this post was submitted on 02 Nov 2025

20 points (91.7% liked)

Typography & fonts

641 readers

9 users here now

A community to discuss and share information about typography and fonts

Sibling community:

!typography@lemmy.world

Rules of conduct:

The usual ones on Lemmy and Mastodon. In short: be kind or at least respectful, no offensive language, no harassment, no spam.

(Icon: detail from the title of Bringhurst's Elements of Typographic Style. Banner: details from pages 6 and 12, ibid.)

founded 2 years ago

MODERATORS

pglpm@mander.xyz

pglpm@lemmy.sdf.org

20

Why do AI models use so many em-dashes? (www.seangoedecke.com)

submitted 4 weeks ago by cm0002@infosec.pub to c/typography@lemmy.ca

4 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] Dave@lemmy.nz 5 points 4 weeks ago* (last edited 7 hours ago) (2 children)

This is a cool article.

But if they want LLMs to use fewer em dashes, why not find and replace with a comma or semicolon using a regex that matches known patterns so as to reduce it's frequency in the training data?

[–] nik282000@lemmy.ca 2 points 7 hours ago

If they could use use regex they wouldn't be using an LLM.

[–] lurch@sh.itjust.works 2 points 4 weeks ago (1 children)

they could just put it in the system prompt or so.

[–] Dave@lemmy.nz 5 points 4 weeks ago

It apparently doesn't work, from the article:

It’s also surprisingly hard to prompt models to avoid em-dashes: take this thread from the OpenAI forums where users share their unsuccessful attempts.