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

Ask HN: How do systems (or people) detect when a text is written by an LLM

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 72 posts

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#41

Post by EagnaIonat »

alex43578 wrote: post #11
Someone1234 wrote: post #4

They cannot. Unfortunately many believe they can, and it is impossible to disprove. So now real people need to write avoiding certain styles, because a lot of other people have decided those are "LLM clues." Bullets, EM Dash, certain common English phases or words (e.g. Delve, Vibrant, Additionally, etc)[0]. Basicaly you need to sprinkle subtle mistakes, or lower the quality of your written communications to avoid ac…

Someone with native fluency in American English can (should) be able to tell the difference between human writing and unpolished AI copy-paste. Essentially 0 people use emoji to create a bulleted list. Nobody unintentionally cites fake legal precedents or non-existent events, articles, or papers. Even the “it’s not X, it’s Y” structure, in the presence of other suspicious style/tone cues signals LLM text.

> 0 people use emoji to create a bulleted list.

I haven't seen this yet, but I guess the only reason I haven't done it is because it never crossed my mind.

What I have found an easy detection is non-breaking spaces. They tend to get littered through the passages of text without reason.

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#45

Post by mghackerlady »

block_dagger wrote: post #36

Em dashes, “it’s x, not y”, excessive emojis and arrows.

Especially where the emoji serves practically no purpose other than to get your attention. If it is especially abstract what the emoji is there to represent, I start looking for other signs

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#46

Post by Filligree »

alex43578 wrote: post #40
prmph wrote: post #19

Earlier quoted context omitted.

Also one big tell that is hard to hide is making verbose lists with fluff but little actual informative content. Ask an LLM to read your project specs and add a section headed: Performance Optimizations, to see an example of this Another is a certain punchy and sensationalist style that does not change throughout a longer piece of writing.

One of my subtle favorites is the “H2 Heading with: Colorful Description” Eg - The Strait of Hormuz: Chokepoint or Opportunity?

I’ve used titles like that for thirty years.

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#47

Post by leumon »

You can try to use an ai detector, here is a leaderboard of the best ones according to this benchmark: https://raid-bench.xyz/leaderboard Results should of course always be taken with a grain of salt, but in most cases detectors are quite good in my opinion.

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#48

Post by lelanthran »

Someone1234 wrote: post #4

They cannot. Unfortunately many believe they can, and it is impossible to disprove. So now real people need to write avoiding certain styles, because a lot of other people have decided those are "LLM clues." Bullets, EM Dash, certain common English phases or words (e.g. Delve, Vibrant, Additionally, etc)[0]. Basicaly you need to sprinkle subtle mistakes, or lower the quality of your written communications to avoid ac…

> Ironically LLM accusations are now a sign of the high quality written word.

Citation needed. The LLM accusations come from the specific cadence they use. You can remove all em-dashes from a piece of text and it still becomes clear when something is LLM written.

Can they be prompted to be less obvious? Sure, but hardly anyone does that.

It's more "The Core Insight", "The Key Takeaway", etc. than it is about emdashes.

Incidentally, the only people annoyed about "witch-hunts" tend to be those who are unable to recognise cadence in the written word.

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#49

Post by jcims »

alex43578 wrote: post #11
Someone1234 wrote: post #4

They cannot. Unfortunately many believe they can, and it is impossible to disprove. So now real people need to write avoiding certain styles, because a lot of other people have decided those are "LLM clues." Bullets, EM Dash, certain common English phases or words (e.g. Delve, Vibrant, Additionally, etc)[0]. Basicaly you need to sprinkle subtle mistakes, or lower the quality of your written communications to avoid ac…

Someone with native fluency in American English can (should) be able to tell the difference between human writing and unpolished AI copy-paste. Essentially 0 people use emoji to create a bulleted list. Nobody unintentionally cites fake legal precedents or non-existent events, articles, or papers. Even the “it’s not X, it’s Y” structure, in the presence of other suspicious style/tone cues signals LLM text.

>Even the “it’s not X, it’s Y” structure

I wonder where some of this comes from. Another one is 'real unlock', it's not a common phrasing that I really recall.

https://trends.google.com/explore?q=real%2520unlock&date=all...

Re: Ask HN: How do systems (or people) detect when a text is written by an LLM

#50

Post by lelanthran »

Filligree wrote: post #46
alex43578 wrote: post #40

Earlier quoted context omitted.

One of my subtle favorites is the “H2 Heading with: Colorful Description” Eg - The Strait of Hormuz: Chokepoint or Opportunity?

I’ve used titles like that for thirty years.

I'm going to ask the qustion I ask everyone who makes the claim that they wrote like that for years: Can you show us a link from prior 2022 that you wrote like that?
Post reply on HN