LLM Voice

本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。

Sometimes when I read a post, I get the growing feeling that I’m reading the output of an LLM. I can’t necessarily define why, although there are the common tells (it’s not the em-dashes, it’s the load-bearing tapestries). As I do this my desire to read on atrophies, sometimes to the point of revulsion.

有时当我阅读文章时，我越来越强烈地感觉到我正在阅读大语言模型（LLM）生成的文本。我未必能说出原因，尽管有一些常见的迹象（不是破折号的问题，而是那些承重墙般的辞藻）。随着这种感觉的出现，我继续阅读的欲望便会萎缩，有时甚至达到反感的程度。

There are tools out there that claim to be able to tell the difference between LLM-written prose and the old-fashioned biological product. I’m wary of them, partly due skeptism about their accuracy, but also because it rather misses the point. The reaction to LLM-Voice is a human one, that sense that we are in an uncanny valley of prose. By the time I’d reach for a tool to tell me what I’m reading, it’s already too late, even if it confidently tells me there’s no LLM present.

市面上有一些工具声称能够区分 LLM 撰写的文章和传统的“生物制品”。我对它们持怀疑态度，部分是因为对其准确性存疑，但也因为这其实偏离了重点。对“LLM 腔调”的反应是一种人类本能，即我们正处于一种文字的“恐怖谷”之中。当我需要借助工具来判断我正在阅读的内容时，一切都已经太晚了，即便工具自信地告诉我其中没有 LLM 的痕迹。

I’m also suspicious of my own ability to accurately recognize LLM voice. Language changes over time, so a common sign of age is complaining about the language of the youngs. I’m inclined to bristle at prose that talks about “adopting a new sales motion,” or “a sharp round-up of news”. But I’ve heard these constructs coming out of human mouths, so that’s more a generational difference rather than between carbon and silicon. (And as a transplanted Brit, don’t get me started on Americanisms, I’m sure I’ll get used to them momentarily.)

我也怀疑自己准确识别 LLM 腔调的能力。语言随时间而变，因此变老的一个常见标志就是抱怨年轻人的语言。我倾向于对那些谈论“采用新的销售动作”或“新闻的精辟综述”的文字感到反感。但我确实听过人类口中说出这些结构，所以这更多是代际差异，而非碳基与硅基的区别。（作为一个移居美国的英国人，别让我开始谈论美式英语，我相信我很快就会习惯它们的。）

Right now I urge authors to be extra-wary of LLM-Voice. In particular I strongly recommend that authors should not fall into the trap of getting the LLM to write a draft. Even if it’s edited by a human, it’s very hard to expel the LLM-Voice - thus causing the uncanny valley reaction. Even accepting suggestions of rephrasing is dangerous. I have heard of people using LLMs to develop outline and structure, that may be ok, but only as far as an outline. Authors should fill the prose themselves.

目前，我敦促作者对“LLM 腔调”保持高度警惕。我特别建议作者不要陷入让 LLM 撰写草稿的陷阱。即使经过人工编辑，也很难彻底消除 LLM 的腔调，从而导致“恐怖谷”效应。即使接受改写建议也是危险的。我听说有人使用 LLM 来构思大纲和结构，这或许还可以，但也仅限于大纲。作者应该亲自填充正文。

Say Your Writing is even more important in the age of LLMs. I habitually speak the words in my head and then write them down (and then edit what I’ve just written). This advice is particularly important to anyone who has any desire to communicate regularly with writing. Like many things, learning to be a good writer relies on lots of practice. It’s a skill worth the time to acquire, but surrendering to an LLM will undermine any progress.

在 LLM 时代，“说出你的文字”变得更加重要。我习惯在脑海中先说出这些话，然后再写下来（接着编辑我刚写的内容）。对于任何渴望通过写作进行定期交流的人来说，这条建议尤为重要。像许多事情一样，学习成为一名优秀的作家依赖于大量的练习。这是一项值得投入时间去掌握的技能，但屈服于 LLM 将会破坏任何进步。

In time it may be that LLMs will be so good that we can’t tell the difference. In many ways, that’s more worrying. Like most writers, I find writing an almost-essential tool for thinking. Often it’s only by writing something down, that I can really get my thoughts on a topic into coherence. I’ve often started an essay knowing I don’t really understand something, but the act of wrestling with the words forces me to overcome my confusions. As more people delegate writing to LLMs they will also delegate thinking and comprehension to LLMs. I don’t want to do that, where’s the fun of writing then?

随着时间的推移，LLM 可能会变得如此出色，以至于我们无法分辨。在许多方面，这更令人担忧。像大多数作家一样，我发现写作是思考中几乎不可或缺的工具。通常只有通过写下来，我才能真正理清对某个主题的思路。我经常在开始写一篇文章时并不真正理解某件事，但与文字搏斗的过程迫使我克服了困惑。随着越来越多的人将写作委托给 LLM，他们也将思考和理解委托给了 LLM。我不想那样做，那写作的乐趣何在呢？

Although avoiding LLM-Voice is a general rule, it isn’t an absolute one. An important example is that of Jim Highsmith (who contributes to this site). He finds working with an LLM is essential to his writing to overcome the bane of Parkinson’s disease. I’ll gladly deal with LLM-Voice in order to continue imbibing my old friend’s wisdom.

虽然避免“LLM 腔调”是一条通用规则，但它并非绝对。一个重要的例子是 Jim Highsmith（他为本网站供稿）。他发现与 LLM 合作对于克服帕金森病的困扰至关重要。为了继续汲取这位老友的智慧，我很乐意忍受 LLM 的腔调。

A more awkward case is that of translation. Many of my colleagues aren’t comfortable in English, it is their second or fourth language. Some have found LLM translation an important part to their communication with those of us who know rather less Marathi. But I also would prefer rather a genuine human’s clunky prose to the smooth but soulless LLM.

一个更尴尬的情况是翻译。我的许多同事并不擅长英语，这是他们的第二或第四语言。有些人发现 LLM 翻译是他们与我们这些不太懂马拉地语的人交流的重要部分。但我个人还是更喜欢人类笨拙的真实文字，而不是 LLM 那种流畅但毫无灵魂的产物。

There are situations where it would be reasonable for even a native Englishman to let LLMs write the prose. Such as if I’m writing a form letter to an official, or preparing a report I suspect no-one will ever read. Maybe most documentation in the future will only be read by LLMs, and they won’t have my uncanny valley worries. But if I want to communicate with humans, my humanity has to shine (or at least ooze) out of my prose.

在某些情况下，即使是母语为英语的人让 LLM 撰写文章也是合理的。例如，如果我正在写一封给官员的格式信，或者准备一份我怀疑永远不会有人阅读的报告。也许未来的大多数文档都只会由 LLM 阅读，它们不会有我这种“恐怖谷”的担忧。但如果我想与人类交流，我的人性必须在我的文字中闪耀（或者至少渗透出来）。