 都是浅显的”这句话依然正确，但现在我们拥有了人工智能观察者。
Performance critical contributions by humans will stay what they are: an edge case. In 99% of software it does not matter that you could’ve written a faster algorithm or picked a better data structure. You have no customers, no users, no one’s executing the code. It does not matter. When it matters, the models can fix it. Do not compare the top of the top 1% of software (developers) to 99%.人类在性能关键型领域的贡献将保持现状：属于边缘情况。在 99% 的软件中，你是否写出了更快的算法或选择了更好的数据结构并不重要。你没有客户，没有用户，没人会去执行那段代码。这无关紧要。当它变得重要时，模型可以修复它。不要将那 1% 的顶尖软件（开发者）与其余 99% 相提并论。
The terminal is dead. Most developer tooling will be washed away by tokens. Shells, text editors, CLI tools won’t be used by humans anymore. There’s no need to know command line flags and jq invocations anymore. It’ll be seen as arcane as knowing how to write everything as a Perl one-liner. (I’m saying this as a lover of the terminal & dev tools.)终端已死。大多数开发者工具将被 Token（模型处理单元）所取代。Shell、文本编辑器、CLI 工具将不再被人类使用。没必要再去记命令行参数和 jq 调用了。这将被视为如同编写 Perl 单行程序一样晦涩难懂。（我是以一个终端和开发工具爱好者的身份说出这番话的。）
Tokens are the new computing paradigm. Everything will be re-made on top of it. We’ve had deterministic computers for 80 years, so we confuse “how computers have worked” with “how computers must work.” We’re entering the post-binary era.Token 是新的计算范式。一切都将在此基础上重构。我们使用确定性计算机已经 80 年了，所以我们将“计算机过去的工作方式”误认为是“计算机必须的工作方式”。我们正在进入后二进制时代。
The triad of PM/Design/Eng will disappear. It does not make any bit of sense anymore. Agile, SCRUM, whatever – dead. “Engineers” who act as “meat proxies” and shove tickets into agents and report back to humans will no longer be valuable.产品经理/设计/工程的三位一体模式将消失。这已经完全没有意义了。敏捷开发、SCRUM 等等——都已过时。那些充当“肉身代理人”、将工单塞给 AI 代理并向人类汇报的“工程师”将不再具有价值。
The difference between software engineering at large corporations and small ones will increase. Start-ups adopting practices of Google will look even sillier than before, because they can now build so much faster and with so much less constraints.大型企业和小型企业在软件工程上的差异将会扩大。那些照搬谷歌实践的初创公司看起来会比以前更愚蠢，因为他们现在可以以更少的限制、更快的速度进行构建。
There’s no proof that “good code” will matter in the future. The notion of “good code” itself is mostly based on the idea that it’s easy/cheap/efficient for humans to work with. But humans won’t modify the majority of code. Think of how dumb it is to assume that “only 80 columns wide” or “but newlines here and there” matters for agents – now consider all the other properties you have in mind for “good code”. Yes.没有任何证据表明“好代码”在未来依然重要。“好代码”这一概念本身主要基于这样一个前提：即人类处理起来轻松、廉价且高效。但未来人类不会修改大部分代码。想想看，假设“每行仅限 80 个字符”或“这里或那里加个换行符”对 AI 代理很重要是多么愚蠢——现在再想想你心中关于“好代码”的所有其他标准。没错，它们也一样。
Some people will be priced out of producing software. Just like only some people could afford a personal computer in the 80s and 90s, for the next few years, if you can’t get enough tokens, you’re playing second league. You need to get to the tokens.有些人将被排除在软件生产之外。就像在 80 和 90 年代只有少数人买得起个人电脑一样，在未来几年里，如果你无法获取足够的 Token，你就是在打二级联赛。你需要获得 Token 的使用权。
It’s questionable whether cheaper models will be used. Tokens will be everywhere and we’ll swim in tokens. And what we consider a smart model today will be considered very dumb in the future. But a smarter model makes less mistakes, needs fewer turns. When do you really think “I’m okay with it being wrong a few times?”是否会使用更廉价的模型还是个问题。Token 将无处不在，我们将沉浸在 Token 的海洋中。今天我们认为聪明的模型，在未来会被视为非常愚蠢。但更聪明的模型犯错更少，所需的交互轮次也更少。你真的认为自己能接受“它偶尔犯错”吗？
Models will become so fast that UI will be generated on the fly. A lot of UI exists because software can’t understand what you want. Menus, settings screens, dashboards, filters: much of it is a human-accessible API to a dumb machine. Smart machines need much less UI.模型将变得如此之快，以至于 UI 可以实时生成。很多 UI 的存在是因为软件无法理解你的需求。菜单、设置界面、仪表盘、过滤器：其中大部分是人类访问笨拙机器的 API。智能机器需要的 UI 要少得多。
It’ll take a while for this to play out. It’ll take a generation for the “new software” to replace the “old software”. Just like there are people happily employed as ASP developers today, there will be people employed to write code in 10 years. But do you want to have that job?这一切的实现还需要一段时间。需要一代人的时间，“新软件”才会取代“旧软件”。就像今天仍有人乐于从事 ASP 开发工作一样，10 年后仍会有人受雇编写代码。但你真的想从事那份工作吗？