←back to thread

Show HN: Hacker News em dash user leaderboard pre-ChatGPT

(www.gally.net)
358 points tkgally | 2 comments | 30 Aug 25 03:40 UTC | HN request time: 0.418s | source

The use of the em dash (—) now raises suspicions that a text might have been AI-generated. Inspired by a suggestion from dang [1], I created a leaderboard of HN users according to how many of their posts before November 30, 2022—that is, before the release of ChatGPT—contained em dashes. Dang himself comes in number 2—by a very slim margin.

Credit to Claude Code for showing me how to search the HN database through Google BigQuery and for writing the HTML for the leaderboard.

[1] https://news.ycombinator.com/item?id=45053933

Show context
Gud ◴[30 Aug 25 11:53 UTC] No.45073865[source]▶
The one thing LLMs do well is manipulating text. The danger is obviously that it will reduce individual expression and make everything the same mediocre sludge.

For me writing is a way to capture a stream of consciousness so I don’t really see the advantage of using an LLM.

When I see some trivial mediocrity I simply stop reading. It’s just not interesting.

replies(1): >>45073916 #
1. A4ET8a8uTh0_v2 ◴[30 Aug 25 12:05 UTC] No.45073916[source]▶
As with most things, it can get interesting if you don't rely on defaults. My personal amusement in that area includes chatting up fictional characters with unique 'voices'. And even simple capture of consciousness can get more interesting if you apply stylometric analysis to it.
replies(1): >>45074964 #
2. Gud ◴[30 Aug 25 14:27 UTC] No.45074964[source]▶
Makes a lot of sense! Interesting choice of use, I’ll have to try it out. I write some sci fi.

Personally I use LLMs to study languages, particularly German. I find it enormously helpful.