The LLM Critics Are Right. I Use LLMs Anyway
The LLM Critics Are Right. I Use LLMs Anyway
大模型批评者是对的，但我依然在使用大模型
2026-07-15
I almost agree with all of the LLM critics, yet I still use LLMs a lot. I know this sounds like I am delusional, and I also feel like that sometimes because of this dissonance, but I don’t think I am alone with it. 我几乎同意所有关于大模型（LLM）的批评意见，但我仍然频繁地使用它们。我知道这听起来像是我在自欺欺人，由于这种认知失调，我有时也会有这种感觉，但我认为我并不孤单。
This week I was at Local-First Conf in Berlin, and the dissonance was everywhere. Armin Ronacher had just given a talk about building machine entities. He created Flask and was one of the early team members of Sentry, so he is clearly a good software engineer. Just recently he founded his company Earendil, which builds Pi.dev, an “open-source coding agent harness”. After the talk you could ask questions via Discord, which would be read out loud on stage, and I asked: are you accepting PRs for Pi, or how do you handle the flood of PRs from LLMs? 本周我在柏林参加了 Local-First Conf 大会，这种认知失调随处可见。Armin Ronacher 刚刚做了一场关于构建机器实体的演讲。他创建了 Flask，也是 Sentry 的早期团队成员之一，显然是一位优秀的软件工程师。最近他创立了公司 Earendil，开发了 Pi.dev，这是一个“开源编码代理工具”。演讲结束后，可以通过 Discord 提问并由现场朗读，我问他：“你们接受 Pi 的 PR（拉取请求）吗？或者你们如何处理来自大模型的 PR 洪流？”
He replied, live on stage, in front of the entire audience, that they auto-close almost all PRs and issues. But that one shouldn’t be discouraged from opening PRs, because the human will always shine through. 他在舞台上当着所有观众的面回答说，他们会自动关闭几乎所有的 PR 和 Issue。但他补充道，人们不应该因此气馁而不去提交 PR，因为人类的智慧总会闪光。
So it is not only me, but apparently some pretty clever engineers too. The people building a tool for working with LLMs are themselves flooded by their own creation, and in order to protect themselves they are auto-closing it all. On their purpose page it says: In a world hurtling towards AI, we believe humans are the best agents. Again, dissonance. 所以不仅是我，显然一些非常聪明的工程师也面临同样的情况。那些构建大模型工具的人，自己也被他们创造的产物所淹没，为了保护自己，他们不得不自动关闭一切。在他们的宗旨页面上写着：“在一个向人工智能狂奔的世界里，我们相信人类才是最好的代理。” 再次强调，这就是认知失调。
When I was sitting in the audience, I could see a lot of people having Claude Code open. And then the speakers would say these critical things about LLMs, and they would get this big round of applause. Even from the people with their Claude Code open. And again, this dissonance. 当我坐在观众席时，我看到很多人都打开着 Claude Code。而当演讲者发表对大模型的批评言论时，他们会获得热烈的掌声。即使是那些打开着 Claude Code 的人也在鼓掌。再次，这种认知失调。
I spoke at that conference myself, and when I later talked to some of the people, they described the feeling as pretty similar to mine, which is a relief, because I know I am not alone with this. 我自己也在那次会议上做了演讲，后来与一些人交谈时，他们描述的感觉与我非常相似，这让我感到宽慰，因为我知道我并不孤单。
So this article is me trying to describe it. I’ll start by going through all of the fair and valid concerns about using LLMs, the things that would get the big round of applause. Then I will explain what makes me still use LLMs. And I’ll finish up with some of the patterns I found, in the hope that by giving concrete examples, others can step in as well and describe their experiences, so we can all come together and get a better understanding of this dissonance. 所以这篇文章是我试图描述这种感受的尝试。我将首先梳理所有关于使用大模型的合理且有效的担忧——即那些能赢得热烈掌声的观点。然后，我将解释是什么让我依然坚持使用大模型。最后，我将总结我发现的一些模式，希望通过提供具体的例子，其他人也能参与进来分享他们的经历，这样我们就能共同对这种认知失调有更深入的理解。
LLMs are bad
大模型很糟糕
Just by listening to people or the talks or reading HN, I think I got a pretty good sense of why certain people refuse to use LLMs. And what makes it extremely weird is that I agree with almost all of their points! 仅仅通过倾听人们的交谈、参加讲座或阅读 Hacker News，我想我已经很清楚为什么有些人拒绝使用大模型了。最奇怪的是，我几乎同意他们所有的观点！
It is full of copyrighted materials, yes. It is bad for the environment, yes. All the ethical problems, yes. And this whole NVIDIA, OpenAI, money-moving circle-jerk is not going to end well. It is a bubble, and it is definitely going to burst. 它充满了受版权保护的材料，是的。它对环境有害，是的。所有的伦理问题，是的。而整个英伟达、OpenAI 这种金钱流转的“圈内自嗨”也不会有好结果。这是一个泡沫，而且注定会破裂。
Let me go through the biggest ones one by one. Let’s start with the most common critique “LLMs produce a lot of slop”. Yes, they do. Definitely. 让我逐一列举其中最大的几个问题。先从最常见的批评开始：“大模型产生了大量的垃圾内容”。是的，确实如此。毫无疑问。
If you look at open source software, you will see more and more repos and projects either straight up refusing all types of contributions or trying to put some kind of filters in front of it. Similar to what Armin and Earendil are doing with their auto-closing. 如果你观察开源软件，你会发现越来越多的仓库和项目要么直接拒绝所有类型的贡献，要么试图在提交前设置某种过滤器。这与 Armin 和 Earendil 正在做的自动关闭机制类似。
I think the core issue here is trust. You should never trust random people on the internet anyway. But before LLMs, there was this base thing: creating a proper PR with proper descriptions would require at least some human time, so it would keep trolls and low quality submissions out. Or at least you could easily filter them out within a couple of seconds. So even if a new person came in, you could trust that this person would have at least spent a couple of hours on that. And then it was probably worth taking a closer look at it. 我认为核心问题在于信任。无论如何，你都不应该信任互联网上的陌生人。但在大模型出现之前，有一个基本前提：创建一个带有适当描述的规范 PR 至少需要人类投入时间，因此这能将喷子和低质量提交拒之门外。或者至少，你可以很容易地在几秒钟内过滤掉它们。所以即使是一个新人加入，你也可以相信这个人至少在上面花了几小时。那么，这通常值得你仔细看一看。
That base thing is not true anymore. Everyone can simply create a new GitHub account and let their LLM loose, and as a maintainer you cannot easily tell whether someone put a lot of time into the PR (and maybe used Claude for just the PR description), or whether it is just an OpenClaw machine acting on its own. Projects like Zig or Gentoo are already refusing to accept LLM generated PRs (which I don’t think is the solution, because how would you even tell?) 这个基本前提不再成立了。任何人都可以简单地创建一个新的 GitHub 账号并让大模型自动运行，作为维护者，你无法轻易分辨某人是否在 PR 上投入了大量时间（可能只是用 Claude 写了 PR 描述），还是这仅仅是一个自主运行的“OpenClaw”机器。像 Zig 或 Gentoo 这样的项目已经拒绝接受大模型生成的 PR（我不认为这是解决办法，因为你根本无法分辨）。
I think LLMs might have serious potential to kill OSS, if we don’t find ways to restore that trust. One idea could be to only allow a small set of verified people to contribute to a project, and in order to get verified you would need to go to a real-life meetup or something. 我认为如果我们找不到恢复信任的方法，大模型可能会严重威胁到开源软件（OSS）。一个想法是只允许一小部分经过验证的人为项目做出贡献，而要获得验证，你可能需要参加线下的聚会之类的活动。
And then there is the situation about junior engineers. There are actually two different points in there: a) you cannot trust the effort behind your junior’s code anymore, and b) seniors have no incentive left to teach juniors. 接下来是关于初级工程师的情况。这里实际上有两个不同的点：a) 你再也无法信任初级工程师代码背后的努力程度；b) 高级工程师失去了教导初级工程师的动力。
Let’s start with a): Senior people have always corrected and fixed the code of junior people. And juniors have always written some pretty bad code (my worst code was written in the before-LLM times). It is just now that as a senior while reviewing you don’t know if that junior just vibecoded it in 10 minutes, or if he sat there for a couple of hours but is genuinely lacking some good insights. 先从 a) 说起：高级工程师一直都在纠正和修复初级工程师的代码。初级工程师也一直会写出一些很烂的代码（我写过最烂的代码是在大模型出现之前）。只是现在，作为高级工程师在审查时，你不知道那个初级工程师是花了 10 分钟“凭感觉”写出来的，还是他确实坐那儿研究了几个小时，但真的缺乏一些好的见解。
And b), the teaching, aka “How do we teach new people?”: previously, there was this balance aka “the junior does some pretty mundane tasks, but for this the senior reviews it together with him and helps him to grow”. Now as a senior, you don’t need juniors anymore. The mundane tasks, at least I find that a lot of people agree with that one, can be fully outsourced to an LLM. So why hire juniors at all? 关于 b)，即教学，也就是“我们如何教新人？”：以前有一种平衡，即“初级工程师做一些相当琐碎的任务，作为交换，高级工程师会和他一起审查代码并帮助他成长”。现在作为高级工程师，你不再需要初级工程师了。琐碎的任务——至少我发现很多人都同意这一点——可以完全外包给大模型。那么为什么还要雇佣初级工程师呢？
And then there are the geopolitical tensions. What happens if China or the US cut us off overnight from these technologies? Just a couple of weeks ago the US government showed it was able and willing to cut off non-US citizens from Anthropic’s latest frontier model. 此外还有地缘政治紧张局势。如果中国或美国一夜之间切断我们对这些技术的访问权限会怎样？就在几周前，美国政府表明它有能力也有意愿切断非美国公民对 Anthropic 最新前沿模型的访问。