问 HN：AI 改变了你作为软件工程师的产出多少百分比？
2 分•作者: nomilk•6 个月前
与 AI 编码工具出现之前（比如大约两年前）相比，如果让你给出一个数字，作为一名软件工程师，你的生产力提升了多少？
我经常思考这个问题，也很想听听其他人的看法。对我来说，简短的回答是：大约提升了 2 倍（也就是说，比 LLM 出现之前快 100%）。长一点的回答是：
当我彻底理解了领域知识（也就是我正在解决的业务逻辑和实际问题），并且熟悉技术栈时，我的速度大约能提升 10 倍，而且代码质量也更好。
当我不理解领域知识时，提示会变得模糊或不充分，LLM 会进行猜测。它可能一天就能完成一个月的任务量，但我会花接下来的 3 周时间进行重构，并意识到代码有多么糟糕，这都是因为提示太糟糕了。总的来说，这可能仍然比 AI 出现之前快，但会带来一种令人沮丧的心理现象，让你觉得某件事快要完成了，结果却要花几周时间调试、重构，而且经常要推倒重来。
在不熟悉的技术栈中，我无法总是发现明显的错误（由 AI 或提示引起的错误），所以效率更低，风险也更高。
生产力提升的 10-15% 是由于开发环境的改进。我用 Cursor 打开了 ~/.dotfiles，告诉它我遇到的问题或请求具体的改进。它通常会修改 .zshrc、.vimrc 或类似的文件（如果第一次尝试没有成功，则会进行迭代）。由于这非常快（例如 5 分钟），我做了大约 20 个小调整，而这些调整以前是不值得花时间的。它们确实让我更开心，也提高了一点生产力。
但总的来说，考虑到所有因素，我认为我的生产力大约是 LLM 出现之前的 2 倍。
查看原文
Compared to the era before AI coding tools (say, ~2 years ago), if you had to put a number on it, how much has your productivity as a SWE changed?<p>I think about this a lot; am keen to hear what others perceptions are. For me; the short answer: about 2x (i.e. 100% faster than pre LLMs). Long answer:<p>When I thoroughly understand the domain (i.e. business logic and real world problem I'm solving), and am familiar with the tech stack, I'm about ~10x faster for the same or better code quality.<p>When I don't understand the domain, prompts will be ambiguous or inadequate, the LLM will guess, it will do a month's work in a day, but I'll spend the next 3 weeks refactoring and realising how trash the code was, due to how trash the prompt was. All in all, it's probably still faster than pre AI, but can give a demoralising psychological phenomena where you <i>think</i> something's nearly completed only to spend weeks debugging it, refactoring, and often tossing it away and starting over.<p>In an unfamiliar tech stack, I can't always spot obvious mistakes (mistakes caused by the AI or the prompt), so it's less productive and more risky.<p>10-15% of the productivity improvement is due to improvements in the dev environment. I open ~/dotfiles with cursor and tell it a problem I have or ask for a specific improvement. It usually modifies .zshrc, .vimrc or similar (and iterates as necessary if the first attempt didn't work). Due to how fast this is (e.g. 5 minutes), I've made about 20 little tweaks that previously didn't justify the time. They definitely make me happier as well as a bit more productive.<p>But overall, taking everything into account, I'd say I'm about 2x as productive as before LLMs.