Hacker News new | ask | show | jobs
by napsterbr 23 days ago
One of the recent AI tells other than em dash is the excessive usage of hyphenated words:

> multi-tenant-safe cache keys

> on a server-rendered app

> byte-for-byte identical (classic)

> gets a cache-speed response

> cached-file-extensions list

Honestly, this is terrible. I had to add a "use simple words only, don't hyphenate unnecessarily" warning to my Claude config. After a full day of work, having to read these Claudisms all the time make a noticeable difference on how tired you get. It gets even worse when Claude starts to make up its own vocabulary.

4 comments

Fuck, I spent all these years developing a thoughtful writing style that leaned toward clarity for the reader, even if it meant extra work to achieve precision, or adding affordances like “excessive” hyphenation, and now I guess have to learn to write worse.
There is a world of difference between well-written human text and sloppy walls of AI-generated text. There's nothing wrong in using hyphenations or emdashes -- I use them myself! That's not the point of my comment.
Whether we like it or not, em dashes are effectively verboten in online discussions and blog posts if you want people to take you seriously. If the idea that excessive hyphenation is an AI tell gains traction, it too will become impossible to use without ruining your credibility.
This is not true. I regularly get HN front page hits, and still use em dashes. Nobody accuses me of AI writing. Writing with em dashes is not a problem if you have something to say.
What does it mean when prompting SoTA LLMs prone to slop to be concise and precise, with respect to context at hand, not work at all? Anyone benchmarking that?
I think it’s exceedingly unlikely for a good-faith reader to mistake good-faith human writing for AI writing.

Even if you use em dashes and a few phrases that have become associated with AI writing, there’s still an unmistakeable sense of how much effort was put into the writing.

But I suppose there might be naive readers who don’t know how to spot this effort and would false positive on em dashes or supposed AI phrases.

Oh no, how will you write clearly without hyphens?
Don't change. The homogenous way LLMs write is just tiresome and boring, like if every movie stared Ryan Reynolds - an actor famous for having no range. Ryan Reynolds is enjoyable to watch on occasion, but I don't want everything I watch to be Ryan Reynolds.
It does feel a bit like the LLMs have commoditised correct writing form, and all the plebs are all up in arms about it...
I read the slop and each has a smell. Each model and company does because the humans behind it have their own taste, smell, and perspective.

The human element cannot be recreated because the human element that created the beast becomes further removed and only the beast remains.

I say beast to provide a tell that what I write is 'human'.

Yeah, I mean, slop is easily recognisable by structure and content. But the obvious "markers" everyone claims (emdashes, hyphenation, etc), are just the writing style taught in the predominantly ex-British-colonial schools where the labellers were educated
I have an over-hyphenated writing-style as well. Probably my Germanness.
There is not reason whatsoever to hyphenate "writing style".
In this example I used the hyphen for comedic effect. But this is a actual sentence I wrote in an older post:

> What's the competition in the gaming-capable pre-built mini-PC category

I think that's probably-satire.
I opine that over-hyphenation adds clarity.
I have used em dashes extensively — for at least a decade — and I also generously apply hyphens when it makes sense to do so as well. You people are about as annoying as the grammar nazis on IRC in the '90s, except you're saying that prose is less readable because a large language model has been trained on nearly the sum total of human knowledge and found that em dashes are used extensively in the highest rated prose and therefore must be the correct choice to make.

Also, most engineers will likely just be skimming this article before feeding it into their harness to implement the changes anyway, so it makes sense for it to be more heavy on context than it would be if meant for only humans to consume.

One of the earliest tells was the use of emdashes.