Ask HN: How do systems (or people) detect when a text is written by an LLM
Hello guys, just curious about how can people or systems (computers) detect when a text was written by an LLM. My question is mainly focused to if there is some API or similar to detect if a text was written by an LLM. Thanks!!!
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 accusations that will side-track whatever youre writing into a "you're a witch" argument. Ironically LLM accusations are now a sign of the high quality written word.
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.
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?
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.
> 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].
I think people will be able to detect the lowest-user-effort version of LLM text pretty reliably after a while (ie what you describe; many people have a good sense of LLM clues). But there's probably a *ton* of LLM text out there where some of the instructions given were "throw a few errors in", "don't use bullet points or em dashes", "don't do the `it's not this, it's that` thing" going undetected.
And then those changes will get built into ChatGPT's main instructions, and in a few months people will start to pick up on other indicators, and then slightly smarter/more motivated users will give new instructions to hide their LLM usage... (or everyone stops caring, which is an outcome I find hard to wrap my head around)
This is the correct answer. We’re at a point where it will soon be safer to assume a human or someone with agency and their approval wrote the text, than to completely dismiss it as “written by LLM” or a human.
So judge the content on its merit irrespective of its source.
Staccato (too may short sentences with periods) is also a telltale for me. Most humans prefer longer sentences with more varied punctuation; I, for example, am a sucker for run-on sentences.
> 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.
i think another part of the problem is that some people are using AI so much that they are starting to mimic its cadence in their own writing. they may have had a prior coincidental predisposition for writing somewhat similar to AI with worse grammar, and now are inching towards alignment as they either intentionally or accidentally use AI output as a model to improve their writing
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.
Indeed, isomorphic plagiarism by its nature forms strong vector search paths that were made from stealing both global websites, real peoples work, and LLM user-base input/markdown.
However, reasoning models adding a random typo to seem less automated, still do not hide the fairly repeatable quantized artifacts from the training process. For LLM, it is rather trivial to find where people originally scraped the data from if they still have annotated training metadata.
Finally, reading LLM output is usually clear once one abandons the trap of thinking "I think the author meant [this/that]", and recognizing a works tone reads like a fake author had a stroke [0]. =3
I don't think you can 100% detect AI content, because at some point someone will just prompt the AI to not sound like AI.
I think the better question to ask is: What are your goals? Is it to prevent AI SPAM, or to discourage people copy-pasting AI? Those are two very different problems: in the case of AI SPAM you look for patterns of usage, (IE, unusually high interaction from a single IP, timing patterns around when things are read and the response comes in,) and in the other case it all comes down to cultural norms.
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.
For HN comments, the LLMs seem to really like 2 or 3 paragraphs long responses. It's pretty obvious when you click a profile's comments and see every comment being that exact same structure.
The principled approaches are statistical. Things like DetectGPT measure per-token log probability distributions. LLM text clusters tightly around the model's typical set, human writing has more variance (burstiness). Works decently when you know the model and have enough text, breaks down fast otherwise.
Stylistic tells like 'delve' and bullet formatting are just RLHF training artifacts. Already shifting between model versions, compare GPT-4 to 4o output and the word frequency distributions changed noticeably.
Long term the only thing with real theoretical legs is watermarking at generation time, but that needs provider buy-in and it slightly hurts output quality so adoption has been basically nonexistent.
I don't look at whether the text is written by an LLM but at whether it has substance and whether the writer understands what they are doing and is respecting my time.
If the text is full of punchy three word phrases or nonsense GenAI images then that's an obvious sign. But so is if the other person has some revolutionary project with great results but they can't really explain why their solution works where presumably many failed in the past (or it's a word salad, or some lengthy writing that doesn't show any signs of getting you to an "aha, that's some great insight" moment).
A good sign is also if the author had something interesting going before 2022, and they didn't fall into the earliest low quality LLM waves. Unfortunately some genuinely talented people have started using LLMs to turbocharge their output while leaving some quality on the table nowadays, so I don't really know. I'm becoming a lot more sceptical of the Internet, to be honest.
It's a lot easier to detect when you mostly interact with non English speakers.
I asked an LLM to rewrite this to make it nicer and got the following. I'd flag the first because I don't usually hear "majority of your interactions" in conversation but I might miss it. The second will probably get by me. As for the third, I never say "considerably easier" unless I'm trying to sound artificially posh.
1. It becomes much more noticeable when the majority of your interactions are with non-native English speakers.
2.It tends to stand out more when most of the people you interact with speak English as a second language.
3. It's considerably easier to identify when most of your interactions involve people whose primary language isn't English.
I believe if you have access to the training data of the specific LLM and the generated text is long enough, using statistics you might be able to tell if its LLM generated.
Overuse of "it's not X, it's Y" kind of writing, strange shifts in writing or thinking patterns, and excessive formatting (or, when I'm on wikipedia especially, ineffective formatting (such as using MD where it isn't supported))
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.
Pangram is probably the best known example of a detector with low false positives, they have a research paper here: https://arxiv.org/pdf/2402.14873. They do have an API but not sure if you need to request access for it.
For humans I think it just comes down to interacting with LLMs enough to realize their quirks, but that's not really fool-proof.
Pangram has time after time been shown as the only detector that mostly works. And that paper is pretty old now! There are recent papers from academics independently bench-marking and studying detectors e.g. https://arxiv.org/abs/2501.15654
Humans detect them mostly through pattern matching. However, for systems, my guess is that a ML model is trained on AI genres texts to detect AI generated texts.
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
Specific language tells, such as: unusual punctuation, including em–dashes and semicolons; hedged, safe statements, but not always; and text that showcases certain words such as “delve”.
Here’s the kicker. If you happen to include any of these words or symbols in your post they’ll stop reading and simply comment “AI slop”. This adds even less to the conversation than the parent, who may well be using an LLM to correct their second or third language and have a valid point to make.
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 accusations that will side-track whatever youre writing into a "you're a witch" argument. Ironically LLM accusations are now a sign of the high quality written word.
[0] https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
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.
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.
Eg - The Strait of Hormuz: Chokepoint or Opportunity?
I suppose my high school essays were not. Apologies, but those are lost.
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...
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.
> It’s the fake drama. Punchy sentences. Contrast. And then? A banal payoff.
It's great because it's a double-decker of annoying marketing copy style and nonsensical content.
[0]: https://news.ycombinator.com/item?id=47615075
I think people will be able to detect the lowest-user-effort version of LLM text pretty reliably after a while (ie what you describe; many people have a good sense of LLM clues). But there's probably a *ton* of LLM text out there where some of the instructions given were "throw a few errors in", "don't use bullet points or em dashes", "don't do the `it's not this, it's that` thing" going undetected.
And then those changes will get built into ChatGPT's main instructions, and in a few months people will start to pick up on other indicators, and then slightly smarter/more motivated users will give new instructions to hide their LLM usage... (or everyone stops caring, which is an outcome I find hard to wrap my head around)
So judge the content on its merit irrespective of its source.
Staccato (too may short sentences with periods) is also a telltale for me. Most humans prefer longer sentences with more varied punctuation; I, for example, am a sucker for run-on sentences.
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.
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.
However, reasoning models adding a random typo to seem less automated, still do not hide the fairly repeatable quantized artifacts from the training process. For LLM, it is rather trivial to find where people originally scraped the data from if they still have annotated training metadata.
Finally, reading LLM output is usually clear once one abandons the trap of thinking "I think the author meant [this/that]", and recognizing a works tone reads like a fake author had a stroke [0]. =3
[0] https://en.wikipedia.org/wiki/Stroke
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 certainly AI-generated: https://news.ycombinator.com/item?id=47658796
And I'm suspicious of this one too - https://news.ycombinator.com/item?id=47660070 - reads just a bit too glazebot-9000 to believe it's written by a person.
I think the better question to ask is: What are your goals? Is it to prevent AI SPAM, or to discourage people copy-pasting AI? Those are two very different problems: in the case of AI SPAM you look for patterns of usage, (IE, unusually high interaction from a single IP, timing patterns around when things are read and the response comes in,) and in the other case it all comes down to cultural norms.
Stylistic tells like 'delve' and bullet formatting are just RLHF training artifacts. Already shifting between model versions, compare GPT-4 to 4o output and the word frequency distributions changed noticeably.
Long term the only thing with real theoretical legs is watermarking at generation time, but that needs provider buy-in and it slightly hurts output quality so adoption has been basically nonexistent.
If the text is full of punchy three word phrases or nonsense GenAI images then that's an obvious sign. But so is if the other person has some revolutionary project with great results but they can't really explain why their solution works where presumably many failed in the past (or it's a word salad, or some lengthy writing that doesn't show any signs of getting you to an "aha, that's some great insight" moment).
A good sign is also if the author had something interesting going before 2022, and they didn't fall into the earliest low quality LLM waves. Unfortunately some genuinely talented people have started using LLMs to turbocharge their output while leaving some quality on the table nowadays, so I don't really know. I'm becoming a lot more sceptical of the Internet, to be honest.
I asked an LLM to rewrite this to make it nicer and got the following. I'd flag the first because I don't usually hear "majority of your interactions" in conversation but I might miss it. The second will probably get by me. As for the third, I never say "considerably easier" unless I'm trying to sound artificially posh.
1. It becomes much more noticeable when the majority of your interactions are with non-native English speakers.
2.It tends to stand out more when most of the people you interact with speak English as a second language.
3. It's considerably easier to identify when most of your interactions involve people whose primary language isn't English.
This is an artifact of the default LLM writing style, cross-poisoned through training on outputs -- not an "universal" property.
I am writting an LLM captcha system, here is the proof of concept: https://gitlab.com/kaindume/llminate
To me, it often feels like the text version of the uncanny valley.
But again, that's just "feels", I don't have proof or anything.
For humans I think it just comes down to interacting with LLMs enough to realize their quirks, but that's not really fool-proof.
There are a couple of tells like em dashes and similar patterns but you should be able to suppress that with even a simple prompt.
Specific language tells, such as: unusual punctuation, including em–dashes and semicolons; hedged, safe statements, but not always; and text that showcases certain words such as “delve”.
Here’s the kicker. If you happen to include any of these words or symbols in your post they’ll stop reading and simply comment “AI slop”. This adds even less to the conversation than the parent, who may well be using an LLM to correct their second or third language and have a valid point to make.