Grok：即使“程序员”使用 LLM，一天写出数千行 C 语言代码也很了不起，对吧？
3 分•作者: adinhitlore•9 个月前
自从我沉迷于“氛围编码”（对不明就里的人来说，“氛围编码”=使用大型语言模型生成代码）以来，几天前我问了Grok一个问题，如果用C语言这种复杂的语言一天生成数千甚至更多的代码行（LOC）算不算多，特别是考虑到这个项目涉及人工智能（所以对于一个复杂的任务，每天的代码行数是四位数，我们不是在讨论一个记事本克隆、POS系统、牙科预约、加密货币钱包，或者任何初级开发人员应该做的事情）。
但问题是这样的：即使一个人是个彻头彻尾的新手，除了下载Python 3.9之外几乎不会写代码，但如果必须处理大量的代码，你就需要编译，解决潜在的错误（在编译期间），如果大型语言模型给你的代码与你的目标背道而驰（例如：它自动在我的项目上设置了一个安全“对齐”，基本上禁止在我的电脑上运行“rm -rf”……但我使用的是Windows，所以我看到了这个“安全”功能，只是手动从代码中删除了它）。
问题是：初级开发人员或者刚开始编程的人和已经编程多年甚至几十年的人之间有什么区别吗？在某种程度上，这有点像问“数学家使用计算器的方式和非数学家使用计算器的方式一样吗？” 我猜区别很小？
查看原文
Since I got addicted to vibe-coding (to the unilluminated "vibecoding = using LLM to generate code), I asked grok couple of days ago if getting thousands or more LOC/day in complex language like say C is a lot or not, especially since the project involves AI (so it's 4-digit loc number/day for a complex task, we're not talking a Notepad clone, PoS, dental appointment, crypto wallet or anything that junior dev should do).<p>Here is the thing though: while one may be a total newbie and can barely type code apart from say downloading Python 3.9 if you have to deal with tremendous amount of code you'd have to compile, address potential errors (during compilation), if the LLM gives you code that erronously works against your goal (example: it automatically put a safety 'alignment' on my project basically forbidding 'rm -rf' to be run on my computer...but i'm on windows so i saw this "safety" feature and just manually deleted it from the code).<p>The question is: Is there any difference between a junior dev or rather someone just starting and someone who's been coding for years or even decades? In a way it's kind of like asking "do mathematicians use calculators the same way non-mathematicians use them?" I guess the difference is minimal?