alt Hacker NewsNew accounts on HN more likely to use em-dashes
Comments
Fwiw I did some more comparisons, looking for words disproportionately favored by noob comments:
word noob new p-value
----------------------------
ai 14.93% 7.87% p=0.00016
actually 12.53% 5.34% p=1.1e-05
code 11.47% 6.04% p=0.00081
real 10.93% 2.95% p=2.6e-08
built 10.93% 2.11% p=2.1e-10
data 8.93% 3.51% p=6.1e-05
tools 7.6% 2.67% p=5.5e-05
agent 7.47% 2.95% p=0.00024
app 7.2% 3.09% p=0.00078
tool 6.8% 1.83% p=8.5e-06
model 6.8% 2.39% p=0.00013
agents 6.67% 2.11% p=5.2e-05
api 6.53% 1.12% p=2.7e-07
building 6.13% 1.54% p=1.3e-05
full 6.0% 1.97% p=0.00017
across 5.87% 1.4% p=1.3e-05
interesting 5.33% 1.54% p=0.00014
answer 5.2% 1.4% p=9.6e-05
simple 4.93% 1.54% p=0.00043
project 4.8% 1.26% p=0.00015I'm still salty that I can't use em-dashes anymore for fear of my writing being flagged as AI generated. Been using them for years—it's just `alt+shift+-` on a Mac keyboard and I find them more legible in many fonts compared to the simple dash on the typical numpad.
It's so sad to me that good typographical conventions have been co-opted by the zeitgeist of LLMs.
The data is available in a SQLite database on GitHub: https://github.com/vlofgren/hn-green-clankers
You can explore the underlying data using SQL queries in your browser here: https://lite.datasette.io/?url=https%253A%252F%252Fraw.githu... (that's Datasette Lite, my build of the Datasette Python web app that runs in Pyodide in WebAssembly)
Here's a SQL query that shows the users in that data that posted the most comments with at least one em dash - the top ones all look like legitimate accounts to me: https://lite.datasette.io/?url=https%3A%2F%2Fraw.githubuserc...
This feels like an existential threat to HN, and to the general concept of anonymous online discourse. Trust in the platform is foundational, and without it the whole thing falls down.
Requiring proof of identity is the only solution I can think of, despite how unappealing it is. And even then, you'll still have people handing their account over to an LLM.
I really struggle to imagine a way around it. It could be that the future is just smaller, closed groups of people you know or know indirectly.
One pattern I've noticed recently is sort of formulaic comments that look okish on their own, maybe a bit abstract/vague/bland, and not taking a particular side on good/bad in the way people like to do, but really obviously AI when you look at the account history and they're all the same formula:
>this is [summary]
>not just x, it's y
>punchy ending, maybe question
Once you know it's AI it's very obvious they told it to use normal dashes instead of em dashes, type in lowercase, etc., but it's still weirdly formal and formulaic.
For example from https://news.ycombinator.com/threads?id=snowhale
"this is the underreported second-order risk. Micron, Samsung, SK Hynix all allocated HBM capacity based on hyperscaler capex projections. NAND fabs are similarly committed. a 57% reduction in projected OpenAI spend (.4T -> B) doesn't just affect NVIDIA orders -- it ripples into the memory suppliers who shifted capacity to HBM and away from commodity DRAM/NAND. if multiple hyperscalers revise down simultaneously you get a situation similar to the 2019 crypto ASIC overhang: companies tooled up for demand that evaporated. not predicting that, but the purchasing commitments question is real."
Weirdly, I learned that it was important to use proper grammar, spelling, and punctuation due to getting repeatedly dunked on in IRC long before the dawn of LLMs. I have no intent of changing, and people thought I was an "old" when I was younger because I texted with correct language, I'm sure people suspect I'm an LLM now. I don't care, and I don't try to guess for other comments either, I care if the content is relevant, accurate, and useful or interesting.
Shoutout to my English Major comrades who have been using em-dashes forever, and have had to stop so we don't sound like AI.
If AI starts use the New Yorker style diaeresis (umlaut-looking thing when there are two vowels in words like coöperate) I swear I'm gonna lose it.
Most of the bots I've caught on here don't really use em dashes at all.
For example, here's an active bot that posted 30 mins ago (as of this comment):
https://news.ycombinator.com/threads?id=aplomb1026
Examine the last two detailed comments it made and you'll see the timestamps show they were posted < 30 seconds apart:
https://news.ycombinator.com/item?id=47155655
https://news.ycombinator.com/item?id=47155648
If it wasn't for them misconfiguring their bot and having it post so quickly, these would go by undetected and most people would engage with them. The comments themselves seem "normal" at first glance.
---
Other bots:
Most people want to avoid looking like AI, ut what if you want to blend in with the robot uprising.
I present ⸻ the U+2E3B dash.
It would be trivial to make a HN comment agent that avoids all the usual hallmarks of AI writing. Mere estimations of bot activity based on character frequency would likely underestimate their presence.
Downstream of this I used to cycle my accounts pretty regularly but have stopped since generative AI. Don't want people thinking I'm an LLM spam bot. My stupid comments are entirely my own.
On reddit it's even worse, I feel like Reddit is internally having their own bots for engagement bait.
As someone who loves LaTeX, I can't imagine ever spending so much time on typography on online forums, italics, bold, emdashes, headers, sections. I quit reddit and will quit hn as well if situation worsens.
Biggest tell that a comment is AI: it's deeply uninteresting.
No one wants to read your ChatGPT outputs.
A couple thoughts:
(1) I don't recommend focusing disproportionately on one signal. They'll change, and are incredibly easy to optimize for. https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
(2) I do recommend taking one minute to dash a note off to [email protected] if you see suspicious patterns. Dang and our other intrepid mods are preturnatually responsive, and appear to appreciate the extra eyeballs on the problem.
Give me back my em dash (2025):
I noticed a similar trend a couple of weeks ago so I auto-hide green comments now. I also autohide all top 1000 user accounts but it strikes me that perhaps I should also choose a “user signed up on $date” filter that precedes OpenClaw.
If I see an em-dash in a comment I stop reading and I've seriously considered setting up a filter across multiple sites to remove any comments containing one.
I know there are legitimate usecases for the em-dash, but a few paragraphs (at most) of text in an HN/Reddit comment? Into the trash it goes.
(author) I saw a 32:1 rate of EM-dashes last night when I just eyeballed the first 3 pages of /newcomments and /noobcomments. So I'm not sure how stable this is over over time.
It's the "incredibly banal" comments that upset me. The ones that just re-state the article in one or two uncontraversial sentences.
Often lean slightly pro-AI, but otherwise avoid saying much about anything.
@dang would there be any possibility of creating a view that hides posts and comments by accounts newer than, say, Jan 1 2026? Similar to how https://news.ycombinator.com/classic works (only showing votes from the oldest accounts)?
I know this is unfair to prospective new community members, but I'm unsure of other good methods to filter out AI bots at scale. Would certainly welcome other ideas.
I’ve occasionally found myself wanting a comments filter with an account-creation date cutoff.
A -3dB cutoff might be >= 01/01/2020, to pick a round figure.
Yet I never browse https://news.ycombinator.com/classic
Perhaps a classic comment filter might work…
I read every book written by Robert Caro—now there was an author who loved em-dashes!
I enjoyed his use of them so much in his writing that I started using them in my own book that came out in 2017. I freely admit—without hesitation—that my own use of em-dashes is due to author Robert Caro's influence.
There is much amusement at the idea that tech-weenies today are freaking out that the appearance of em-dashes in text is a surefire tell that so-called "AI" generated said text.
Read some books, get away from the computer, eh?
My writing style is influenced a lot by what I read. Because I read a lot of LLM output I use more - phrasing in my writing.
I'm also influenced by the email style of my colleagues, books I'm reading, X, etc.
My literary diet really does show in my writing, so I'll keep up reading the classics to balance out all the LLM content :)
I’ve had this sense that HN has gotten absolutely innundated with bots last few months.
Is it possible to differentiate between a bot, and a human using AI to 'improve' the quality of their comment where some of the content might be AI written but not all? I don't think it is.
Honestly, comments are just half the problem. At least half the articles I read from HN are vibe written. And I only spot it after reading a few paragraphs. It's leaving a bad taste, and it's sad because HN was guaranteed to have plenty of things worth reading and it's deteriorating
Why is the em dash so popular with LLMs, given that they are likely not as popular in the writings used for training them?
I don't understand what is the purpose of these bots? Nihilism? Vandalism? At first I doubted when people were saying that such and such comments was AI generated, I didn't understand the goal, the motives so I thought it couldn't be ; but lately I understood how dead wrong I was, we are submerged, I came to realize that we are eaten by a sea of these useless comments.
I won't support this rampant emdashophobia. The internet deserves better typography.
So much so that I've started a Wikipedia project to replace the dashes and other abysmal characters with proper typography.
All of my devices replace hyphens with emdashes, ascii typography with glorious unicode, etc.
You can turn off iOS automatically converting dashes to em-dashes. It also turns off smart-quotes which when used converts any sms you send from normal GSM-7 (7-bit) encoding to utf-8 which doubles the number of sms messages you're sending in the background (even though they're stitched together to look like a single message)
To turn off Smart Punctuation: Home > Settings > General > Keyboard > Smart Punctuation > Off.
Several factors: 1. Em dashes are common use in the Queens English
2. People with dyslexia and dysgraphia can more easily interact online
3. People who speak a primary language other than English can more easily interact online
The last 2 options mean people who previously would have been more reluctant to participate now have less of a barrier.
So while there may be AI generated content, we should just assume it is all negative.
— — — — — — — — — — — — — — — — — — — — — — — — — — —
Don’t mind me, just skewing the results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — results. — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —
There is one thing I am the most scared off and that is believing a comment, video, picture is AI generated while it wasnt.
There is no real AI detection tool that works.
When we see something like emd-ashes its simply the average of the used text the models trained on. If you fall into one the averages of a model you basically part of the model ouput. Yikes.
My truth is that the LLM usage of em-dashes doesn’t seem excessive. If anything, the kind of text generated by LLMs (somewhat informal, expressive) calls for em-dashes at a higher frequency.
I had a past life of drumming up community comments for engagment: The only thing that's changed is that humans are getting lazy and using AI. Fake comments have always been a thing.
Actually I love the — ever since my first Mac, I have enjoyed the finer characters of typography. It’s much easier to access on a Mac keyboard. Not saying the proliferation of AI has that as a signature, like the weird phrasing, but at least allow for the few mammals who likes to indulge.
You'd think that by now people running bots would just set a system prompt instruction to "Never use em-dashes." That still works even with modern models.
Our life has become so dumb in certain ways. There are people who invested heavily in learning their mother or a foreign language, its spelling, grammar, syntax and idiosyncrasies, like when to use an em-dash, an Oxford comma, a semicolon, an ellipsis -- these smart educated people now seriously deliberate whether using wrong dashes and adding a spelling mistake or two would be a good way to prove you are a human (I think we never should have allowed the framing of CAPTCHA to be "prove you are not a robot", it was demeaning back then and still is now, it's just that the alternatives were not and still aren't clear-cut). The same things that would have made you fail a written essay in school are somehow becoming a requirement, but not in "haX0r" or online communities where "writing funny" has always been a differentiating factor, but for absolutely everybody who has to communicate with others in written form.
It's of course not a surprise that an LLM would be most proficient in language use and, adjacent to that, in proper formatting of said language. But it's a good thing and a good tool for writing, as anyone who has ever used a classic spell or grammar checker will attest to. But apparently we as a society have once again managed to completely overlook and demonise the good and now people who have paid attention in school have to bow to people who are somehow convinced that perfect spelling is a sign that someone cheated. This is not LLMs' fault, it's people's who think they've understood something when they really haven't, crying heresy over others doing things the correct way.
That being said: of course there are social and technological challenges with cheating, spam bots and sock puppets and what not, but the phenomenon itself is not really new, just the scale, cost and quality is way different now. We need to find a balanced way to approach it -- trying to weed out every last possible AI cheater while hurting real innocent people in the process is not worth it. Especially since we don't have a proper metric to actually prove who's a cheater and who is not, it's gotten way harder since the days of "As a large language model" being in every second sentence.
700 is actually a pretty good sample size unless you are looking at some tiny crosstab, or there’s some skew (which you won’t naively scale your way out of anyway).
It is also interesting to note that the comparison is between recent comments and recent comments by new users. So, I guess this would take care of the objection that em-dashes (a perfectly fine piece of punctuation) have just been popularized by bots, and now are used more often by humans as well.
Maybe there is a bot problem. Seems almost impossible to fix for a site like this…
Funny to see this after me being influenced to use em dashes more adequately in my blog :)
Good to know so I don't do it x10 more :D
The part that doesn't make sense to me is: Why? As in what are the incentives to use AI to write comments on HN? This is not a platform like Youtube or X where views get you money. Is this just for internet karma?
TBH, i've largely stopped correcting any spelling or grammar mistakes in my communcations as a way to assert I am a human.
If we are ok with flooding the world with AI generated software. I find it funny to reject the increase of comments or even articles written by AI. Can't have the cake and eat it too or something like that
I'm just going to continue to mis-use the en-dash like I've always done.
Related:
Show HN: Hacker News em dash user leaderboard pre-ChatGPT - https://news.ycombinator.com/item?id=45071722 - Aug 2025 (266 comments)
... which I'm proud to say originated here: https://news.ycombinator.com/item?id=45046883.
I used to love using em-dashes in my texts, especially in titles. Now I am way too afraid of appearing as using an LLM while I do my best to redact everything by myself :')
Bye bye em-dash, we had a nice run together.
I might start using that⸻one (a bit long...)
As someone who has the key combos Alt-0150 and Alt-0151 saved in muscle memory I feel offended by being compared to a machine.
I get the punchline here but is there possibly some sort of Streisand effect where real people now are more inclined to use an em dash?
Prior to the rise of LLM-written posts and the natural reaction of hair-trigger suspicion, I used to em and en dash fairly often in posts on HN. No reason really other than being a bit of a typography geek who happens to have always used dashes in casual writing instead of semicolons. So when I was setting up a modifier-key keyboard layer with AHK many years ago I put the em dash on modifier+dash just because I could - which made it easy.
Now someone may search old posts without a time cutoff and assume I'm an LLM. That combined with the fact I sometimes write longer posts and naturally default to pretty good punctuation, spelling and grammar, is basically a perfect storm of traits. I've already had posts accused twice in the past year of being an LLM.
Kind of sad some random quirk of LLM training caused a fun little typography thing I did just for myself (assuming no one else would even notice) to become something negative.