Topic: AI-generated post discussion thread: how to identify & report (Read 2498 times)

This is an interesting twist in terms of crypto related content that ChatGPT Plus can now generate. ChatGPT Plus, the version that works on a dataset that surpasses September 2021, and that has apparently moved on to include web browsing capabilities, can now connect to a plugin created by CoinMarketCap to interact with all their crypto related datasets.

The above, theoretically, gives ChatGPT better capacity to reference near real-time data, which can be used by some to further trick their way around here, citing real and recent data whilst not really having a clue themselves.

These are some of the examples that CoinMarketCap claims the combination can now respond to (although these examples do not strictly relate to close to or real time data):

See:
https://cointelegraph.com/news/coinmarketcap-launches-chatgpt-plugin
https://chainwire.org/2023/10/11/coinmarketcap-provides-a-personal-crypto-analyst-for-all-with-new-chatgpt-plugin/

Phrases not used by people? Who would they be used by then, martians? They are words and many words are used by a large percentage of the population.

The difference is ChatGPT's use of these phrases is exceedingly common. And like I said the presence of these phrases is just one part of the puzzle. Them on their own isn't enough to determine if a post is AI-generated or not, and nobody ever claimed that it was.

Let's take one at random and look at the 10 most recent forum posts to use it: "It is important to emphasize"

#1-2: in reference to AI discussion
#3-4: non-AI
#5: 71.8% probability for AI
#6: 84.9% probability for AI (post deleted as spam)
#7-8: non-AI
#9: in reference to AI discussion
#10: 99.5% probability for AI

So in the latest 10 instances of someone writing "It is important to emphasize" 3 of the posts are found to have a strong likelihood of being AI generated by a detector.

That makes the phrase exceedingly common in AI posts as compared to "Howdy", "What's up", "The trend is your friend", "Holy cow", etc., or anything not in the list of commonly used AI phrases.

I did not mention artificial intelligence detectors in my message, I had a specific question about the list of phrases used by ChatGPT, which was published by you. As I reported earlier, your list of phrases prepared by ChatGPT is identical to the one that people use. That is, ChatGPT uses the same phrases that are used by people and for this reason you cannot use it for identification. Only if ChatGPT used phrases that are not used by people, it would be possible to consider such messages as created by artificial intelligence.

They are just one piece of the puzzle. They are an indicator, that combined with other such indicators, serves to reveal when a post has a strong likelihood of being written by AI.

Every criticism of attempting to identify AI posts that I've seen in this thread stems from honing in on one indicator and proclaiming it to be unreliable by itself. Which is true. Its the sum of all indicators that establishes a basis for assuming a post is AI-generated.

The strongest indicator thus far are the results of the detectors, and some seem to be better than others. If 2 detectors indicate a strong likelihood of a post containing AI-generated text, its safe to say that it does.

Also as has also been mentioned here previously, what matters more is if the post is considered spam or not. If the post contributes nothing original to the forum, which is the case for most AI-generated posts, then it should be deleted as spam, and 90% of the time it is.

This list interested me and I walked down it with searching. What can I say, the majority of those who use these phrases on the forum use them in natural posting, but there were several AI posters who were caught by this search. This experiment was not of big enough selection, so it could be just eventual. But right you are, we can't make any conclusions just basing on if someone uses these phrases or not. I use some of these phrases from time to time, many people with whom I speak offline in English use them. So it is not a proof for blaming.

You could continue your experiment and ask a similar question to ChatGPT:


I will not publish the answer from ChatGPT here for the reason that in his answer you will find all the phrases that you published earlier.

And it is not surprising that ChatGPT uses the same expressions that are often used by people. In the end, it is thanks to such expressions that the answers in ChatGPT become more similar to people's messages and, accordingly, you cannot use such a list of phrases to identify a message as created by AI.

Hardly, many people use it and there's no problem. What looks here like AI is that text is impersonal, written in general words, such texts can look like borrowed from somewhere else or written by AI. AI detectors also catch for combinations of words which are characteral for AI. I went through other your recent posts and I see no reason for searching for some other posts which can look like AI written.

If you want to improve your posting (because it probably has something what can be improved, if some reputable users have questions if you are using AI), then you probably should avoid impersonal trivial texts written in general words. Share what you think, what you feel, how you see. Grammar helpers won't make problems.

No need to worry about that, if you're using Grammarly to make sure your post are coherent or are in the correct manner, I don't see anything wrong with it. And iirc Grammarly only corrects your grammar so if your post is organic and you really did typed it up yourself then using a grammar correcting tool to make it more clean is acceptable in my opinion. If you're that worried then just don't use it, idk if AI detecting tools consider posts that have been polished by Grammarly to be a writing of an AI. Try the to write a paragraph or something then pass it under Grammarly's grammar checker then see if it's considered an AI writing, if it does then probably stop using it so you can avoid the hassle of having to explain that you don't use AI to write your post.

Is that possible that the use of Grammarly makes this post sounds AI-generated? If this is the case then I will stop using grammarly from now on.

Doing it myself is some how with the way offenders take things  (like they take it personal and also bear grudges against you after smoking them out) is like they're doing the right thing especially those ones with higher ranks like hero and legendary, I'll prefer it should be done by those guys who have the power to banned lock post or delete post, to be clear higher authorities, they should be the ones to do that.
And those ones that get to have a rethink by apologizing after being caught are those who knows they have being messing up and coming back to reality means they still have the forum at heart, is good to give them a second chance but also keep an eye on them.

It looks like what can be AI written, but too short texts are not so easy to work with. What do we have? AI detecting: copyleaks 71.7% for Human, hivemoderation 76.4% for AI, sapling 0% for AI. Text.ru says this text has borrowings.



So you can be right, there is a chance that this user uses AI. But these proofs are not enough for me for leaving a tag. Too short text, too few overlaps. If there are no multiple texts in a row from him with the same results, I'd prefer to wait for more data.

This can be partially incorrect but i haven't use any kind of tools to wrote it nor i copy it from somewhere. I only use Grammarly to fix some minor grammar mistake. I am not sure why you think this is a chat AI spam or plagiarism!! You can check my old post too i have never been accused of using AI tools.

What's the verdict on this one?
It's partially incorrect and sounds very much like chat AI spam/plagiarism.

You can do it by yourself if you have enough free time. Some forum users do warn others when they see AI usage. I don't remember when some AI user stopped just because of warning from another regular user. They sometimes start to worry when they see how their posts are starting being deleted or when they see tags in their profile. But majority of AI users have many accounts and they usually have more offenses, so they start doing the same from other accounts. I remember two cases when someone was caught, said that he is sorry, that he understood his mistake and stopped using AI, while staying on the forum with not so bad posts. Well, I think they'll restore their reputation with time. But majority will just use other accs from their mults.

Ok let's say he knows that there have been some trace of him using AI and with time he'll be caught without him defending himself. With him deleting or editing his post knowing when he wants to be caught, can't you guys drop a warning sign for him because without that he'll keep doing his thing, can't it be done that way?
He thinks he's smart but he's not, using AI is a sign of laziness I'll keep saying it.

Well, Adams0001 decided to write me a PM saying that it was an occasional case, that he is good and never uses AI. He occasionally used the same words as in some other text in Internet. Main mistake is not to delete all AI written posts. If I said that I'm too lazy to catch all his AI written posts and prove it, it doesn't mean it is so hard that no one will see.

I just took randomly one of his recent posts more.


First let's look at the grammar. As you can see English is not my mother tongue so I can't be an expert, but it looks like Adams0001 writes in nearly perfect language. Native speakers can confirm or not, but online grammar checkers say he is great.

And unexpectedly we see that there are two incomplete sentences in this post (marked with yellow; looks like he deleted some parts not to be detected). Strange, right?

Let's ask some detectors if this is human written? Copyleaks says no, 72.3% of probability fir AI, Hivemoderation says no, 58.1% likely to contain AI Generated Text, Sapling says no, 86.3% for fake.

Okay, let's detect for plagiarism with text.ru. And what was expected, we see that this post is copied from invstr.com/risks-and-rewards-of-investing/ for 47%!!! Nearly half of this text entirely from some single other source!



And moreover each time we see that a plagiarism tool doesn't say that there are many others who read some texts in Internet and used the same words. No, it finds an exact text which was a base for AI to generate this exact post. But there are hundreds of millions users in Internet who writes in English and read some texts. How can they not say some way the same things with the same words? It doesn't happen so usually, and even if here was an outstanding case, then not two in a row.

---

And you know, I decided to go through the challenge. I decided to check all my own words from the text above with the same 4 tools I used for Adams0001's post. Copyleaks gives 79% of probability for Human, Hivemoderation gives 0% likely to contain AI Generated Text, Sapling gives 7.6% for fake, Text.ru says 100% unique. As expected, because I really wrote everything of this by myself. And reading other texts in Internet didn't make me writing like AI.

And not only that post created by A.I are plagiarized, but are also totally useless, as they add no value to forum discussion. Because though they may sound super brilliant, they lack that human-to-human feeling (expression) that a normal conversation ought to have, and as such I wish to thank our forum moderators who have always been working hard just to flush away such people off this forum who add no value here.

However, I think the job of detecting an A.I poster can best be done by human and not any online tool.

That's right. If they think that the worst thing they can face is being detected as AI writers and then getting neutral or negative tag, then no. As I showed, AI uses ready patterns for writing so there are several cases when AI writers were reported as plagiarists (who they really are, because posting what was written by AI not saying that, is plagiarism anyway) and were permanently banned. So my advice for all of them is to stop using AI for posting and delete all AI posts they left. Because otherwise sooner or later they all will be caught and get negative tags or ban.

If the post beginning sounds like the answer to a prompt, then there's a high chance of it being an AI post. I mean, come on, "It is difficult to determine if cryptocurrencies will survive indefinitely"? What kind of person on this forum would write that? (Besides Peter Schiff's known trolls) For everyone here, it is very easy to determine that at least the majority of popular coins are here to stay, so if you're writing something that sounds like what an Oxford professor in a research paper would write, then your posting days are strictly numbered.

He uses, and we know it, and he knows it (he just deleted the mentioned post when he saw that he was caught). But even if someone will wish to spend time for making more proofs (there are some options of proving even for those who make small edits of texts, but it takes time) that he uses AI all we'll get is deleting of posts with proven AI usage. Too much time to spend for not too big result.

But you talked not about how to ignore that someone uses AI if he edits his posts good enough not to be caught by automated detectors, but how to prevent spamming forum with AI texts, right? Here we have an example of why is it not so easy. Automated tools are not as good as we could wish. So some part of the ones who use AI are still here and use AI, and it takes time for catching them, and no automated tool can fully automate this process.