Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I miss using em dashes

bassi.li

Post reply on HN
Print view View original

161–167 of 167 posts

Re: I miss using em dashes

#161

Post by SAI_Peregrinus »

the_af wrote: post #159
SAI_Peregrinus wrote: post #157

Earlier quoted context omitted.

Then it's stupid and you're going to have an inevitable failure. Hopefully without any expensive sounds, so don't put LLMs in charge of heavy machinery or medical devices.

I think you misunderstood. What we're discussing is whether a set of heuristics to determine whether something is the output of a human or an LLM are "stupid", not whether we should put LLMs in charge of critical work. It's not the LLMs we're talking about, but the heuristics to detect them. The person you initially replied to claimed the heuristics (to detect LLMs) are not stupid if they are shown to work (by detect…

I think the heuristics are stupid, but happen to work with the current round of LLMs. The next round of training will work to stop the heuristics working, since if they work it means the LLM isn't correctly guessing the next token a human would produce. I don't think LLMs will become indistinguishable from humans any time soon, but I think it'll be a very long back & forth of training & finding new heuristics.

Re: I miss using em dashes

#162

Post by the_af »

SAI_Peregrinus wrote: post #161
the_af wrote: post #159

Earlier quoted context omitted.

I think you misunderstood. What we're discussing is whether a set of heuristics to determine whether something is the output of a human or an LLM are "stupid", not whether we should put LLMs in charge of critical work. It's not the LLMs we're talking about, but the heuristics to detect them. The person you initially replied to claimed the heuristics (to detect LLMs) are not stupid if they are shown to work (by detect…

I think the heuristics are stupid, but happen to work with the current round of LLMs. The next round of training will work to stop the heuristics working, since if they work it means the LLM isn't correctly guessing the next token a human would produce. I don't think LLMs will become indistinguishable from humans any time soon, but I think it'll be a very long back & forth of training & finding new heuristics.

> I think the heuristics are stupid, but happen to work with the current round of LLMs.

This goes back to the initial comment you objected to: "if it works, it's not stupid".

I don't think anybody here is arguing they will work forever, or that they won't influence the next generation of LLMs.

Re: I miss using em dashes

#163

Post by lmm »

buu700 wrote: post #124
lmm wrote: post #120

Earlier quoted context omitted.

> the false positive rate is unacceptably high — we're talking about a standard, widely used character Citation needed. > Who is it helping if we collectively bully ourselves into excising a perfectly good punctuation mark from human language? Humans can adapt faster than LLM companies, at least for the moment. We need to be willing to play to our strengths. Who is it helping if we bully ourselves into ignoring a sim…

Citation needed. https://en.wikipedia.org/wiki/Dash Humans can adapt faster than LLM companies No one said anything about LLM companies. If I were a spammer today, I'd just have my code replace dashes in LLM output with hyphens before posting it. As a human, I'm not going to suddenly stop using dashes because a handful of people are treating a silly meme as if it were a genuinely useful heuristic.

> https://en.wikipedia.org/wiki/Dash

That maybe backs up the claim that it's standard, but not that it's widely used or the false positive rate would be unacceptably high.

> If I were a spammer today, I'd just have my code replace dashes in LLM output with hyphens before posting it.

No you wouldn't, for the same reason spammers don't put more plausible stories in their emails: they want to filter for the most gullible segment before investing any human effort.

Re: I miss using em dashes

#164

Post by buu700 »

lmm wrote: post #163
buu700 wrote: post #124

Earlier quoted context omitted.

Citation needed. https://en.wikipedia.org/wiki/Dash Humans can adapt faster than LLM companies No one said anything about LLM companies. If I were a spammer today, I'd just have my code replace dashes in LLM output with hyphens before posting it. As a human, I'm not going to suddenly stop using dashes because a handful of people are treating a silly meme as if it were a genuinely useful heuristic.

> https://en.wikipedia.org/wiki/Dash That maybe backs up the claim that it's standard, but not that it's widely used or the false positive rate would be unacceptably high. > If I were a spammer today, I'd just have my code replace dashes in LLM output with hyphens before posting it. No you wouldn't, for the same reason spammers don't put more plausible stories in their emails: they want to filter for the most gullibl…

It's a standard punctuation mark available on Android/iOS/macOS keyboards, and automatically inserted into text by widely used software such as Microsoft Word. You guys are acting like it's an obscure Unicode character that GPT just spontaneously started using out of the blue, and ignoring the obvious answer that it's common in LLM output because it's common in training data. The burden of proof is on anyone claiming that it isn't common.

I was referring to social media spam. It would be a simple way to defuse people citing the use of dashes as "proof" that your spam was spam and having the hivemind bury it. You can't ensnare gullible readers if they never see your comment to begin with — not that following an absurd blanket rule of categorizing em dash usage as AI output has anything to do with whether or not the reader is gullible.

Re: I miss using em dashes

#165

Post by dgfitz »

buu700 wrote: post #158
dgfitz wrote: post #156

Earlier quoted context omitted.

Prompt engineering isn’t hard to master, weeks to months tops. That is the point. LLMs are at the top of the s-curve. Assuming prompt engineering is hard, assuming that LLMs are going to continue to make any kind of substantial leap without _any_ evidence other than blind faith, is as close to believing in a religion as it gets. Having blind “faith” in this house or cards, saying things like “when things continue to…

Define "hard to master". I use LLMs all the time, sometimes as a writing assistant, and have never had the problem of trying to pass off a GPT response to a single one-line prompt as my own words. I haven't found LLMs hard to master. An 80-year-old who barely uses computers and still types full sentences into Google (or who struggled for years to unlearn that habit) might find LLMs hard to master. Someone with poor w…

I’m tired of things like this:

> Eventually, as models and their users improve

You’re pushing opinion and assumption as fact. Stop doing that.

Re: I miss using em dashes

#166

Post by buu700 »

dgfitz wrote: post #165
buu700 wrote: post #158

Earlier quoted context omitted.

Define "hard to master". I use LLMs all the time, sometimes as a writing assistant, and have never had the problem of trying to pass off a GPT response to a single one-line prompt as my own words. I haven't found LLMs hard to master. An 80-year-old who barely uses computers and still types full sentences into Google (or who struggled for years to unlearn that habit) might find LLMs hard to master. Someone with poor w…

I’m tired of things like this: > Eventually, as models and their users improve You’re pushing opinion and assumption as fact. Stop doing that.

It's a pretty safe assumption. Models and tooling are still improving on a regular basis, and most people haven't even used LLM chatbots, much less mastered them. Don't forget that we're talking about an extremely novel technology, which for all intents and purposes has existed for less than three years.

Do you honestly believe that the LLM tech landscape and end user competency with them will both look exactly the same in 2050 as they do in September 2025? You don't think the codebases of social media spambots will at least have become sophisticated enough to avoid copying the default writing style of a basic ChatGPT response? This is a very conservative prediction. Based on the vitriol you've been responding with, one would think I'd written that AGI was around the corner and anyone who disagreed with me was an idiot.

Re: I miss using em dashes

#167

Post by gxonatano »

JKCalhoun wrote: post #11

I'm not sure why people let others change them. I keep punctuating like it's the 20th Century.

> I keep punctuating like it's the 20th Century.

I keep punctuating like it's the 18th Century, myself;—compound points are my favorites:—like the colon-dash compound, AKA the "dog's bollocks."

Post reply on HN