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

31–40 of 72 posts

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

#31

Post by spindump8930 »

fortran77 wrote: post #16
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…

And I'm sure we've all seen what happens if you run the Declaration of Independence or the Gettysburg Address or the book of Genesis through an AI "detector". They usually come back as AI.

Only for poor quality systems. Unfortunately there are many systems that tried to make easy hype, but are the equivalent of an ML 101 classifier class project.

If one measures for perplexity (how likely text is under a certain language model), common text in a training set will be very likely. But you can easily create better models.

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

#32

Post by rcxdude »

There are some systems which can use the LLMs themselves to detect writing (basically, if the text matches what the LLM would predict too well, it's probably LLM generated), but they are far from infallible (with both false positives and false negatives). There's also certain tropes and quirks which LLMs tend to over-use which can be fairly obvious tells but they can be suppressed and they do represent how some people actually write.

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

#33

Post by elC0mpa »

m_w_ wrote: post #14

I don’t think there’s a reliable system or API for doing so, unclear that arms race will ever favor the side of the detectors. As far as how I / other people do it, there are some obvious styles that reek of LLMs, I think it’s chatgpt. There’s a very common structure of “nice post, the X to Y is real. miscellaneous praise — blah blah blah. Also curious about how you asjkldfljaksd?" From today: This comment is almost…

Thanks a lot for the detailed answer, will take a look at the examples

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

#34

Post by sumeno »

LoganDark wrote: post #9
loloquwowndueo wrote: post #8

Earlier quoted context omitted.

The key insight is to avoid – em dashes. You’re absolutely right. It’s not the content, it’s the style.

That's an en-dash.

You're absolutely right! I unintentionally used an en-dash instead of an em-dash. Here is the em-dash you requested: –

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

#35

Post by alex43578 »

derwiki wrote: post #21
alex43578 wrote: post #11

Earlier quoted context omitted.

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.

Emojis for lists: completely agree with you, but presumably this was learned in training?

I think that’s a RLHF issue - if you ask people “which looks better”, they too-frequently picked the emoji list. Same with the overuse of bolding. I think it’s also why the more consumer-facing models are so fawning: people like to be praised.

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

#40

Post by alex43578 »

prmph wrote: post #19
alex43578 wrote: post #11

Earlier quoted context omitted.

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.

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?

Post reply on HN