bliki: LLM Voice

📝 摘要 #

Martin Fowler 提出 "LLM Voice" 概念：读一段文字时逐渐升起的"这是 LLM 写的"直觉，一种散文层面的恐怖谷效应（uncanny valley of prose）——不是 em-dash，而是那些"承重的挂毯"式修辞。他指出检测工具本身错失了重点：这种反感是人类的即时反应，等到需要借助工具判断时已经太晚。他也警惕自己对"年轻人语言"的代际偏见，认为应区分世代差异与碳基/硅基差异。

核心概念： LLM 腔无法通过事后编辑轻易洗掉，因此作者不应让 LLM 写初稿，甚至接受 LLM 的改写建议也很危险；提纲/结构辅助"或许可以"，但散文必须自己写。

关键技术栈 / 关键要点：

1. LLM Voice 与恐怖谷 — 读者对 LLM 文风的排斥是即时的人类反应，事后检测工具价值有限。
2. 初稿陷阱 — 即使经人类编辑，LLM 初稿的腔调仍极难清除（极少数例外需专业编辑大改）。
3. 写作即思考 — 写下来才能让想法连贯；把写作外包给 LLM 等于把思考与理解一并外包。
4. 使用披露政策 — 本站要求任何用 AI 辅助写作的人在致谢中声明用法，兼顾透明与教学。
5. 合理的例外 — 帕金森病患者借 LLM 继续写作、非英语母语者的翻译、无人阅读的公文/报告等场景可以接受 LLM 代笔。

关键结论 / 实践建议： 若要与人沟通，人性必须从文字中透出来。坚持"先在脑中说出、再写下来、然后编辑"（Say Your Writing）的练习，不要把写作与随之而来的思考能力一起交出去。

LLM Voice #

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

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.

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.)

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. 1 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. 2 Authors should fill the prose themselves.

1: Very hard, but not impossible. I've come across one case where I do know the first draft was entirely done by LLM, but I detected no LLM Voice when I read the final piece. It did, however, need a professional editor at a major periodical publication to clean it up.

2: My policy on this site, is that anyone who uses AI to help them write should declare how they used it, usually in the acknowledgments. This is partly for transparency, and partly so that readers can learn useful ways to use AI. In my own case, I don't use AI for generating prose, nor for help in structure. The only way I use it for writing is as a search tool (but I verify any information by going to the source).

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.

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?

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.

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.

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 3. 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.

3: Michael Nygard commented: “There you really aren't trying to communicate thoughts from one person to other people. You're communicating with a process rather than a human. A human may open the envelope but that person is acting as a component in a cybernetic organism.”

Notes #

1: Very hard, but not impossible. I've come across one case where I do know the first draft was entirely done by LLM, but I detected no LLM Voice when I read the final piece. It did, however, need a professional editor at a major periodical publication to clean it up.

2: My policy on this site, is that anyone who uses AI to help them write should declare how they used it, usually in the acknowledgments. This is partly for transparency, and partly so that readers can learn useful ways to use AI. In my own case, I don't use AI for generating prose, nor for help in structure. The only way I use it for writing is as a search tool (but I verify any information by going to the source).

3: Michael Nygard commented: “There you really aren't trying to communicate thoughts from one person to other people. You're communicating with a process rather than a human. A human may open the envelope but that person is acting as a component in a cybernetic organism.”

Acknowledgements #

Alessio Ferri, Caer Sanders, Ian Cartwright, Jie Jessie Xia, Joshua Kerievsky, Michael Feathers, Michael Nygard, Scott Davies, and Wei Zhang commented on drafts of this post.

I did not use AI or LLMs in any way while writing this post.