问 HN:可能是一个很基础的问题,但我该如何有效地使用 AI 呢?
2 分•作者: jdw64•大约 2 小时前
我是一名程序员,大约有七年经验,但我觉得我比这里很多程序员都差,而且我做的大部分工作都相当简单。我主要负责开发 WPF 和 WinForms 应用程序,这些应用程序充当工业现场基于梯形图系统的用户界面层。<p>由于这项工作的性质,它非常耗时。需要频繁出差去工厂,体力消耗很大,而且相对于投入的精力,薪水也不高。这就是我想成为一名更注重产品导向的程序员的原因。为了朝着这个方向发展,我一直在尝试尽可能积极地使用人工智能。但在我目前的工作中,这很困难,因为工厂的安保通常是封闭的,而且人工智能工具实际上无法在那里连接。<p>我一直在阅读关于提示工程、Harness 风格的文档以及类似的话题。我也使用 OpenClaw,老实说,我觉得我几乎尝试了所有能接触到的东西。我把它与 Obsidian 连接起来,并在工作时记下我认为我的代理需要的知识。<p>尽管如此,十倍生产力的说法对我来说还是有些夸张。我想知道人们实际上是如何提高人工智能的使用水平的,以及他们如何学习底层方法。人工智能周围有太多炒作,很难分辨什么是真的,而且学习这些东西比我预期的要困难。<p>我应该如何正确地学习这个?<p>现在我特别想学习如何管理多代理系统。到目前为止,我构建或尝试过的每一个人工智能多代理框架都失败了。起初,我试图以类似 TDD 的方式控制它,但认真使用过 TDD 的人可能知道我说测试可能变得过于局部化是什么意思。有时架构开始崩溃,然后代理不断地反复修复那些小区域,而 token 成本却不断上升。<p>与此同时,在韩国,有大量关于如果你不使用人工智能,你就会落后的说法。因此,我一直在努力学习它,以免被落下。老实说,自从我开始使用人工智能以来,编程对我来说变得更有趣了。<p>一个原因是编程感觉与英语思维方式紧密相连,这在韩国一直让我感到不自在。即使是编写代码的行为,过去对我来说也感觉很费脑力。但有了人工智能,我可以用韩语思考,仍然可以有效地编写代码。<p>你是否知道当你从头开始编写代码时,最初会感到巨大的疲惫?<p>当我编写一个接口时,我立刻开始看到实现的数量。
当我看到实现时,我开始看到生命周期的冲突。
当我看到生命周期问题时,我开始考虑所有权和处置。
当我考虑所有权时,我开始考虑池化的可能性和重置契约。
当我考虑 DI 时,我开始看到组合根和测试接缝。
当我考虑契约本身时,我开始担心未来的扩展成本。<p>所有这些曾经让编码对我来说感觉非常沉重。<p>但人工智能只是写了一个草稿,而不会陷入所有这些问题,我真的很喜欢拿着那个草稿,并根据我自己的想法来重塑它。<p>我想在这方面更好地使用人工智能。<p>提高这方面的最佳方法是什么,以及如何在不被炒作淹没的情况下跟上有效的趋势?
查看原文
I am a programmer with about seven years of experience, but I would say I am below many of the programmers here, and most of the work I do is fairly simple. I mainly work on WPF and WinForms applications that act as UI layers for ladder diagram based systems in industrial sites.<p>Because of the nature of this work, it is very labor intensive. There are too many factory trips, it is physically exhausting, and the pay is not great relative to the amount of effort involved. That is why I want to become more of a product oriented programmer. To move in that direction, I have been trying to use AI as actively as possible. In my current job, though, that is difficult because factory security is usually closed off and AI tools cannot really be connected there.<p>I have been reading about prompt engineering, harness style documentation, and similar topics. I also use OpenClaw, and honestly I feel like I am already trying almost everything I can get my hands on. I connect it with Obsidian and write down the knowledge I think my agents need while I work.<p>Still, the idea of ten times productivity feels somewhat exaggerated to me. I want to know how people actually get better at using AI, and how they learn the underlying methods. There is so much hype around AI that it is hard to tell what is real, and learning this stuff has been more difficult than I expected.<p>How should I study this properly?<p>Right now I especially want to learn how to manage multi agent systems. Every AI only multi agent framework I have built or tried so far has failed. At first I tried to control it in a TDD like way, but people who have used TDD seriously probably know what I mean when I say that tests can become too locally focused. Sometimes the architecture starts to fall apart, and then the agents keep fixing only those small areas over and over while the token cost keeps rising.<p>At the same time, in Korea there is a huge amount of talk that if you are not using AI, you will fall behind. Because of that, I have been trying hard to learn it so I do not get left behind. And to be honest, programming has become much more enjoyable for me since I started using AI.<p>One reason is that programming feels deeply tied to English ways of thinking, and that has always felt awkward with Korean. Even the act of writing code used to feel mentally heavy for me. But with AI, I can think through things in Korean and still code effectively.<p>You know that huge fatigue you feel when you first start writing code from scratch?<p>When I write a single interface, I immediately start seeing the number of implementations.
When I see the implementations, I start seeing lifecycle conflicts.
When I see lifecycle issues, I start thinking about ownership and disposal.
When I think about ownership, I start thinking about pooling possibilities and reset contracts.
When I think about DI, I start seeing the composition root and the test seams.
When I think about the contract itself, I start worrying about future extension costs.<p>All of that used to make coding feel painfully heavy for me.<p>But AI just writes a draft without getting stuck in all of that, and I genuinely enjoy taking that draft and reshaping it around my own thinking.<p>I want to get much better at using AI this way.<p>What are the best ways to improve at it, and how do you keep up with useful trends without getting buried in the hype?