HN 提问：你如何应对 AI 编程带来的“失控感”？
1 分•作者: xiaoyu2006•6 天前
我不得不承认，最新的模型和辅助工具已经做得非常出色，即使是普通的提示也能很快生成可用的代码，这就像“许愿式编程”。
问题更多出在我这边，而不是 LLM 方面。我感觉我 1) 对我的项目失去了控制，甚至是我的业余项目，因为 LLM 生成代码的速度太快了，而且 2) 我懒得手动审查所有代码，即使我确实掌握了整体架构设计和有时直接用自然语言写的伪代码。但自然语言，顾名思义，不是形式化的，而编程是将非正式需求转化为正式语言的过程。这与软件工程中通过导入库等方式来降低复杂性的抽象化是根本不同的。其结果是，不深入细节的实现会加剧失控感和不自信感。
这可能读起来不像一篇连贯的投稿，因为它只是我一些随机的、令人不安的想法，但我相信至少有一些像我一样的 HN 用户有（过）同样的感受。你们对此有什么看法？
查看原文
I have to admit that newest models and harness tools have gotten really good and produce working code really fast with even mediocre prompts "wish programming".<p>The problem is more on my side than the LLM side. I feel I am 1) losing control of my project, even my hobby ones, because LLM outputs code so fast that I am 2) too lazy to manually review all of them, even if, indeed, I had the overall architecture design choices and sometimes straight up pseudo-code in natural language. But NL is, by definition, not formal, and programming is the process of expanding informal demands into formal languages. It is still fundamentally different from abstraction (like importing a lib) as in software engineering as a means to reduce complexity. The result is that not-going-into-nitty-gritty-impl-details builds the feeling of loss-of-control and -confidence.<p>This may not read as a coherent submission since it's just my random unsettling thoughts, but I am sure at least some of you fellow HNers feel (felt?) the same. What is your take on this?