Comment by akersten
4 hours ago
Text is simply not information dense enough to be able to decode some arbitrary signal of provenance from it. Sure you might be able to detect today's tells (particular sentence structures preferred by Claude, phrases, etc) to get you some arbitrary chance percentage it was machine generated, but it's a bad fiction to perpetuate that any of this is anything more than tarot card reading.
Images, absolutely, there are tell-tale artifacts from today's generators that simply aren't emitted by "natural" paths to create them, and you can "detect AI" with high confidence (for now). Words, no, the signal is far too sparse and we are well into undetectable sophistication with today's models, let alone tomorrow's.
Whether a text was written by a human or not is just a single bit of information. So you can't rule out its detectability a priori, since even the shortest text contains more information than that.
As long as LLMs are used to write texts humans wouldn't want to write if they could help it (that's why they're getting an LLM to do it, after all), they'll remain detectable. Even if the reasoning might end up equivalent to "This looks like spam; no human in their right mind would write this spam by hand if they could get an LLM to write it, therefore it's most likely written by an LLM."
Not all humans are in their right minds, unfortunately.
There are two problems, false positives and changing the LLM's pattern.
It's really easy to have a false positive and false positives can be very harmful if the person using the detector isn't aware of that risk.
It's also very easy to change the pattern of LLM output. You can provide basic prompting that will significantly change the structure of the output. For example, having it utilize the Wikipedia article on signs of AI writing and avoid everything it describes. https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
"It's really easy to have a false positive"
Not really. The false positives for the SOTA detector are very very low.
"It's also very easy to change the pattern of LLM output."
Not in a way that can reliably avoid detection. The problem is the patterns are baked into the distribution itself. It's smoothed over, so it becomes difficult to prompt your way out of that.
Signal is easier to detect with more data to work with.
Largely AI generated books are a vastly different situation than a one paragraph homework assignment. But multiple rounds of homework assignments would change the accuracy.
"Text is simply not information dense enough to be able to decode some arbitrary signal of provenance from it...it's a bad fiction to perpetuate that any of this is anything more than tarot card reading."
Not true at all. Pangram is highly effective and has a very low false positive rate.
The post here is impressive for a small project, it looks like they independently thought of one of the core ideas Pangram uses of creating twins to compare.
You can see how it works here: https://arxiv.org/pdf/2402.14873
So, if the decision from Pangram determined, on every assignment, if you would be expelled from university for plagiarism, would that be acceptable to you regardless of how you actually did the work?
If you would not be okay with that, what level of consequence would be acceptable for the output from this tool?
> but it's a bad fiction to perpetuate that any of this is anything more than tarot card reading.
Hard disagree. LLMs (especially base ones, that only received pre-training) can produce output that is undistinguishable from human writing (because that's what they were trained to do).
But commercial chat models are specifically tuned in a way that maximizes user engagement. It's that specific tuning that is very easy to spot when reading AI slop, and that's not surprising that it's easy to spot automatically either. And I don't think that's going to change anytime soon, unless their incentives change.
(We can say exactly the same thing about man-made stuff optimized for a specific purpose, like stock photography, clickbait titles or industrial food: they aren't stereotypical because their creator lacks the skill to make them otherwise, they are like that because that's what works best).
> especially base ones
Did you actually try them? I did.They generated even more "slopey" text than instruction-tuned ones.
They're also designed to not offend anybody, so their output tends to be very bland even compared to the most milquetoast of human beings. I was only surprised once when ChatGPT responded with an enthusiastic "hell yes" seemingly organically, but 99.9% of the time these AI services clearly are instructed and trained to provide flavorless word vomit. I don't think there's a technical reason why an LLM couldn't produce totally convincing output, but internet grifters don't need to go through that trouble. It's like how most phone, email, and social media scams come off as completely transparent to most of us, but that's the whole point; we're not the target audience of the scams. Readers looking for substance, nuance, and real opinions aren't going to notice if something with written by an LLM – unless there are some cliche punctuation tells.
When DANmode bypasses were a common thing the LLMs would drift significantly far from corporate speak.
But that's the point of corporate speak, you tend not to say thing that may offend your clients and deprive the company of future revenue. Of course there are some companies that make their living being 'counter-culture' and saying what they want, but they are a small percentage of all revenue.
> But commercial chat models are specifically tuned in a way that maximizes user engagement. It's that specific tuning that is very easy to spot when reading AI slop, and that's not surprising that it's easy to spot automatically either.
There are two problems with this.
The first is that it would still misclassify human-authored text written under the same incentive, and most people have various incentives to "maximize engagement".
And the second is that then people would just make other models that are tuned for defeating that sort of classifier, which would be used whenever the classifier is being used.
All of that may be true, but pangram currently has a false positive rate of about 1 in 10000, and this has been tested by feeding in thousands of texts written before 2020.
That may not last if AI companies start trying to build models that fool it, but for the time being at least, modern models do have strong tells.
6 replies →
> The first is that it would still misclassify human-authored text written under the same incentive, and most people have various incentives to "maximize engagement".
The thing is, humans are significantly worse at maximizing numerical goals than computers.
> And the second is that then people would just make other models that are tuned for defeating that sort of classifier, which would be used whenever the classifier is being used.
Anyone can already do that right now, just grab unsloth studio and fine-tune your local Gemma, but nobody cares. People posting slop content don't care if pangram or I flag their slop with certainty, they are using the easiest option, which is commercial chat models. And given this segment of user doesn't care, the provider have zero incentive to provide a dedicated stealth model for that purpose.
6 replies →
It does mean that this will have a drift problem if it's just trained on the idiosyncrasies of model fine tuning. That's fine! But it is something to be aware of.
I don't know, the thing about most text slop is how little effort goes into disguising it (for now, anyway). I'm sure anyone dedicated can go undetected, but it's the really low-effort stuff that's generally the problem. If you can catch some of it, that's something at least.
i think one thing overlooked by this perspective is that many of a detectors adversaries are not that sophisticated. so despite this i think it is a useful thing to try to do. particularly when people are trying to do fraud which will often having to use abliterated models and generally trying to be as economical in their efforts
This sounds like it was edited by an llm.
Sure it is; we do it all the time, and then we modify each other's etc, etc; english we speak today was spoke yesterday waspake the same in yesteryears; we have no trouble dating english or other languages to a time.
A better argument is people themselves are just too influenced by reading that they'll sound like LLMs in a couple of years.
It depends on how much text. For example, chardet often falls down on short strings, but 1K characters it nails it.
[dead]