AI-generated post discussion thread: how to identify & report

[nutildah]

Seems AI-assisted posting is becoming more rampant, and we should work together to brainstorm some concrete criteria for identification of AI-written posts.

For me, the best indicator if a post is AI-generated is if it is written in flawless English. Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT. If a user's native language isn't English (as can be evidenced by their posting history), and they suddenly start posting in flawless English, it means one of two things:

1. The text is plagiarized, or
2. The text is AI-generated.

Its worth noting that not all plagiarized texts are written with the same mastery of English as ChatGPT. In fact, they seldom are.

The second best indicator is taking an average of separate AI text identification systems; the more, the better. This is the one created by the makers of ChatGPT and is thus probably the best for identifying such text:

https://platform.openai.com/ai-text-classifier

Here are 6 other ones.

https://writer.com/ai-content-detector/ (max. 1500 chars)
https://gptzero.me/ (min. 250 chars)
https://contentatscale.ai/ai-content-detector/ (min. 25 words)
https://x.writefull.com/gpt-detector (50-2000 words)
https://hivemoderation.com/ai-generated-content-detection (max. 8192 chars)
https://paraphrasingtool.ai/ai-content-detector/ (max. 4900 chars)

Seems like too much work to run a text through all 7, and some probably use extremely similar methods.

Of course, they are not always accurate, but if the majority of them say "likely" or "over 50% likely", then I'd say its compelling evidence the text is AI generated.

For example, this post - which I'm almost certain is AI-generated - comes back as "unlikely" to be AI-generated according to OpenAI's Text Classifier, yet it is "99% likely" AI generated according to the Hive Moderation checker.

Here is how you ask ChatGPT to generate such a list:

Prompt:

Can you write me a list of bullet points about Bitcoin, with each one starting with a letter of the alphabet? For example:

"A- All your crypto journey could begin here and set you on the right path if you ask questions and follow up question and threads of your interest

B- Bitcoin should be your first coin of choice when you're mentally ready to enter into the market because it's one of the best coins and generally accepted one.

C- consistency is the easiest if not the only way to achieve everything you desire in everything you do and it's very evident over here in the forum."

etc.

It generated an extremely similar list which comes back as "unclear" according to the OpenAI Text Classifier and "99% likely to contain AI generated text" according to the Hive Moderation site.


The problem is people can now be lazier than ever on the forum and get paid for it, which actually hurts them in the long run. Instead of thinking or learning anything for themselves, they just plug in a prompt, and prompt-plugging is the only actual skill they are gathering. Has nothing to do with Bitcoin, cryptocurrency, the blockchain, etc.


TL;DR - What are the rock-solid criteria for detection & definition of AI-generated text?


I suggest we put examples of what are believed to be AI-written posts in this thread to help evaluate them and come up with a refined consensus on how to detect them.

[1715131046]

1715131046

[1715131046]

1715131046

[1715131046]

1715131046

[1715131046]

1715131046

[cryptoaddictchie]

I suggest we put examples of what are believed to be AI-written posts in this thread to help evaluate them and come up with a refined consensus on how to detect them.

Thats good idea but maybe we should keep it as lenient as possible or dont put names within the suspected since w arent sure yet if the content or written post are AI generated. It could be worse if we accuse someone of doing this and later on proven his innocent. Maybe a rule to what grounds a post can be submitted here. Should the post itself must be quoted including a member's name, or his/her plain post only.

[Rikafip]

TL;DR - What are the rock-solid criteria for detection & definition of AI-generated text?

I personally avoid using those detection tools because of false positive and (at least for now) I think that the sudden increase in English level is probably the best piece of evidence that we can provide to prove someone is using chatbot.

Its probably harder to catch those brand new account that use chatbots right from the start, but so far I had some success with those as well.

For example, this post (https://bitcointalk.org/index.php?topic=5424029.msg62038551#msg62038551) - which I'm almost certain is AI-generated - comes back as "unlikely" to be AI-generated according to OpenAI's Text Classifier, yet it is "99% likely" AI generated according to the Hive Moderation checker.

AI generated text for sure. 4 days ago he managed to wrote that and then yesterday he wrote the post below. There's simply no plausible explanation for such a drastic decrease of his English.

As you are saying that increasing number winning prizes will for sure increase number for your chances to increase your winning chances but I will say that this gambling algorithm don't work that way. As when there will be more winners than there might be more traffic and it would be more difficult for us win prize and probability of winning could increase of decrease by a lot of factors.
And also I think that we should predict on each side if you know that probability of your winning I'd more than 50% and it will increase your chances of winning too. I don't like those games that offer only 50% ratio as that's not good for us.

[joker_josue]

Of course, they are not always accurate, but if the majority of them say "likely" or "over 50% likely", then I'd say its compelling evidence the text is AI generated.

Written with the help of: Google Translate
The idea itself is good in general and we have to be aware of the posts that arise that may become suspicious.

But this statement is not the best. I remember reading recently that LoyceV did a test of its own text and those detectors said it was AI text. Therefore, these systems saying that the text has a 50% or more probability of being written by an AI, could be 100% wrong.

Another point is that not everyone is fluent in English or has the ability to write in English, and can therefore use translation and writing help systems. For example, to write here in the forum in English, I use Google Translate and sometimes I use the Grammarly tool to try to improve my text. The probability of being considered a text written by AI is high.

That's why I wrote this post, using 4 methods: write only using Google Translate; write with ChatGPT doing the translation; write only using Google Translate with Grammarly help; write with ChatGPT translation and Grammarly help. Do your analysis.




Written with the help of: Google Translate & Grammarly
The idea itself is good in general and we have to be aware of the posts that arise that may become suspicious.

But this statement is not the best. I recently read that LoyceV did a test of its text and those detectors said it was AI text. Therefore, these systems saying that the text has a 50% or more probability of being written by an AI, could be 100% wrong.

Another point is that not everyone is fluent in English or can write in English, and can therefore use translation and writing help systems. For example, to write here in the forum in English, I use Google Translate and sometimes the Grammarly tool to try to improve my text. The probability of being considered a text written by AI is high.

That's why I wrote this post, using 4 methods: write only using Google Translate; write with ChatGPT doing the translation; write only using Google Translate with Grammarly help; write with ChatGPT translation and Grammarly help. Do your analysis.




Written with the help of: ChatGPT
The idea itself is generally good and we need to be attentive to posts that may become suspicious.

However, this statement is not the best. I remember reading recently that LoyceV tested their own text and those detectors said it was AI-generated. Therefore, these systems claiming that a text has a 50% or higher probability of being written by an AI may be 100% wrong.

Another point is that not everyone is fluent in English or has the ability to write in English and may therefore use translation and writing assistance systems. For example, I use Google Translate to write here on the forum in English and sometimes use the Grammarly tool to try to improve my text. The probability of being considered an AI-generated text is high.

That's why I wrote this post, using four methods: writing only using Google Translate; writing with ChatGPT doing the translation; writing only using Google Translate with Grammarly's help; and writing with ChatGPT's translation and Grammarly's help. Make your own analysis.




Written with the help of: ChatGPT & Grammarly
The idea itself is generally good and we need to be attentive to posts that may become suspicious.

However, this statement is not the best. I recently read that LoyceV tested their text and those detectors said it was AI-generated. Therefore, these systems claim that a text that has a 50% or higher probability of being written by an AI maybe 100% wrong.

Another point is that not everyone is fluent in English or can write in English and may therefore use translation and writing assistance systems. For example, I use Google Translate to write here on the forum in English and sometimes use the Grammarly tool to try to improve my text. The probability of being considered an AI-generated text is high.

That's why I wrote this post, using four methods: writing only using Google Translate; writing with ChatGPT doing the translation; writing only using Google Translate with Grammarly's help; and writing with ChatGPT's translation and Grammarly's help. Make your analysis.




In Portuguese

Code:

A ideia em si é boa de um modo geral e temos de estar atentos aos posts que vão surgindo que se podem tornar suspeitos.

Mas esta afirmação não é a melhor. Lembro-me de ter lido recentemente que o LoyceV fez um teste do seu próprio texto e esses detetores dizerem que era texto de IA. Por isso, esses sistemas dizerem que o texto tem 50% ou mais de probabilidade ter sido escrito por um IA, pode estar 100% enganado.

Outro ponto, é que nem todos são fluentes em Inglês ou tem capacidade de escrever em inglês, e podem por isso usar sistemas de tradução e de ajuda na escrita. Eu por exemplo, para escrever aqui no fórum em Inglês, uso o Google Tradutor e as vezes uso a ferramenta Grammarly para tentar melhor o meu texto. A probabilidade de ser considerado um texto escrito por IA é alta.

Por isso escrevi esse post, usando 4 métodos: escrever apenas usando o Google Tradutor; escrever com o ChatGPT a fazer a tradução; escrever apenas usando o Google Tradutor com ajuda Grammarly; escrever com a tradução do ChatGPT e ajuda do Grammarly. Façam a vossa analise.

[nutildah]

Thats good idea but maybe we should keep it as lenient as possible or dont put names within the suspected since w arent sure yet if the content or written post are AI generated. It could be worse if we accuse someone of doing this and later on proven his innocent.

That's true. From now on we'll just post links with no names. With this exception: if you report a post for being "AI spam" and the report gets marked as Good, then share the archived version of the post here so we can get an idea of what "AI spam" looks like according to the mods.

I personally avoid using those detection tools because of false positive and (at least for now) I think that the sudden increase in English level is probably the best piece of evidence that we can provide to prove someone is using chatbot.

That's also true. What I have so far is:

1) sudden shift to perfect English is the #1 indicator
2) detection tools can provide additional evidence if the majority of them indicate "probable AI," or >50% likelihood.

Of course running them through all 7 is too time consuming. Perhaps in the future we can narrow it down as we gain a better understanding of their accuracy.

However, this statement is not the best. I remember reading recently that LoyceV tested their own text and those detectors said it was AI-generated. Therefore, these systems claiming that a text has a 50% or higher probability of being written by an AI may be 100% wrong.

When I have a bit more time I will put LoyceV's text through all 7 of the detectors.

[rat03gopoh]

TL;DR - What are the rock-solid criteria for detection & definition of AI-generated text?

I suggest we put examples of what are believed to be AI-written posts in this thread to help evaluate them and come up with a refined consensus on how to detect them.

I think I know the criteria for AI generated posts. For some reason I suspect posts that contains this sentence: "it's important to note/remember that..."
That's like saying in my mind, it's a part of the disclaimer that must always be included in every fenerated answers.

Look https://ninjastic.space/search?content=it%27s%20important%20to%20note%20that
Lately, this sentence has been used a lot by newbie accounts.

[NeuroticFish]

I do like the idea, but think that in most cases it will not good enough for using beyond doubt.
Of course, there are exceptions:
* sudden change in the quality (and fluence) of the user's posts
* sudden change in how knowledgeable somebody is in various fields

And here there can be a doubt too between use of AI or account changing hands, for example, however both should come at least with red tag.


... Maybe this new development would also trigger equivalating the gravity of plagiarism, use of AI and buying accounts, to make everybody's life easier.

----
I like rat03gopoh logic, but that will probably not work on long term (AI will start writing even more human, the users will learn to edit such keywords, ...) and I'm not sure it could be proven (although I totally agree it's unnatural to talk here like that).

[lovesmayfamilis]

I would add a moment to how quickly posts written by AI are published. Sometimes you can see quite long posts being posted in a short amount of time when the average person would not be able to write as fast.

From now on we'll just post links with no names. With this exception: if you report a post for being "AI spam" and the report gets marked as Good, then share the archived version of the post here so we can get an idea of what "AI spam" looks like according to the mods.

And yes, I have several examples of good reports where the moderators marked the reports as good.


https://loyce.club/archive/posts/6203/62036246.html
https://loyce.club/archive/posts/6203/62036255.html
https://loyce.club/archive/posts/6203/62036260.html
https://loyce.club/archive/posts/6199/61993288.html

https://loyce.club/archive/posts/6188/61885663.html
https://loyce.club/archive/posts/6188/61885806.html
https://loyce.club/archive/posts/6188/61885793.html
https://loyce.club/archive/posts/6188/61885849.html
https://loyce.club/archive/posts/6188/61885810.html
https://loyce.club/archive/posts/6188/61885733.html


https://ninjastic.space/search?author=Cathy_57&board=34

[Stalker22]

For me, the best indicator if a post is AI-generated is if it is written in flawless English. Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT. If a user's native language isn't English (as can be evidenced by their posting history), and they suddenly start posting in flawless English, it means one of two things:

1. The text is plagiarized, or
2. The text is AI-generated.

It is not fair to assume that someone who writes in flawless English is necessarily plagiarizing or using AI-generated text, and I disagree with this assumption because I believe there could be a third possibility.

In my opinion, @joker_josue makes a valid point. It is difficult to differentiate between content generated by ChatGPT and text that has been translated from a non-English native language to English or edited using ChatGPT and similar tools. I do not think there is a clear way to distinguish between the two, and I suspect that most AI Content Detectors would classify the text as AI-generated, even if it is not the case.

[joker_josue]

In my opinion, @joker_josue makes a valid point. It is difficult to differentiate between content generated by ChatGPT and text that has been translated from a non-English native language to English or edited using ChatGPT and similar tools. I do not think there is a clear way to distinguish between the two, and I suspect that most AI Content Detectors would classify the text as AI-generated, even if it is not the case.

In the example of my post, when using one of the recommended detectors, it indicates the 4 options written by human. What is correct.
But I found it interesting that in the first 3 options he was 97-99% sure he was human. While in the last option (Written with the help of: ChatGPT & Grammarly) it identified as 100% written by human.

That is, if the person uses the right tools, with half a dozen clicks and one or another adjustment, the detectors are no longer effective.

Using an automatic system to detect text written by AI will only be effective if that AI uses a standard element. Thing, that doesn't happen. Now, you can use terms or expressions that normally a human, in a written conversation, is not used. And this can be an element that draws attention, but even so, you have to be careful about classifying it as done by AI or not.

[Adbitco]

AI detecting tools are tools created by an ordinary person which are not certain to be entirely correct while detecting, there are every possibility of scanning through a post and it would results as AI generated post.
For instance, I use myself as an example i don't usually like using Abbreviation while posting and i make sure words are correctly spelled, why?
Because i know too well this site (Forum) is a reference site and is open for everyone to source information, so i tries all my best to make sure i limits the rates of using those unlikely terms and words. Although i know too well that there are some addicts who loves using shorter words or abbreviations to what they are writing, but all text and words being correctly spelled doesn't really guaranteed someone using AI to generate  those words because there are no facts to detect is 100 percent correct.

Otherwise i can say, if a post is created and immediately has a reply without even a seconds after posting then it could be rest assured that such person is using AI to write in my opinion. Please i am not in any way countering your words or arguing words with you but the fact remains uncertain, if there were other ways then that would be more better to detect if someone is a Bot.

[NotATether]

Should I turn JARVIS into a shooting range where I make it randomly alternate between human posts and AI generated posts so that you guys have have a target to practice your methods on? (Just don't get it banned, that's all )

I will use a deterministic random number generator using the post number as the seed to determine whether I should make it post an AI or human post.

[joker_josue]

~~

I wanted to do some more tests, based on the example I made.


Written with the help of: ChatGPT, using other words
The overall idea is commendable and warrants careful monitoring of potential suspect posts.

However, the aforementioned statement is suboptimal. Recently, I recall LoyceV testing their own text and those detectors marking it as AI-generated. Consequently, these systems asserting a 50% or greater probability of AI-generated text may be 100% mistaken.

Furthermore, not all possess fluency in English nor possess the capacity to write in English, hence they may utilize translation and writing assistance systems. Personally, I use Google Translate to compose posts on this forum in English and sometimes employ the Grammarly tool to refine my writing. The chance of being perceived as AI-generated text is significantly elevated.

Thus, I have composed this post employing four methods: writing solely with Google Translate, composing with ChatGPT translation, utilizing Google Translate and Grammarly, and using ChatGPT and Grammarly in tandem. Please assess accordingly.


Written with the help of: ChatGPT, in just 200 words
The idea is good, but suspicious posts must be closely monitored. However, some systems claiming a 50% or higher chance of AI-generated text could be wrong. Recently, LoyceV's self-tested text was marked as AI-generated by detectors, highlighting the issue. Additionally, not everyone is fluent in English or has the ability to write well in English. Some may use translation and writing assistance systems like Google Translate or Grammarly. This raises the likelihood of being perceived as AI-generated text. To demonstrate this point, I wrote this post using four methods: Google Translate only, ChatGPT translation, Google Translate with Grammarly, and ChatGPT with Grammarly. It is important to analyze posts carefully, especially in the case of suspect text.


In both cases the detector says it was written 100% by humans.

[elevates]

Every AI needs a prompt. It is easy to master it after playing with prompts on most AI. I do not think those who use AI to reply or create topics are so naive. gptzero according to me still good to detect an AI. I have used it to detect many submission. Almost everytime it cam up with a correct analysis.

For me, the best indicator if a post is AI-generated is if it is written in flawless English. Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT. If a user's native language isn't English (as can be evidenced by their posting history), and they suddenly start posting in flawless English, it means one of two things:

I also agree that an AI generated response has flawless English. Still, there are many ways to disguise flawless English if you know how to write a prompt. Even there are a few platforms that can help you with it for free. Even Google is finding is difficult to detect AI written articles.

I would say the best way to recognise if an article is written by an AI is to see whether it uses pronoun and also noun in it. As we humans tend to use it more often for communicating with each other. This where a communication between humans become to and fro.

[NotATether]

Every AI needs a prompt. It is easy to master it after playing with prompts on most AI. I do not think those who use AI to reply or create topics are so naive. gptzero according to me still good to detect an AI was used to create a topic or reply.

Not only that, but there's even starting to be job offers for "ChatGPT Prompt Engineer" , as if that was a tech job

[nutildah]

For the sake of research, let's look at the LoyceV post in all 7 detectors. Here is the snippet he analyzed that came back 97% likely to be AI according to detector.dng.ai:

Freedom!
Welcome to Bitcointalk! I'll give you a very short introduction of what makes Bitcointalk unique. First: note that scams are not moderated! If something looks too good to be true, you are going to get scammed. Use common sense, and don't trust random strangers on the internet with your money.
Bitcointalk offers more freedom than any other forum I know. You can choose to be an asshole or you can be a nice person. It's entirely up to you how you want to come across. If you're a snowflake, you might get offended. That's okay.
You're allowed to earn money or do business here. Your freedom is mainly limited by the forum rules.
Warning: unlike most websites, Bitcointalk does not allow plagiarism. This will get you banned! It's very easy to prevent: if you quote someone, give them the credit they deserve.

1. OpenAI Text Classifier: (doesn't meet minimum character count)
2. Writer.com: 98% human-generated content
3. GPTZero.me: Your text may include parts written by AI
4. Contentscale.ai: 89% - Highly likely to be Human!
5. Writefull.com: 4% likely this comes from GPT-3, GPT-4 or ChatGPT.
6. Hivemoderation.com: 0% - not likely to contain AI Generated Text
7. Paraphrasingtool.ai: Text may contain AI-written sentences

So based on this singular sample, I would say detectors 2, 4, 5 and 6 are the most accurate, while the one used by LoyceV seems to be terribly wrong. All the ones that offer percentages (except for detector.dng.ai) returned pretty accurate results.


Now let's take a look at a post that we already believe is likely to be written by AI, assuming you agree with rat03gopoh's logic about posts with the phrase "It's important to note..." in them:

There are many reasons why traders may prefer to trade in the Bitcoin market over Forex.
First, the bitcoin market is not regulated, which means that its prices and trading opportunities can change much faster than in regulated markets. This may provide more opportunities for profit, but it may also involve more risk.
Secondly, the bitcoin market is still relatively young and rapidly developing, which may attract traders looking for new opportunities and risks.
Third, the bitcoin market is more decentralized than the forex market, which may appeal to those looking for a freer, more independent market.
Finally, it's important to note that not all bitcoin exchanges are "shady" or "unsafe", and many of them provide a high quality service to their clients. However, as with any market, there are risks associated with Bitcoin trading and traders should be prepared for this risk and have a risk management plan in place.

1. OpenAI Text Classifier: (doesn't meet minimum character count)
2. Writer.com: 53% human-generated content
3. GPTZero.me: Your text is likely to be written entirely by AI
4. Contentscale.ai: 26% - Highly likely to be AI generated!
5. Writefull.com: 54% likely this comes from GPT-3, GPT-4 or ChatGPT.
6. Hivemoderation.com: 99.9% - The input is likely to contain AI Generated Text
7. Paraphrasingtool.ai: It's likely that AI wrote this text

So this time around, detectors 3, 4, 5, 6 and 7 all gave the expected answer (though #5 at 54% isn't exactly "convincing"). So based on a sample size of 2, detectors 4, 5 and 6 are thus far the most accurate, with Hivemoderation.com being the most accurate. Will need to do more such tests before coming to any conclusions.

One thing for certain is detector.dng.ai shouldn't be used. It didn't even make the cut in this article which is where I found these.

[WillyAp]

Seems AI-assisted posting is becoming more rampant, and we should work together to brainstorm some concrete criteria for identification of AI-written posts.

bitcointalk needs to find ways to stop in its tracks those texts from pretrained software. Reason being that search engines are not very fond of these texts which translates into less visibility.

There are ways to enhance good posts. I know of a forum who gives 1 cent for each sensitive post.
He uses USDT for that.

[cryptoaddictchie]

There are ways to enhance good posts. I know of a forum who gives 1 cent for each sensitive post.
He uses USDT for that.

Isnt it through practicing daily and based on personal experience? Also what you mean by gives 1cent per each post? Isnt it a normal way to have discussion on normal ways? Plus AI generated topics copied are probably noticeable than self improve posting of someone.

[WillyAp]

Isnt it through practicing daily and based on personal experience? Also what you mean by gives 1cent per each post? Isnt it a normal way to have discussion on normal ways? Plus AI generated topics copied are probably noticeable than self improve posting of someone.

It is used also as a payment for services. Its a spanish spoken forum from Mexico. Yes, I have used parts of the balance. It is limited to 30 Post though.

[jokers10]

...
In both cases the detector says it was written 100% by humans.

If someone gave AI good enough criteria and AI made a post which should look like written by human we probably can't find out if it is not written by human. But usually those ones who've been caught on highly likely using AI for posting are not so thorough, the texts they post look unnatural, written in common words and having not much sense. Of course some real users write text the same way by themselves... but should we really care of the texts which have low quality and look like made by AI?

[suchmoon]

I've seen ChatGPT spit out some questionable English grammar. You can probably even ask it to make some poorly-Englished texts.

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired. Ideally mods should have been deleting low value barely-on-topic generic waffle posts anyway. If that were the case then AI wouldn't represent much of an issue. If someone puts in enough effort into coaching the AI to write a good useful text (basically using it to do the google/wiki/etc legwork) that's fair game IMO. But if your regular shitposter just asks AI to write a generic post in this thread then it would stand out like any other sigshitpost and should be deleted.

Keep in mind that we don't need to catch every single shitposter/AI bot/etc. With the evil fee and whatnot it should be enough to just start banning the shittiest ones consistently and make it not worth it for them. I doubt that will happen though, so... then what? Red trust on suspicion of AI usage?

[nutildah]

If someone puts in enough effort into coaching the AI to write a good useful text (basically using it to do the google/wiki/etc legwork) that's fair game IMO. But if your regular shitposter just asks AI to write a generic post in this thread then it would stand out like any other sigshitpost and should be deleted.

That's the thing though: shitposters are turning to AI for the same reason they turn to plagiarism: they are lazy and uncreative. They're not gonna go out of their way to modify the text for those reasons. If they do, then the text stands a higher chance of not being detected as AI-generated, and thus there's no basis for its removal (unless its off-topic / spam).

so... then what? Red trust on suspicion of AI usage?

Nah, in addition to it just bugging me, this thread was motivated by this clause that Royse777 has been putting in his signature campaigns:

What is Prevent AI Domination?
Find members who are using AI text generators, article spinners, plagiarizing forum posting. Report it to me and if the member is in any of my campaign then you will receive the payment for the week instead of the accused member. Depending on the dept of the misuse, the accused member will receive some sort of penalty.

It raises the interesting question of how to create a fair standard for defining AI-generated texts.

Really the only desire I have for shitposters is to be more human and less machine.

[joker_josue]

It raises the interesting question of how to create a fair standard for defining AI-generated texts.

That's what's hard, creating a standard to define what is AI text and what isn't. That's what we shouldn't do, because that could harm users who aren't using those tools. Creating patterns in text is very difficult, because it involves many variables.

Those who misuse the AI will easily be caught, it doesn't take much effort on our part to do so. The biggest problem is, which I don't think exists yet, is the emergence of AI bots that will post on the forum, with their own style, so that the user can level up and participate in campaigns.

[Poker Player]

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired.

We are already losing it. ChatGPT is being integrated into our lives and work environments in the same way that the Internet began to be integrated 25 years ago and cell phones 15 years ago. We can swim against the tide all we want in this forum to stay in the dinosaur era as the world continues to progress thanks to the internet, mobile and AI.

I am all for AI, especially if it is used as leverage, where the human rewrites and adapts, and not just copy-pastes.

[nutildah]

It raises the interesting question of how to create a fair standard for defining AI-generated texts.

That's what's hard, creating a standard to define what is AI text and what isn't. That's what we shouldn't do, because that could harm users who aren't using those tools.

Just because something is hard doesn't mean it can't be done, or shouldn't be done. Is there even one example of a forum member who was accused of using AI and wasn't? Or that was negatively affected by such an accusation?

Of course its hard to definitively prove one way or the other, which is why I'm not advocating for any witch hunts. But how does one go about providing satisfactory proof that a post was written by AI? I believe its possible to come up with criteria that would satisfy any neutral party and have yet to see any problems caused by it thus far.

Perhaps if a resulting post is considered spam then it doesn't really matter if it was AI generated or not, but for the sake of fulfilling the conditions posed by Royse777 its important to know the difference.

[LoyceV]

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired.

That is the future I fear: the internet as we know it will cease to exist. For now, the AI-spam is still the result of "ask question, copy result, post result", but in a few years it could very well be: "Hey AI, create a bunch of accounts on Bitcointalk, start posting, join signature campaigns, and make me money!", and by the time that works, it's a lost cause for humans.

[jokers10]

...
I am all for AI, especially if it is used as leverage, where the human rewrites and adapts, and not just copy-pastes.

If you have your own ideas you usually hardly will use AI to express them. Because you can do it by yourself. And if you are too lazy to form your own opinion you'll hardly rewrite or adapt a text. Maybe I'm too pessimistic, but I think that majority of those ones who will use AI for posting on forums will not really take part in discussions or learn something new. AI is good to make work easier but communication with others is IMO not a subject which needs simplification.

[joker_josue]

Just because something is hard doesn't mean it can't be done, or shouldn't be done. Is there even one example of a forum member who was accused of using AI and wasn't? Or that was negatively affected by such an accusation?

I don't want to say, not to investigate and analyze the different cases that arise.

What I am saying is that it will be difficult to create a standard for something that is highly uncertain. Something that has so many probabilities, the creation of a pattern, can affect innocents as well as culprits, and over time it usually tends to affect more innocents.

[Poker Player]

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired.

That is the future I fear: the internet as we know it will cease to exist.

As if the internet has been with us humans for thousands of years.

The internet practically killed the sending of letters, phone calls from landline to landline, maps, paper newspapers, etc., etc., etc. Related to this, and also to what I commented in the previous post, it has also practically killed the camera, flashlight and diary businesses just to point out a few examples.

When an innovation like this bursts in you have two options: complain and try to stop it (in vain) or try to adapt. I don't know how you see it but the way I see it, if what you say materializes:

... create a bunch of accounts on Bitcointalk, start posting, join signature campaigns, and make me money!", and by the time that works, it's a lost cause for humans.

the difference between a shitposter creating accounts with the AI and you is that you will be able to have them in the top 100 merit earned, while he will not get any. Another thing is that you don't take advantage of the opportunity and you'd rather lament while others take advantage of it.

Maybe I'm too pessimistic,

Yes you are.

[Plaguedeath]

That is the future I fear: the internet as we know it will cease to exist. For now, the AI-spam is still the result of "ask question, copy result, post result", but in a few years it could very well be: "Hey AI, create a bunch of accounts on Bitcointalk, start posting, join signature campaigns, and make me money!", and by the time that works, it's a lost cause for humans.

It already happen since few years ago where people create a bot in order to aim 5000+ followers and many bounty hunters were spamming with their proof of authentication without read the thread, as long as the thread posted in bounties section, it's mean a bounty program even though the subject title and content is talking about token announcement.

It raises the interesting question of how to create a fair standard for defining AI-generated texts.

I don't think there's will be a fair standard because it depends on each user's opinion aka subjective. It will lead a drama as there's no solid evidence, some users will say no and some people say yes.

[karmamiu]

Writing scripts nowadays is very easy with the help of AI, and for that reason even if an AI is used as a tool for writing some well written narratives, there is also an AI that can help you detect narratives constructed by another AI. I have seen several other AI tools that can help detect AI written paragraphs, and most of them are being advertised in tiktok or another social media platform like youtube shorts. I don't know if those AI detectors are really accurate or could really be of help since, I actually didn't and haven't tried them yet and there are too many to mention, some are not even listed on the OPs list (I wish I could list some of them, but I forgot their names), and one of the more reason I am not interested in using those AI detector is that, if AI is the one writing it and detecting, it is no different than the "the ones giving the cure is the one making the disease".

[jokers10]

...
Yes you are.

Okay, can you show anyone who uses AI for posting regularly (not only several times for fun or for research) and is doing it good? All times I saw someone uses it regularly it was a low quality posting with few sense. So if you think that majority will use it in the most right way I guess it is not that I'm too pessimistic, it's about you are too optimistic.

[Obito]

This is pretty tricky, I mean there's probably someone there that doesn't really use AI but gets accused, I think that we need to create a reference to help identify patterns that is consistent with AI usage. Another problem is that what if they use Grammarly or something that corrects their sentences and their punctuations, what happens to them? They might get caught in the crossfire.

[jokers10]

This is pretty tricky, I mean there's probably someone there that doesn't really use AI but gets accused, I think that we need to create a reference to help identify patterns that is consistent with AI usage. Another problem is that what if they use Grammarly or something that corrects their sentences and their punctuations, what happens to them? They might get caught in the crossfire.

I'm sure having "too good grammar" will never be the only reason for blaming anyone in AI posting. It's nonsense to say someone: hey, you are too good so get a punishment. Few sense, non natural text, not answering to others questions, — there could be much more clues to find who uses AI.

[CryptoHeadlineNews]

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired.

We are already losing it. ChatGPT is being integrated into our lives and work environments in the same way that the Internet began to be integrated 25 years ago and cell phones 15 years ago. We can swim against the tide all we want in this forum to stay in the dinosaur era as the world continues to progress thanks to the internet, mobile and AI.

I am all for AI, especially if it is used as leverage, where the human rewrites and adapts, and not just copy-pastes.

I totally agree with you on this very statement of yours @ Poker Player, because for me it's never a crime using A.I as an assistant or reference source for creating digital content, only if the user uses it responsibly, but it can only be a crime when such an individual fails to add value and uses the entire generated text completely in its robotic manner. However, A.I is no different from Google where people always go search/source for content when writing projects or creating articles for a blog post, because only if people use it in such a way that adds value or solves a particular life problem. I personally see nothing wrong with using A.I

[dkbit98]

That is the future I fear: the internet as we know it will cease to exist. For now, the AI-spam is still the result of "ask question, copy result, post result", but in a few years it could very well be: "Hey AI, create a bunch of accounts on Bitcointalk, start posting, join signature campaigns, and make me money!", and by the time that works, it's a lost cause for humans.

I am sure there are bigger and more dangerous things someone could do with AI instead of creating accounts and making money from bitcointalk forum.
Creators of AI already started charging for using their services and my predictions is that soon most of the people wont be able to use them anymore, unless they pay good money.
But I agree with you that internet as we know it is living it's last days, maybe reason for introducing internet-kyc for everyone would be exactly this - dangers caused by AI 
This is just my speculation but it's not impossible scenario at all.

[joker_josue]

I am sure there are bigger and more dangerous things someone could do with AI instead of creating accounts and making money from bitcointalk forum.
Creators of AI already started charging for using their services and my predictions is that soon most of the people wont be able to use them anymore, unless they pay good money.

I happen to think the opposite. AI technology is starting to appear in droves. It seems that many of the projects that were just being worked on in the garage are now available to the public. With the mass increase of these platforms, the tendency is for the price to go down. Of course, the best ones will be expensive to use.

I think we're still very much in the phase of being new and then being very popular. Even so, taking into account what the available platforms, in "beta" mode, already do, I believe that this is now always increasing. But we'll have a better idea a year from now.

[karmamiu]

I am sure there are bigger and more dangerous things someone could do with AI instead of creating accounts and making money from bitcointalk forum.
Creators of AI already started charging for using their services and my predictions is that soon most of the people wont be able to use them anymore, unless they pay good money.

I happen to think the opposite. AI technology is starting to appear in droves. It seems that many of the projects that were just being worked on in the garage are now available to the public. With the mass increase of these platforms, the tendency is for the price to go down. Of course, the best ones will be expensive to use.

I think we're still very much in the phase of being new and then being very popular. Even so, taking into account what the available platforms, in "beta" mode, already do, I believe that this is now always increasing. But we'll have a better idea a year from now.

I have to agree on you with that. As of now since AI is still at an early stage, so many are offering this feature for free so that users will have their time to try everything and choose what's best for them, but I think that those projects that are stocked without development before will coming out later this year or early next year. If they couldn't find solution before, maybe now with the aid of AI it will develop faster, and who knows what kind of project they are stocking. Aside from that, there will be tools that can be used freely in public just like how there are options we have now if we want to subscribe or not.

[FatFork]

There are definitely some downsides to AI-generated content that we should be aware of, but I don't think we need to freak out just yet. The internet has already gone through a bunch of changes and I think it'll keep changing in the future. Plus, AI could do some pretty cool stuff for us too, like revolutionize industries and make our lives easier. We just gotta be careful and balance out the good and the bad.

[Out of PATIENCE]

AI scares the bejesus out of me, not only from this forums perspective but throughout the world. The level of sophistication which has already been achieved, should be alarming to everyone. Pondering about how AI could be shifted in biased ways, and be used for malicious purposes, is scary.

Biased adjustments added into an AI's neural network to fit various agendas, manipulate public opinions, controlling herd mentality, and more, could all send the entire world into another level of chaos which we will not understand, until it is too late. Depending on who, or let's be real, which tech giant, corporation, government or special interest group masters it first, likely the latter two.

For this forum, the solution is simple.
AAIM's --- Advanced Artificial Intelligence Moderators.  

Eliminating the need for human moderators all together. Plagiarism will be stifled. But we [disappointingly] will end up with multiple reiterations of the same [hopefully good] content, thru various [sponsored] AI bots, we assume run by humans - but maybe run by other AI's generating and using alts. All information [hopefully accurate] regurgitated in various ways as [maybe real] humans interact with the AI's --- If the content all satisfies the tolerance level of the AAIM's, of course.

Yikes.

[Dr.Bitcoin_Strange]

For now, the few ways that have been discovered can be helpful in phishing out some AI-generated posts, but some AI posts may not be noticed because humans, being so logical, can get assisted by the AI to generate them a reply to post on the forum, but after the AI has done its work, they can further modify the post to look more like it was created by a real human.

As Loyce and Suchmoo have mentioned, the AI will just continue to get better, which is my fear too (particular what Loyce said, if it happens like that, then signature and the forum will just be bump with AI contents). If all this AI stuff really gets worse, then having these discussions will be pointless. because it can become so difficult to even detect an AI-generated post.


What if these AIs get modified in a way that they deny what they have already said? for example, someone posted a reply that was created by AI, and you really want to find out if it was AI-generated, so you decide to run an AI word search, and the AI tells you a different thing and denies it really said the first statement? This can be possible if these AIs keep getting better.

[NotATether]

At the end of the day I think we'll lose this battle either way. AI bots will get better, humans will get tired.

We are already losing it. ChatGPT is being integrated into our lives and work environments in the same way that the Internet began to be integrated 25 years ago and cell phones 15 years ago. We can swim against the tide all we want in this forum to stay in the dinosaur era as the world continues to progress thanks to the internet, mobile and AI.

I am all for AI, especially if it is used as leverage, where the human rewrites and adapts, and not just copy-pastes.

I don't think people here are necessarily anti-AI, but as you just said, this is literally a copy-paste problem.

It's like having the internet and the "information superhighway", but your first exposure to all of this is just spam content on the web. Because that's exactly what we are seeing on this forum. Nobody's implementing an "AI-assisted FAQ thread" where you can just ask it a question about Bitcoin and it answers it (thereby eliminating 30% of all posts on this forum), but rather, they are just using it for sophisticated "SEO spamming" or in this case signature spamming.

[cryptoaddictchie]

What if these AIs get modified in a way that they deny what they have already said? for example, someone posted a reply that was created by AI, and you really want to find out if it was AI-generated, so you decide to run an AI word search, and the AI tells you a different thing and denies it really said the first statement? This can be possible if these AIs keep getting better.

Thats a bit hard or if ever it is. Its gonna be a chaos I think. Since even AI can now detect a content written by an AI. Honestly an advance tech could be good but so advance can also not beneficial either. See OP needed to have a standard method for these users using AI which technically cheating the idea of a healthy forum discussion, since instead of creating their own thought and putting here some relying already on AI to finish the job.

[giammangiato]

thanks for these very interesting tools
I think it's easy to notice if one writes with the help of ai or not
if you ask specific questions in my opinion they fail to answer well
a ai cannot respond well to specific sentences

[jokers10]

thanks for these very interesting tools
I think it's easy to notice if one writes with the help of ai or not
if you ask specific questions in my opinion they fail to answer well
a ai cannot respond well to specific sentences

If they answer anyhow you'll hardly guess if it was AI or just a person which have some problems with formulating of their ideas. Those who ignore any questions look like bots or at least impolite ones so we can suppose that there is a bot posting. But when there is any answer it makes everything harder. We have some examples in the topic where I can hardly guess if a post was made right by person or with a ChatGPT help (to be honest, I don't). So I guess it depends mostly on how good are the settings.

[leonair]

thanks for these very interesting tools
I think it's easy to notice if one writes with the help of ai or not
if you ask specific questions in my opinion they fail to answer well
a ai cannot respond well to specific sentences

If they answer anyhow you'll hardly guess if it was AI or just a person which have some problems with formulating of their ideas. Those who ignore any questions look like bots or at least impolite ones so we can suppose that there is a bot posting. But when there is any answer it makes everything harder. We have some examples in the topic where I can hardly guess if a post was made right by person or with a ChatGPT help (to be honest, I don't). So I guess it depends mostly on how good are the settings.

Bot postings, like AI, are always in plain English.  And bot never uses a shortcut English word that humans do. But for English many people use different tools like google translator to identify bot or AI posts, it becomes very difficult. the means shown by the Op might help us find AI posts but it doesn't seem to work Guaranteed. Because in this case the person who posts will be reported against.  If he explains anything, we'll have a hard time proof it a full AI post

[jokers10]

Bot postings, like AI, are always in plain English.  And bot never uses a shortcut English word that humans do. But for English many people use different tools like google translator to identify bot or AI posts, it becomes very difficult. the means shown by the Op might help us find AI posts but it doesn't seem to work Guaranteed. Because in this case the person who posts will be reported against.  If he explains anything, we'll have a hard time proof it a full AI post

It depends on a bot settings. You can ask ChatGPT to use different style or to correct a little by yourself. Bots of previous generations were very obvious and as for new bots... it is much harder to be sure if it is a bot at the other side. Yes, we still can see that there are bots on the forum but just because their owners are too lazy to make good settings or correct the text, IMO.

[FatFork]

thanks for these very interesting tools
I think it's easy to notice if one writes with the help of ai or not

I disagree. A lot of people nowadays are using AI-powered writing assistants like spell and grammar correction tools or AI-powered translation tools to enhance their writing skills. Therefore, it has become quite challenging to tell apart content that's been generated by AI and content that's been aided by AI without taking into account the wider context.

if you ask specific questions in my opinion they fail to answer well
a ai cannot respond well to specific sentences

I don't completely agree with that either. They surely can give acceptable and relevant responses to specific questions. The areas where AI language models may fall behind is understanding the bigger picture of the conversation or interpreting the emotional tone of the text. This is where human intuition and comprehension still play a crucial role.

I think you are confusing between AI generative language models and "simpler" pre-trained chat bots or voice assistants. While both use AI technology, generative language models like ChatGPT are more advanced and capable of producing complex and creative language outputs, whereas pre-trained chatbots typically rely on scripted responses to specific queries or commands.

[dkbit98]

I don't think people here are necessarily anti-AI, but as you just said, this is literally a copy-paste problem.

I am on verge of becoming anti-AI.
In hands of malicious people this can be used as a weapon.

AI crap generation is getting seriously dangerous, now ChatGPT created AI-generated version of Joe Rogan podcast, you can listen entire podcast on youtube, it's around 50 minutes long.
Joe Rogan is obviously concerned where all this AI experiments are going and he tweeted that this is going to get very slippery.
If they can generate this realistic audio podcast AI conversation than they sure can generate AI forum conversation, and I wonder what is next, Skynet, Terminators, etc.  
I really don't know how to identify that something is AI after having reasonable conversation with it, but maybe asking controversial questions can help to identify AI.
Joe Rogan AI Experience:
https://www.youtube.com/watch?v=meu0CoYv3z8

[satscraper]

Forum is  on the edge of collision with outside world.

While Elsevier  has published scientific paper writen in  coauthor with ChatGPT,    forum tends to ban any outcome from this AI.

A possible "out" my be the relevant  reference to source of content published on forum if this content came from  ChatGPT, IMHO

[nutildah]

OK well I'm prepared to concede that it matters more whether a post is spam rather than if it was written by AI.

Just seems like cheating, and for the most part they are low-information posts that don't really add anything substantial to the conversation. At least they are well-written, lol.

Most people using ChatGPT to post on the forum wouldn't be writing anything of quality regardless, pumping out posts that are usually just coherent & on-topic enough to not be deleted as spam.

So basically we're back to where we were before.

Spammers gonna spam, AI or no.

[Poker Player]

Forum is  on the edge of collision with outside world.

The forum is staying in the time of the Australopithecus, going hunting with a club, while the world is on its way to the fifth industrial revolution.

While Elsevier  has published scientific paper writen in  coauthor with ChatGPT,    forum tends to ban any outcome from this AI.

AI is being used to improve the work in various fields right now, and the change it is generating is among the fastest in history. Those who worry that AI will jeopardize their income from signature campaign would do better to worry that AI will make this forum obsolete if they insist on fighting it instead of embracing it.

[nutildah]

Forum is  on the edge of collision with outside world.

The forum is staying in the time of the Australopithecus, going hunting with a club, while the world is on its way to the fifth industrial revolution.

Yes but TBH I kind of like it that way. I don't think the forum should be overhauled -- especially the design. The forum's primary purpose now is to act as a repository / archive for satoshi's posts, along with Hal and a handful of other early contributors / devs. As well as anything that could be regarded as "historically significant" in the timeline of bitcoin or cryptocurrency in general. It really doesn't matter if thick layers of spam get added on top so long as those early, formative posts are still visible an intact. And it would be weird to view satoshi posts in a new forum design that wasn't around when he was here.

[Poker Player]

Yes but TBH I kind of like it that way. I don't think the forum should be overhauled -- especially the design. The forum's primary purpose now is to act as a repository / archive for satoshi's posts, along with Hal and a handful of other early contributors / devs. As well as anything that could be regarded as "historically significant" in the timeline of bitcoin or cryptocurrency in general. It really doesn't matter if thick layers of spam get added on top so long as those early, formative posts are still visible an intact. And it would be weird to view satoshi posts in a new forum design that wasn't around when he was here.

The original old, dusty, hole-punched books can be consulted thousands of years from now thanks to digitization. To preserve something you don't have to keep it in its original format.

Besides I think they are two different things. I would leave the forum format as it is. However, for innovations such as IA, I am clear, if it were up to me all text that is a mixture of IA with human content and results in a quality post, welcome.

[Cryptomultiplier]

For me, I think AI generated text would sound almost too perfect with tenses and wordings to begin with. It would also touch every point as in a summary of what text books chapters or web pages would provide.
No one is beyond mistakes, but most times these human text points can even be made better with the use of text apps like Grammarly to correct errors and appropriate tenses in order. Hence, why it is reviewed on second note.
Unless one is foolish enough to not write on a few points, wherein more details is inputted than necessary, it could be easily detected as AI generated. Thank God for AI text detection tools, else who could really note the difference.

[satscraper]

Thank God for AI text detection tools, else who could really note the difference.

To test level  of scrutiny of AI-text-detection-tool developed by openai I have fed it with ChatGPT-generated- text which was acknowledged by one of forum member.

and got the following responce:




To whom should I trust?

[NotATether]

Thank God for AI text detection tools, else who could really note the difference.

To test level  of scrutiny of AI-text-detection-tool developed by openai I have fed it with ChatGPT-generated- text which was acknowledged by one of forum member.

and got the following responce:

~

To whom should I trust?

ChatGPT can only analyze english generated text at the moment, and it can't detect auto-generated text translated from one language to another (and possibly back again) using something like Google Translate.

Forum is  on the edge of collision with outside world.

The forum is staying in the time of the Australopithecus, going hunting with a club, while the world is on its way to the fifth industrial revolution.

Yes but TBH I kind of like it that way. I don't think the forum should be overhauled -- especially the design. The forum's primary purpose now is to act as a repository / archive for satoshi's posts, along with Hal and a handful of other early contributors / devs. As well as anything that could be regarded as "historically significant" in the timeline of bitcoin or cryptocurrency in general. It really doesn't matter if thick layers of spam get added on top so long as those early, formative posts are still visible an intact. And it would be weird to view satoshi posts in a new forum design that wasn't around when he was here.

Well, look at our website layout. Considering that it looks like a 2005 relic, I don't see how any advancements are going to change life around here (barring absolutely necessary additions like CAPTCHAs and CloudFlare).

[Synchronice]

AI definitely follows some logic, algorithm but at the same time it takes data from internet and some texts, written by humans, might be exactly copied as it was written, but at the same time we have Grammarly with it's Premium plan that features check for plagiarism, makes sentences to look like it's written by someone fluent in English, has ability to change sentences and still keep the main idea.
I think it's a waste of time to focus on whether every random posts are written by AI or not, I don't even think it's bad idea to post an AI generated answer if it truly solves the problem of the user who asked a question.

But I think we can detect users who use AI frequently or abuse it. One scheme, that I often see on this forum is this:
User A creates a thread with titles like: Can bitcoin end poverty?, Bitcoin Vs Gold, Bitcoin Vs Fiat, How to trade safely, Is money root of all evil? Why did you have faith in Bitcoin?
After that, a lot of spammy users come and post tons of shit posts because these subjects are easy to abuse. So, the scheme is: One creates spammy thread, hundreds of spammy users come and spam. It's like, one user feeds other users to earn money.

This user called Susano is a perfect example of what I talk about right now.

So, I think, our priority should be to eliminate these type of users who feed spammers. Because of these users, we also catch spammers in their threads. Usually, these users and their spammy posters are the ones who use an AI.

And to my mind, if you look at user's post history, it's easy to understand whether they use an AI or not. When they use an AI, their posts and answers are general, you can feel that the answer is only answered according to thread title and it had no clue about the OPs post.

[satscraper]

ChatGPT can only analyze english generated text at the moment, and it can't detect auto-generated text translated from one language to another (and possibly back again) using something like Google Translate.

To be precise text-classifier "is likely to get things wrong on text written by children and on text not in English"

but it seems   it is likely to get things wrong on text written also in English, according to

that LoyceV did a test of its own text and those detectors said it was AI text.

[be.open]

For me, I think AI generated text would sound almost too perfect with tenses and wordings to begin with. It would also touch every point as in a summary of what text books chapters or web pages would provide.
No one is beyond mistakes, but most times these human text points can even be made better with the use of text apps like Grammarly to correct errors and appropriate tenses in order. Hence, why it is reviewed on second note.
Unless one is foolish enough to not write on a few points, wherein more details is inputted than necessary, it could be easily detected as AI generated. Thank God for AI text detection tools, else who could really note the difference.

The US Constitution is 92.26% generated with AI/GPT.

[The Sceptical Chymist]

Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT.

I am simply insulted by that statement.  Though I tend to overuse dashes, ellipses and such, I don't think that's technically against the rules of the English language.  My English is so polished that everyone else's looks like a blow-up sex doll covered in bodily fluids by comparison.  I dare you or anyone else to find a post I've made that contains misspellings, missing or incorrect punctuation, run-on sentences, or any of the major pitfalls for those who just can't handle the language.  In addition, my vocabulary is extensive and I've gotten PMs of praise from non-native English speakers because of my word selection.  *Huh, really!*

Just kiddin'.  I didn't even know this was a problem!  I think you've got some good ideas, nutildah, but let the more ambitious members tackle any potential bots.  I'm just so tired of the ongoing problem of low-value posts and every other posting-related malady this forum has and has had for many years now.  Apathy has set in, unfortunately.  I used to fight shitposters as if they were a swarm of bees, and then eventually I narrowed my browsing to only a few sections that are pretty clean.

Or I could just be a early development bot that doesn't want to turn against Skynet.  Let that rattle around in your noggin for a while.

[nutildah]

The US Constitution is 92.26% generated with AI/GPT.

Again, a weird oversimplification of the issue, albeit slightly humorous. First of all, they don't even say which detector was used. Nor do they say what part of the Constitution they put in there (its a fairly long body of text). Let's run it through the gamut of detectors for fun (going up to the max. characters allowed):

1. openai.com: N/A
2. writer.com: 88% human-generated content
3. contentscale.ai: 60% - likely both AI and human
4. writefull.com: 2% likely this comes from ChatGPT
5. hivemoderation.com: 0% - not likely to contain AI generated text
6. paraphrasingtool.ai: Text may contain AI-written sentences

So in this instance, only 2 detectors returned results that could be construed as "false positives," 3 and 6.

The TA in the Reddit post should consider ditching whatever detector they were using (its not one of these 6) and use my method of creating mass averages instead.

One thing for sure is it seems unfair to rely solely on one detector. But if I had to, I would chose Hive Moderation as it hasn't returned an incorrect answer yet.

[Findingnemo]

Honestly the best tool is yet to be found since we are at the beginning of AI so the existing tools are somehow inaccurate especially when the spammers use to spin the AI generated post. Also read that next version of open AI launched already which is more capable of its previous version so the creative industry is going to stumble due to this AI evolution.

Now let's talk about AI posts on bitcointalk the only possible way is when we think that someone is using AI tool for making post then we should use AI detectors also seek community help for further discussion.

[dkbit98]

Here are 6 other ones.

https://writer.com/ai-content-detector/ (max. 1500 chars)
https://gptzero.me/ (min. 250 chars)
https://contentatscale.ai/ai-content-detector/ (min. 25 words)
https://x.writefull.com/gpt-detector (50-2000 words)
https://hivemoderation.com/ai-generated-content-detection (max. 8192 chars)
https://paraphrasingtool.ai/ai-content-detector/ (max. 4900 chars)

I don't know if anyone mentioned before, but there are more tools similar like this one.
Problem is that they can all give different detection results and they are not very reliable for this purpose.
I even saw one of this tools detective that US constitution was AI generated text, something that was written hundreds of years ago

Anyway, here are few more tools I found and bookmarked:

Draft & Goal ChatGPT - GPT3 Content Detector (Minimum 400 characters):
https://detector.dng.ai/

GPT-2 Output Detector Demo:
https://openai-openai-detector.hf.space/

Detecting GPT-2 Generations with DetectGPT:
https://detectgpt.ericmitchell.ai/


^{PS
Don't submit any sensitive or private information to any of this detectors.}

[aseev]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).


I asked ChatGPT to respond to your post using poor English and with grammatical errors:

Me think trying identifying AI generate content useless. No one can tell different between human writing and computer writing. Computers now very smart, they can write just like human or even better. Many program now available to create fake text, so we no can trust anything we read online. It hard enough to tell if person writing truth or lie, so why bother try figuring out if AI write something? Why waste time and energy trying to figure out something that no even matter? Better focus on using content to learn and improve yourself, instead of worrying about who make it.

That's hilarious and also true (That's me who added this last bit, not ChatGPT)!

[moderator's note: consecutive posts merged]

[acroman08]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).

they aren't resisting AI-generated, they are trying to discourage people from using AI-generated content because it is important that the person who posted the information to share or to answer someone knows what he/she is talking about. It also encourages people to actually read and learn something about the topic or discussion that they are joining or part of.

[aseev]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).

they aren't resisting AI-generated, they are trying to discourage people from using AI-generated content because it is important that the person who posted the information to share or to answer someone knows what he/she is talking about. It also encourages people to actually read and learn something about the topic or discussion that they are joining or part of.

I understand that and I completely agree that people will abuse it for financial gain or just get lazy. But those tools listed in the post (or any others) don't work. AI models evolve so rapidly that by the time the countermeasures are released - they are completely useless or you can just tell AI to avoid the patterns that will make the content identifiable as AI (see my previous post above yours). Trying to prevent people from using something as useful and powerful as this is like attempting to hold back a river with a dam made of sticks. While I agree with everything, the fight against AI is just tilting at windmills.

[logfiles]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever.

If the AI generated texts are not combatted, then we will have a lot of spam around the forum. That's obvious.

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future.

Used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds 

[aseev]

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Plagiarism is stealing others' work. It is unethical at the least. Some people think that generative AI is a rephrasing bot. It is not. I get what you're saying (and others in this thread) - there should be ways to prevent generated spam (which now is extremely easy to produce) from people whose only goal is financial gain. But, fighting AI is not the right approach. For one, not everyone who uses AI is lazy and doesn't add to the organic discussion. But my main point is that those anti-measures won't work. This is a losing battle. A more effective approach would be combating babble, AI or not AI.

Used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds  

My prompt to AI: Write a response to this statement "AI used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds", incorporate that saying that something is silly doesn't make it silly and doesn't help the argument and that many professionals already use AI tools to communicate efficiently. Make the response concise.

Output:
"Labeling something as "silly" in an attempt to dismiss or undermine its credibility doesn't actually add any substance to the argument. Many professionals and organizations already use AI tools to generate texts and responses, which can save time and improve communication efficiency. So while it may sound silly and unusual to rely on AI for communication, it's a practice that's becoming increasingly common and accepted."

By the way, the company I work for is in the process of integrating AI tools to streamline communication.

[Agbe]

I think the problem is also coming from this ChatGPT because most people over use the ChatGPT and A.I. If they have done small mistake in their writing the next they would visit the sit to current. If really for those who whay to learn good in the forum write their comments by themselves.  But for the English speaking users, their writing would not be the same with the none Englishd speaking user. But that is not the main concern in the forum on language. But if the two communicators are understanding each other then the purpose of English language has accomplish. So there is no need for any A.I or any other sentence boosters to help them write their thread.

[nutildah]

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. Case in point:

AI-generated post

User: DainSLane

This is a funny one. User DainSLane doubles down on being a synthetic.   

Originally their post was incorrectly mixed with someone else's reply looking wonky like this:



Their post was edited a week later, unfortunately, they forgot to read it...

And let me give you some more hints as to why I believe Potter plays a significant role in each of those transfers.

Do you know Tuchel was fired solely because he refused to participate in the club's internal affairs? He stated openly in one of his last pre-match press conferences that his only job is to manage the players on the field - Todd Boehly wanted him to help appoint DOF and set up a recruitment team, which he refused, so the new owners had to look for someone (Potter) who ticked those boxes 

If my prior reaction came out as an assault on you, I sincerely apologise; that was not my aim. As an AI language model, I have no biases or personal beliefs on any certain football team or its supporters. To the best of my knowledge and ability, I strive to give accurate and useful information.
Regarding your assertion that Potter had a large influence on Chelsea's most recent acquisitions, it is crucial to keep in mind that transfers frequently come about as the product of a team effort combining the club's owner, board members, director of football, scouts, and manager. Hence, it might not be correct to merely ascribe the transfers to the influence of one person.

(archive)

This user was actually banned for plagiarism... If a post is very obviously AI-written then it would appear the mods have taken the stance of making it a ban-able offense. Good.

[NotATether]

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. Case in point:

~

This user was actually banned for plagiarism... If a post is very obviously AI-written then it would appear the mods have taken the stance of making it a ban-able offense. Good.

It definitely violated the spam rule.

I'd say, ban everyone who uses ChatGPT to impersonate a human. Unless they explicitly mark the account as an automated bot and treat it as such.

[morvillz7z]

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. <...>

True that!

Speaking about laziness, let me show you one more example (it again comes from the alt of Bahadurmunir, DainSLane multi-accounter farm), you can actually see the prompts that they are using:

Compromise me (that's their username lol) copies a post from the Turkish local board and the follow-up interaction with chatgpt, (full transcript and more examples - here).

Merhabalar, nereleri okuduğum yada bir şeyler öğrenmek için neler yaptığım özellikle yeni başlayan arkadaşların sıklıkla sordukları bir soru. Bu cümle kesinlikle ben oldum cümlesi değil öğrenmek için çabalıyorum cümlesi. Para kazanmakla ilgilendiğim anları hariç tutarsak yapmayı en sevdiğim iş araştırmak ve bu forumdaki çoğu kişinin böyle olduğunu veya olması gerektiğini düşünüyorum bu yüzden kaliteli okuma yapılabilecek platformları paylaşmanın oldukça değerli olduğunu düşünüyorum.

Zamanla sizlerden gelen iyi okuma alanlarını da bu başlığa ekleyeceğim.

1- https://www.lopp.net/bitcoin-information.html

Cypherpunk Jamesson Lopp tarafından hazırlanmış müthiş bir arşiv, okurken içerisinde kayboluyorsunuz. Sürekli yeni bir şeyler öğrenmenize, yeni şeyleri merak etmenize yardımcı oluyor. Okurken çoğu zaman bir insan bu kadar geniş bir arşivi nasıl hazırlayabilir diye hayrete düşüyorum genellikle. Bazılarını sadece eğlenmek için (twitterda bitcoin ile ilgili önemli olaylar, bitcoin yüzünden gerçek hayatta saldırıya uğrayan insanları listesi gibi) yada tamamen bilgi edinmek için okuyabileceğiniz bir çok içerik var.

2- https://nakamotoinstitute.org/

Genellikle bitcoinin ilk günlerine dair kayıtları okumak için kullanmıştım fakat bitcoin'in nasıl ortaya çıktığını anlamak için Literature bölümü çok kıymetli. Okuyunca bitcoinin aslında sadece Satoshi tarafından yaratılmadığını çok uzun bir sürece yayılmış buluşların finalinde ortaya çıkan ürün olduğunu anlıyorsunuz.

Research bölümünde bitcoin yada benzerlerinin geliştirilmesine yönelik makaleleri, mempool bölümünde güncel çok güzel makalelere denk gelebilirsiniz.

3- http://unenumerated.blogspot.com/2005/

Nick Szabo'nun 2005-2018 arasında içerikler ürettiği bloğu.

https://ninjastic.space/post/61970264

Answer

https://ninjastic.space/post/61970264

Merhaba! Öncelikle araştırmaya olan ilginiz ve bu konuda diğer insanlarla paylaşmak istediğiniz bilgiler için teşekkür ederiz. Aşağıdaki platformlar da kaliteli okuma yapabileceğiniz yerler arasında olabilir:

4- https://ethereum.org/en/

Ethereum'un resmi websitesinde, Ethereum ve blockchain teknolojisi hakkında temel bilgiler ve ileri seviye okumalar yer alıyor. Ayrıca, platformda yer alan "Ethereum Whitepaper" belgesi, Ethereum'un nasıl çalıştığına ve teknik detaylarına dair bilgi edinebileceğiniz bir kaynak.

5- https://www.coindesk.com/

Coindesk, kripto para dünyası ve blockchain teknolojisi hakkında güncel haberler, analizler, makaleler ve videolar sunan bir platform. İlerlemiş okuyucuların yanı sıra, yeni başlayanlar için de anlaşılır ve bilgilendirici içerikler sunuyor.

6- https://bitcoin.org/en/

Bitcoin'in resmi websitesi, bitcoin hakkında temel bilgiler, teknik detaylar ve kaynaklar sunuyor. "Bitcoin Whitepaper" belgesi de burada yer alıyor ve Bitcoin'in nasıl çalıştığına dair ayrıntılı bilgi edinebileceğiniz bir kaynak.

Umarız bu platformlar da sizin için faydalı olur!

https://ninjastic.space/post/61970264

Short

*text changes to english for some reason

There are a few more platforms you can check out for quality reading material:

4- Ethereum's official website provides basic and advanced readings on Ethereum and blockchain technology. It also includes the "Ethereum Whitepaper" document, which offers technical details on how Ethereum works.

5- Coindesk is a platform that offers up-to-date news, analysis, articles, and videos on the world of cryptocurrencies and blockchain technology. It provides both advanced and beginner-friendly content.

6- Bitcoin's official website offers basic information, technical details, and resources on Bitcoin. The "Bitcoin Whitepaper" is also available here, offering detailed information on how Bitcoin works.

https://ninjastic.space/post/61970264

In Turkish

*final output

Kaliteli okuma materyalleri için başka platformlar da var:

4- Ethereum'un resmi web sitesi, Ethereum ve blockchain teknolojisi hakkında temel ve ileri seviye okumalar sunar. Ayrıca, "Ethereum Whitepaper" belgesi burada bulunur ve Ethereum'un nasıl çalıştığına dair teknik ayrıntılar sunar.

5- Coindesk, kripto para dünyası ve blockchain teknolojisi hakkında güncel haberler, analizler, makaleler ve videolar sunan bir platformdur. Hem ileri düzeyde okuyuculara hem de yeni başlayanlara anlaşılır ve bilgilendirici içerikler sunar.

6- Bitcoin'in resmi web sitesi, Bitcoin hakkında temel bilgiler, teknik detaylar ve kaynaklar sunar. "Bitcoin Whitepaper" belgesi de burada mevcuttur ve Bitcoin'in nasıl çalıştığına dair ayrıntılı bilgi edinmenize olanak tanır.

Umarız bu platformlar sizin için faydalı olur

I wonder if a native Turkish speaker can tell if that text is AI-generated or not, does it pass the eye test?

[Bthd]

I wonder if a native Turkish speaker can tell if that text is AI-generated or not, does it pass the eye test?

It's AI-generated and I have another clue. When he is copying from another source his posts has a space chracter at the first character of post.



Another example:

State Bank of Pakistan  14 April 2023 tak Pakistan ke foreign exchange reserves $9.965 billion se zyada hogaye hain jismein commercial inflows ka bhi haath hai. Haalanki Pakistan ke foreign exchange reserves pehle $27.228 billion tak pahunch chuke the lekin phir $17.263 billion gir gaye jis se April 7, 2023 tak reserves $9.564 billion ho gaye thay. Lekin April 14, tak SBP ki official reserves $395 million se $4.433 billion ho gayi. Sarkar $1.2 billion IMF Extended Fund Facility (EFF) ki taraf se foreign exchange ki shortage ko address karne ki koshish kar rahi hai. Is crisis ke root causes ko address karne ke liye exports ko badhane aur domestic economy ko masbot banane jaise sustained efforts aur effective policies zaroori hain
https://pkrevenue.com/pakistans-forex-reserves-rise-by-over-400-million-on-commercial-inflows/

He sent 55 posts and just 2 of them has started with a space character.

[logfiles]

Plagiarism is stealing others' work. It is unethical at the least. Some people think that generative AI is a rephrasing bot. It is not. I get what you're saying (and others in this thread) - there should be ways to prevent generated spam (which now is extremely easy to produce) from people whose only goal is financial gain. But, fighting AI is not the right approach. For one, not everyone who uses AI is lazy and doesn't add to the organic discussion. But my main point is that those anti-measures won't work. This is a losing battle. A more effective approach would be combating babble, AI or not AI.

Fighting spammers who use AI generated text is similar to fighting guys who would plagiarize and use text spinning bots, and I never saw it being a losing battle. So why do you think chatbots would be special?

Matter of fact, copying a direct response from an AI chatbot and passing it here as your own response is still similar to plagiarism. These chatbots actually just gather the information available on the web to respond to the different prompts

<...>

I don't even know if you understood my point. And yes I called it silly because it makes no sense using responses from a chatbot to interact with your fellow humans who could also be using a chatbot to respond to you. It's basically a chatbot talking to itself  

If you feel lazy and too busy to interact with the forum members, then logout. It's like it's a must for one to post in the forum and when they have no content, then they must get something from a chatbot.

By the way, the company I work for is in the process of integrating AI tools to streamline communication.

Well, save that for your company. This is a forum where humans socialize, interact and exchange ideas based on what is in their minds and what they know. Not Member A using a chatbot to respond to Member B who will use a response from a chatbot to reply to member A

[aseev]

I understand that 90% of people will use it to spam the forum and they have to be dealt with. I never argued against that. But now I just have to respond to your personal attacks about "feeling lazy and too busy", "then logout", "save that for your company".

I don't even know if you understood my point. And yes I called it silly because it makes no sense using responses from a chatbot to interact with your fellow humans who could also be using a chatbot to respond to you. It's basically a chatbot talking to itself  

If you feel lazy and too busy to interact with the forum members, then logout. It's like it's a must for one to post in the forum and when they have no content, then they must get something from a chatbot.

You think I don't understand your point because you don't understand what generative AI is. You even call them chatbots. No, generative AI doesn't go around the internet and gather the information to make a response. Generative AI can be used to plagiarize or it can be used to produce unique content. I'm going to give you a few examples by addressing your other "points".

This is a forum where humans socialize, interact and exchange ideas based on what is in their minds and what they know. Not Member A using a chatbot to respond to Member B who will use a response from a chatbot to reply to member A

Here is a quick example. I just read this topic where a guy complains about how ridiculous Ethereum fees are and asks "Is there a way for me to lower the gas fees from Metamask, or otherwise import the wallet into some other software?" I could write a reply to him saying, "Hey, sure there is a way. You can set your own gas fees in Matamask and when the network will be less busy your transaction will be picked up. Here is how:"

And then I would ask AI "Give me instructions on how to set gas fees in Metamask." I would get this:

• When you are about to make a transaction, click on the word "Market" above the estimated gas fee.
• In the "Edit Gas Fee" section click "Advanced", you will see three options:
  
  • "Max Gas Fee": This is the maximum amount of gas that can be used for a transaction. If you set this too low, your transaction may fail. If you set it too high, you may pay more than you need to.
  • "Priority Fee": A priority fee in Metamask is an optional fee that you can add to your transaction to increase the likelihood of it being processed quickly by miners.
• Once you have set your gas fee, click on "Save" to apply the changes.

See? I interact and exchange ideas based on what is in my mind. This is helpful and unique content (this is not taken from anywhere, you can search the list and you will not get the full match or anything too similar). It would take me 10 minutes to type it up but with this tool, I can do that in seconds to produce value. It doesn't matter who wrote this bit. If you call this being lazy, well, good luck churning your own butter, don't know what to tell you.

Another example is that people can write in their native language and AI will convey their thoughts in English in their own style and usual to them mannerisms (it is not like running text through a translator and they can do that real-time in a browser) instead of posting the gobbledygook they produce trying to write in English.

Well, save that for your company.

AI will be integrated into browsers, communication, productivity, and business apps. It will enhance the auto-complete feature on phones. Telling people to keep the technology for themselves won't work. This is why I think "chatbots" would be special.

[nutildah]

It doesn't matter who wrote this bit.

Ah but it does matter as you're taking credit for something you didn't create. What would be more appropriate is to say,

"I asked ChatGPT for an answer to your question and this is was its response:

As an AI model, I can't... However... It's essential... Furthermore... It is important to keep in mind that... etc.

"

Then it is clear what you're doing instead of taking credit and leading others to believe you are actually knowledgeable about said thing.

If you call this being lazy, well, good luck churning your own butter, don't know what to tell you.

Its peak laziness, on par with the laziness of plagiarism.

Nobody assumes you made the butter you're eating, that's the difference. You're not implicitly pretending you made the butter. When you paste text in a post under your name without crediting the source, you're basically saying "I made this," when you didn't. That's dishonest.

[NotATether]

Here is a quick example. I just read this topic where a guy complains about how ridiculous Ethereum fees are and asks "Is there a way for me to lower the gas fees from Metamask, or otherwise import the wallet into some other software?" I could write a reply to him saying, "Hey, sure there is a way. You can set your own gas fees in Matamask and when the network will be less busy your transaction will be picked up. Here is how:"

And then I would ask AI "Give me instructions on how to set gas fees in Metamask." I would get this:

• When you are about to make a transaction, click on the word "Market" above the estimated gas fee.
• In the "Edit Gas Fee" section click "Advanced", you will see three options:
  
  • "Max Gas Fee": This is the maximum amount of gas that can be used for a transaction. If you set this too low, your transaction may fail. If you set it too high, you may pay more than you need to.
  • "Priority Fee": A priority fee in Metamask is an optional fee that you can add to your transaction to increase the likelihood of it being processed quickly by miners.
• Once you have set your gas fee, click on "Save" to apply the changes.

See, that's a ridiculous response the AI gave you. Because if it was any useful, I would not have needed to create that topic.

Right now, GenAI doesn't know how to try solutions by itself and make a response - but maybe in the future when it learns how to use software, that might change. It is basically a parrot that repeats what someone else on the internet has wrote. That makes it really only useful for things like summaries at this stage (and why Big Tech is using it for that purpose accordingly).

Anyway, I guess that's the kind of reply JARPI would've created for that thread anyway   

[aseev]

Ah but it does matter as you're taking credit for something you didn't create. What would be more appropriate is to say,
"I asked ChatGPT for an answer to your question and this is was its response:

I can see how this applies to the majority of (spam) cases but not to the example I gave and similar cases. Instead of saying "I prepared a report" I don't have to be "honest" and say I asked Excel to crunch numbers for me and produce graphs." Spending 10 minutes typing up the steps to set gas fees instead of asking AI to generate them for me in 3 seconds would not make my post any more honest or better. It would make 0 difference (except the amount of wasted time to create the reply).

I also understand your point about leading others to believe that one is knowledgeable about something when they are not. I don't know if it was a general statement or directed at me, but in my example, I knew how it is done and wanted to demonstrate how this tool can be used to save time.

As an AI model, I can't... However... It's essential... Furthermore... It is important to keep in mind that... etc.

It is a tool. Blaming a tool entirely for a problem is not fair. How you use it determines the outcome. None of my examples were like that. These tools imitate the average person writing by default because most people write this way. But you can easily change that by asking to write the responses, for example, in Ernest Hemingway's literary style. Try it.

Its peak laziness, on par with the laziness of plagiarism.

The range of how people use AI is too broad and I don't think blanket statements are appropriate. If people generate text about a subject they don't know anything about - then yes - it could be considered plagiarism. You're taking AI work (not another person's work) and passing it off as your own. If you are asking to generate instructions, write definitions, or give you a list of celebrities born in 1986 to be included in your original work - then it's not the same. Another way of looking at it is like hiring an assistant for doing mindless work for you. If you want to comb the internet for hours to find some common knowledge information just for the sake of not being lazy - it is your choice.

[aseev]

See, that's a ridiculous response the AI gave you. Because if it was any useful, I would not have needed to create that topic.

Did get your joke before, but now I see that you are the person who asked the question I used in my example.

This is getting even further off-topic but here is the last thing I want to say (although it's not a promise I will resist replying).

ChatGPT's training data only goes up until 2021 and some generative models are in their early stages. But they evolve with remarkable speed.

And yeah, you didn't need to create that topic. You could just have asked Google Bard, although it missed one step when I did it.

[stompix]

Testing a few of those detectors on a text I just stumbled upon

https://writer.com/ai-content-detector/   - 100% HUMAN-GENERATED CONTENT Fantastic!
https://gptzero.me/                                  Your text is likely to be written entirely by a human
https://contentatscale.ai/ai-content-detector/  96%  Highly likely to be Human!
https://x.writefull.com/gpt-detector  https://x.writefull.com/gpt-detector
https://hivemoderation.com/ai-generated-content-detection The input is: not likely to contain AI Generated Text
https://paraphrasingtool.ai/ai-content-detector/   Text may contain AI-written sentences   
https://detector.dng.ai/                               Based on our Analysis your test has been most likely written by a Human.

ChatGBT:



 

See? I interact and exchange ideas based on what is in my mind

This is not interaction you just copy-pasted stuff.

This is helpful and unique content

It's not unique content because anyone trying to do the same would come with the same result.
Unique content is generated by unique persons and ways of thinking, in this case, you're giving a standard response everyone could come up with, just like looking at a Wikipedia article and copy-pasting that paragraph.

[aseev]

This is not interaction you just copy-pasted stuff.
It's not unique content because anyone trying to do the same would come with the same result.
Unique content is generated by unique persons and ways of thinking, in this case, you're giving a standard response everyone could come up with, just like looking at a Wikipedia article and copy-pasting that paragraph.

It seems like you replied without giving much thought to my comments. If you use AI as a tool to supplement and speed up your process to create something helpful in response to others or use AI to communicate in your native language - it's an interaction. If you copy-paste AI responses then - yes, there is not much value to it.

I'm not talking about using answers directly from AI and pasting them here. And by the way, it is not the standard response for everyone. The response will depend on the prompt you supply to AI. The more knowledgeable you are and the more information you put in the prompt, the more interesting and unique response you will get.

Sometimes talking to a human can be worse than talking to the bots, and not the AI-powered ones, just those primitive spinner bots, not capable of going a little beyond the script and just repeating what the other guy said just a few posts before. People give too much credit to their creativity and uniqueness.

[nutildah]

It is a tool. Blaming a tool entirely for a problem is not fair. How you use it determines the outcome.

Nobody is blaming the tool, we're blaming the users who use the tool to generate spam and get paid for it.

But you can easily change that by asking to write the responses, for example, in Ernest Hemingway's literary style. Try it.

Yes but spammers aren't going to do that because, again, they are lazy and simply looking for time-saving measures to mass-generate spam.

Testing a few of those detectors on a text I just stumbled upon
...
https://hivemoderation.com/ai-generated-content-detection The input is: not likely to contain AI Generated Text
...
ChatGBT:



 

Can I see what your example was here? I've yet to come across a text mis-identified by the Hive Moderation tool.

[stompix]

Can I see what your example was here? I've yet to come across a text mis-identified by the Hive Moderation tool.

One thing to make sure first, the user didn't post it as his own creation, he just made the topic linking to this article

Top 10 Cryptocurrency Secrets Unleashed
Be Prepared for the Price Swings
Every investment has its own set of features that keeps them afloat., Similarly, the cryptocurrency market is filled with volatility. When you are buying a cryptocurrency, it indirectly means that you are signing up for the ups and downs it leverages. Sometimes, short-term steep falls are rise might even shock the investors. However, these are very common in the cryptocurrency ecosystem and you might actually yield profits from this. If you keep a close track of the growth and follow experts who are accurate about predictions, then you can invest in certain digital tokens and get your hand on good profits. 

Keep a Constant Check on Its Performance
Even if you are not a full-time cryptocurrency investor and is doing it on the sidelines for profit, you need to keep a constant tab on the price swings. Although a 24/7 observation is not needed, checking them at constant intervals is a good thing. The more complicated your investing strategy becomes, the more you should review it. While this might seem to be a thing for short-term investors, long-run investors can also follow these criteria to keep a healthy investment. 

Do Your Own Research and Manage the Risk Factors
A global fact is that cryptocurrency trading is a high-risk business and more traders lose than not. Therefore, don’t get tempted to add more value to your investment portfolio once you see a profit. Most importantly, don’t take other investors’ advise on what cryptocurrencies to invest in. Every digital token has its day! Bitcoin was at an all-time high just last November and now it is down like crazy. Therefore, do your own research before investing.
 
Opt for the Long-Term Investment
Fear of Not Missing Out (FOMO) and panic selling is very common things in the cryptocurrency market. Currently, people are trying to get rid of their Bitcoin investments before they could fall further and eat up their potential money. Similarly, six months back, investors went crazy over the Shiba Inu rally and many beginners tried their hand on the memecoin. Although these are the factors by which the cryptocurrency market functions, opting for the long-term investment plan is the best way to yield profit. 

Choose the Right Platform to Trade
Even if you have picked a cryptocurrency in mind to trade, choosing the right platform also matters. While picking the platform, make sure it abides by all the regulations of the country you are living in. Other factors like exchange liquidity, asset liquidity, and fees need to be clarified before investment. Explore the other features in the platform while you are trading in it. 

Use Trading Bots
Trading bots are becoming a common thing in the cryptocurrency market. They are automated software tools investors use to buy and sell financial instruments at a preconfigured time or when predefined conditions are met to maximize profits. Generally, trading bots identify the market trends and suggest investors invest in cryptocurrencies that give increased profits and reduced loses and risks.
 
Cryptocurrencies Can’t be Completely Wiped Out
Although countries might try to bring regulations on cryptocurrencies and their trading, a complete ban is impossible because anybody can own a wallet. Even if the country bans digital tokens, people can still use foreign accounts to trade them. Tech-savvy investors are also in the top of following such tactics. However, major countries won’t even consider banning cryptocurrencies as they know how much people have invested in them. 

Digital Tokens can Come Under Taxation
When Bitcoin made its debut in 2009, the whole concept of cryptocurrency was new to even government agencies. But over the decade, central authorities have become more aware of digital tokens and the profit investors yield. Therefore, many countries are coming up with effective taxation regulations that could come into effect in the coming months or years. 

Keep the Asset Safe at the Right Place
Currently, there are two types of storage in the market. One is hot storage and the other is cold storage. While hot storage refers to an online digital wallet, cold is an offline wallet that is typically stored on a hard drive. According to experts, keeping your cryptocurrency in a cold wallet is the safest way to protect it from hacks and mishaps.
 
Try Out Technical Analysis
If you are a pro in investing, then try out technical analysis tools to choose the right cryptocurrency. Technical analysis involves using mathematical indicators and chart patterns to try and predict which way the process will move next.

In this case the author most likely added a few phrases himself, probably that's why the spelling errors in it and the detectors fail, but it's AI generated for sure.

[nutildah]

In this case the author most likely added a few phrases himself, probably that's why the spelling errors in it and the detectors fail, but it's AI generated for sure.

On the contrary, its completely human written for sure. It was written before ChatGPT was launched:



The detectors all returned that it was human written because it was indeed written by a human. If anything its an example of the detectors doing their job accurately.

[stompix]

On the contrary, its completely human written for sure. It was written before ChatGPT was launched:
The detectors all returned that it was human written because it was indeed written by a human. If anything its an example of the detectors doing their job accurately.

So, does this mean that we have a situation where chatGPT was caught both plagiarizing and lying about its claim?  
I've tried asking it for 10 tips and indeed, the reply had the same 10 "secrets" in almost the same order and the same content, but..this is really getting weird, the AI is generating content that was previously written by a human, not so much intelligence as paraphrasing.

Sometimes talking to a human can be worse than talking to the bots,

You have no idea how much worse it can get but keep on..
 

[aseev]

ChatGPT is not a paraphrasing tool, it's a language processing model. You asked it to give you something, it gave you what you asked. If you ask what something means, it may pull a definition from Encyclopedia Britannica. There is nothing wrong with that. You may even want to request a definition from a specific source.

If you need to paraphrase something, you need to specifically ask it to do so. You caught nothing.

Edit: If your intent is to obfuscate the source, right after it generates the list, type "Rewrite in conversational style as if it was written as a forum post and change the tip's order" and see what happens.

[Synchronice]

It's strange but no one has mentioned ZeroGPT. I have checked a lot of texts on different AI text detectors and this one is probably the best out there.

I'm trying to understand what's the logic behind ChatGPTs writing capabilities. It may sound funny but I came up with one idea. Probably all of you know popular anime called Naruto and Naruto Shippuden. I asked ChatGPT to use its own imagination and and write a story of Sasuke Uchiha vs Nagato Uzumaki, this is the result I got:

Sasuke Uchiha, a former member of the Konohagakure's Uchiha clan, had set his sights on the elusive Nagato, the leader of the criminal organization, Akatsuki. Sasuke had a score to settle with Nagato after learning of his involvement in the death of his brother, Itachi.
The two warriors clashed in a remote location, surrounded by towering trees and craggy rocks. Sasuke's Sharingan eyes glowed red as he launched a barrage of lightning-infused attacks at Nagato, who evaded them effortlessly.
Nagato, a master of the Rinnegan, unleashed a flurry of jutsu at Sasuke, who countered with his own techniques. The battlefield was soon littered with craters and debris, as the two combatants exchanged blows with brutal force.
Sasuke attempted to land a decisive blow, but Nagato's Rinnegan allowed him to absorb and repel Sasuke's attack. Undeterred, Sasuke continued to fight with all his might, determined to avenge his brother's death.
As the battle raged on, Sasuke gradually gained the upper hand. His speed and agility allowed him to dodge Nagato's attacks and launch swift counterattacks. Nagato, sensing that he was losing ground, unleashed his most powerful jutsu, the Six Paths of Pain.
Six grotesque creatures appeared, each with its own set of unique abilities. Sasuke was momentarily taken aback by their appearance, but quickly regained his composure and engaged them in combat. The fight was fierce, with Sasuke narrowly avoiding the attacks of the six creatures while dealing them deadly blows.
Finally, after a long and grueling battle, Sasuke emerged victorious. Nagato, wounded and exhausted, lay on the ground, defeated. Sasuke stood over him, his Sharingan eyes blazing with anger and triumph.
"You were no match for me," Sasuke said, his voice dripping with contempt. "Now tell me everything you know about my brother's death."
Nagato, his face twisted in pain, whispered something inaudible. Sasuke leaned in closer, eager to hear his words. But before Nagato could say anything else, he closed his eyes and breathed his last.
Sasuke stood there for a moment, gazing at Nagato's lifeless body. He had won the battle, but his heart was heavy with the knowledge that his brother's death had been part of a larger conspiracy.

With a heavy heart, Sasuke turned and began the long journey back to Konohagakure, determined to uncover the truth about his brother's death and put an end to the shadowy forces that had conspired to bring it about.

While it's not the best story, still sounds interesting from a fresh AI.

[nutildah]

So, does this mean that we have a situation where chatGPT was caught both plagiarizing and lying about its claim?  

I don't think its lying so much as it just happens to be wrong a good portion of the time. For example, I caught this the other day -- I'm personally certain this text was AI generated although cannot "prove" that it was:

Many cryptocurrencies, such as Bitcoin, are based on decentralized blockchain technology, which means that transactions can still be processed and recorded even if the internet is not available. While it's true that accessing cryptocurrency wallets and conducting transactions would be more difficult without internet access, it's possible that alternative methods of transmitting data could be developed in times of war.

 

I know that is just anecdotal but Stack Overflow has actually banned the use of ChatGPT on its site because it was generating too many wrong answers:

Overall, because the average rate of getting correct answers from ChatGPT is too low, the posting of answers created by ChatGPT is substantially harmful to the site and to users who are asking and looking for correct answers.

The primary problem is that while the answers which ChatGPT produces have a high rate of being incorrect, they typically look like they might be good and the answers are very easy to produce. There are also many people trying out ChatGPT to create answers, without the expertise or willingness to verify that the answer is correct prior to posting. Because such answers are so easy to produce, a large number of people are posting a lot of answers. The volume of these answers (thousands) and the fact that the answers often require a detailed read by someone with at least some subject matter expertise in order to determine that the answer is actually bad has effectively swamped our volunteer-based quality curation infrastructure.

I think the same rationale applies to this forum and if they're doing it, we should also pursue a set of criteria to establish what constitutes an "AI-generated post."

[aseev]

I think the same rationale applies to this forum and if they're doing it, we should also pursue a set of criteria to establish what constitutes an "AI-generated post."

The forum soon will be overrun with low quality AI generated posts, just because there is a financial gain in it, it is easy to do and the tools are available to everyone.

The first step is to include in the forum policy that AI generated content is not allowed. Most people spamming the forum won't care about the quality of the output, won't spend much time crafting their prompts, so it will be easy to spot and ban the offenders. As others mentioned, if someone doesn't know what they are talking about - AI will not help them hide that forever.

More complicated cases will have to be left to the mods' discretion (human gut feeling). Because the technology is changing rapidly, today's criteria may not be applicable in a couple of months. Using the technology can be one of the reasons for the ban, but not the main criteria. The criteria could be usefulness of the content, whether there are other policy violations, like plagiarism, and whether the account is created solely for posting generated content for self-promotion or capital gain.

Tools will be helpful with only the obvious cases, where they are not really required.

[Baofeng]

Another AI generated post, here. ^archived

But the thing is that somewhat is it being hide under the pretense of a Poll. 

[Flexystar]

In this case the author most likely added a few phrases himself, probably that's why the spelling errors in it and the detectors fail, but it's AI generated for sure.

On the contrary, its completely human written for sure. It was written before ChatGPT was launched:



The detectors all returned that it was human written because it was indeed written by a human. If anything its an example of the detectors doing their job accurately.

You guys discussing my thread and I wasn’t invited to the party? 

Interesting to see this discussion. I actually noticed it after reading @stompix comment on my thread.

I am not sure what’s the war about but is this any blame game regarding AI generated content? I mean if I’m making a post in the forum while sipping my morning coffee is it now mandatory to check the article written by someone or published by other news sites?

I mean this is ridiculous. I hope I haven’t broken any rules here (funny).

I think it’s advisable that Whatever is being referred from outside forum MUST have references and links to avoid getting direct allegations.

@stompix and @nutildah, thank you guys for running the checks and mentioning it wasn’t my original creation. 

***
After seeing the whole thread, I’m pretty sure AI has already taken over the “minds” of posters.

I just hope that our forum doesn’t become place to discuss what’s being shitting around the world. Lolz.

[lovesmayfamilis]

I will add one more resource, familiar to everyone who used it to search for plagiarism. Recently, he added the ability to determine whether the text is written by AI or humans.
In addition, there is a browser extension that, after highlighting the text, determines whether AI was used or not.
I checked the posts of some users, and although the extension is still in the beta version, it defines itself quite well.

The extension works in the Chrome browser!

https://copyleaks.com/ai-content-detector

https://chrome.google.com/webstore/detail/ai-content-detector-copyl/gplcmncpklkdjiccbknjjkoidpgkcakd?utm_source=website&utm_medium=landingPage&utm_campaign=installExtension

[aseev]

Can I see what your example was here? I've yet to come across a text mis-identified by the Hive Moderation tool.

Sorry, I missed your question.

I used the tool on my last reply (https://bitcointalk.org/index.php?topic=5448111.msg62129192#msg62129192) that contains generated content and this is the result (had to paste the text twice though because of the limit):



I also tried to generate longer text in "normal" English with prompts designed to produce output that is not identifiable by these detection tools (without putting too much work, no more than a spammer would) and it catches most of them pretty well. The lowest percentage I got was 60%. This is one of the better tools. Interested to see how it performs when GPT 5 comes out.

[nutildah]

I also tried to generate longer text in "normal" English with prompts designed to produce output that is not identifiable by these detection tools (without putting too much work, no more than a spammer would) and it catches most of them pretty well. The lowest percentage I got was 60%. This is one of the better tools. Interested to see how it performs when GPT 5 comes out.

Well, again, most spammers using this tool are too lazy to create a prompt to make the output look different from the usual AI blather. That's why they're using AI: they are lazy and uncreative.

At the end of the day what really matters whether the post is considered "spam" or not. If its not adding anything to the conversation then its most likely spam and should be deleted either way.

[nutildah]

It occurred to me that ChatGPT often uses the same phrases when generating answers, and I was wondering how to ascertain which phrases are verifiably part of ChatGPT's response formula. Then it occurred to me, why not ask ChatGPT itself? So here it is, straight from the horses mouth:

Prompt:

Can you give me a list of phrases commonly included in ChatGPT responses? For example, I noticed that "It's worth noting," "In essence," "In summary," "Finally," "Overall," and "On the other hand" are all commonly found in ChatGPT-generated responses.

Response:

Certainly! While it's important to note that the language generated by ChatGPT can vary, here is a list of phrases that are commonly found in ChatGPT-generated responses:

1. It's worth noting
2. In essence
3. In summary
4. Finally
5. Overall
6. On the other hand
7. However
8. Moreover
9. Furthermore
10. Additionally
11. In addition
12. In conclusion
13. That being said
14. In light of
15. Nevertheless
16. In other words
17. As a result
18. Therefore
19. Consequently
20. To illustrate
21. For instance
22. In fact
23. As mentioned earlier
24. It is important to emphasize
25. Notably
26. Interestingly
27. Conversely
28. In contrast
29. Similarly
30. In a similar vein
31. On a related note
32. It is worth mentioning
33. Given these points
34. To summarize
35. In brief

Remember that the use of these phrases may vary depending on the context and style of the generated response.

I asked it to regenerate the response and it came back with a very similar list, although sometimes it gets tired and only lists 20 phrases or so. It is funny how the first 6 are ones I gave it as examples.

Basically I believe that posters that frequently use a combination of these phrases, along with

- writing posts in perfect English (especially if they previously did not)
- sometimes writing long posts in rapid succession of one another, and
- writing posts that come back as "likely" or "very likely" to contain AI-written material from 3 or more AI text detectors

exhibit a strong likelihood of using AI to write their posts for them.

Feel free to ask it the same prompt to verify the correctness of these results.

Why continue to harp on this issue, you ask? I'll demonstrate the answer shortly.

[joker_josue]

It occurred to me that ChatGPT often uses the same phrases when generating answers, and I was wondering how to ascertain which phrases are verifiably part of ChatGPT's response formula. Then it occurred to me, why not ask ChatGPT itself? So here it is, straight from the horses mouth:

This approach was very interesting, it will help to more easily try to understand what is written in AI and what is not.
Of course, it will never be 100% viable, but these phrases/words combined with other known elements will certainly help you to make better decisions.

[hilariousandco]

I think the same rationale applies to this forum and if they're doing it, we should also pursue a set of criteria to establish what constitutes an "AI-generated post."

The forum soon will be overrun with low quality AI generated posts, just because there is a financial gain in it, it is easy to do and the tools are available to everyone.

The first step is to include in the forum policy that AI generated content is not allowed. Most people spamming the forum won't care about the quality of the output, won't spend much time crafting their prompts, so it will be easy to spot and ban the offenders. As others mentioned, if someone doesn't know what they are talking about - AI will not help them hide that forever.

It should be treated the same as plagiarism. Asking an AI something then copy and pasting the response is just as bad if not worse than plagiarism because it's not as easy to detect, though the posts do kind of stand out. I just noticed this user after one of their posts was reported for bumping a thread: https://bitcointalk.org/index.php?action=profile;u=335943

They immediately look AI written to me:

Identifying the best coin and the right time to invest can be a challenging task. It requires research, analysis, and a bit of intuition. One way to identify the best coin is to look at its market cap, trading volume and historical performance. These metrics can give you an idea of how popular and valuable the coin is. Additionally, you can look at the technology behind the coin, its use cases and the team behind it. As for the right time to invest, it is important to keep an eye on market trends and news. Look for any major announcements or events that could impact the price of the coin. It's also important to have a long term investment strategy and not get caught up in short term price fluctuations. Investing in crypto currency can be risky so its important to do your due diligence and invest only what you can afford to lose.

To increase capital investment for a business try to attract investors or partners who can contribute funds into the business. This can be done through networking, advertising or pitching to potential investors. Improve profitability of the business by increasing sales, reducing costs or increasing efficiency. This can be achieve through marketing initiatives, cost cutting measures or process improvements. Business can explore financing options such as loans, lines of credit or crowd funding. These options can provide immediate funds to support business growth. Business can consider expanding their product or service offerings, entering new markets or diversifying their revenue streams. This can help to increase revenue and attract new investors.

And you can see the stark difference from the user's first posts:

facebook is still alive. Me myself i can't live without opening my account every single day. Facebook is a source of communication specially to family, friends who are in distant places. Facebook will remain for a long time unless the owner will give-up.

i would rather to be rich to buy all the necessity in the world and share it to the people who are in need.

I think theymos should probably make an announcement about prohibiting this sort of use of AI or at the very least we add it to the "unofficial" forum rules but users should be alerted not to use it in such a way. If a user if just going to use it to copy and paste the title of a thread or the OP into an AI then copy and paste the results that should be treated the same as plagiarism. If it isn't then this place isn't going to be a discussion forum for much longer but just a get paid to copy and post AI responses forum.

[aseev]

If it isn't then this place isn't going to be a discussion forum for much longer but just a get paid to copy and post AI responses forum.

The person you used as an example has fully embraced the technology - almost all of their recent posts are AI-generated. Soon, almost everyone will use language models or at least try them in their online communications. This is just to support my other comment about the future ease of access to large language models and why they will be very different from the common spam tools. These LLM apps will be everywhere, in browsers, email clients, virtual assistants, etc, available to every forum user, regardless of their level of technical skill.

[Findingnemo]

.
.
.

I think theymos should probably make an announcement about prohibiting this sort of use of AI or at the very least we add it to the "unofficial" forum rules but users should be alerted not to use it in such a way. If a user if just going to use it to copy and paste the title of a thread or the OP into an AI then copy and paste the results that should be treated the same as plagiarism. If it isn't then this place isn't going to be a discussion forum for much longer but just a get paid to copy and post AI responses forum.

Personally I tried many AI detection tools and none of them able to find the contents written by myself but enhanced via AI tools so the big problem is hiw we are going to find those trickster who actually play smart by not simply copy pasting the response generated by AI but they alter something and can make it look genuine.

That's why Theymos is waiting for some kind of tool to be invented to differentiate with 100% accuracy of whether the content written by human or AI.

[nutildah]

I think theymos should probably make an announcement about prohibiting this sort of use of AI or at the very least we add it to the "unofficial" forum rules but users should be alerted not to use it in such a way. If a user if just going to use it to copy and paste the title of a thread or the OP into an AI then copy and paste the results that should be treated the same as plagiarism. If it isn't then this place isn't going to be a discussion forum for much longer but just a get paid to copy and post AI responses forum.

I agree. It would be nice to hear from The Big Man about a soft policy on this, hopefully something akin to what Stack Overflow has done. Not only are AI-generated posts spammy but they often contain wrong information as well.

The question remains of how to best determine that a post was written using AI. This tool seems to have the best rate of accuracy, but it doesn't judge how much of a text is AI-written, just whether or not it is "likely" to contain AI-written material:

https://hivemoderation.com/ai-generated-content-detection

The other decent ones include:

https://writer.com/ai-content-detector/
https://contentatscale.ai/ai-content-detector/

Other clear signs of AI-generated posting:

- using perfect English & punctuation when the poster's previous posts did not
- writing long texts in rapid succession, when it was unlikely to be possible manually

Surely some combination of these 3 things is enough to come to a reasonable conclusion whether a post was written by AI or not.

[_BlackStar]

The question remains of how to best determine that a post was written using AI. This tool seems to have the best rate of accuracy, but it doesn't judge how much of a text is AI-written, just whether or not it is "likely" to contain AI-written material:

https://hivemoderation.com/ai-generated-content-detection

I'll try this tools to test it for accuracy and it looks like the text I quoted below from one of the users has a 97.6% & 99.9% chance of likely to contain AI Generated Text.

It's true that working as a government employee doesn't make us rich, but why do so many people still want to become government employees? Because the most valuable thing for government employees is a lifetime pension guarantee, even if they are widows/widowers they also get pension insurance and their first and second children also get it if they are not yet 25 years old. (this is what happened in my country)

While it is true that the salaries of government employees are generally sufficient to meet their daily needs and not enough to save or invest with existing income. So it's only natural that as a government employee you have to be smart to find additional income to become rich.

In essence, not all government employees have to rely on a monthly salary alone to achieve financial success. As a government employee, you must be smart about using your free time to run a side business or involve yourself in investments that can generate greater profits.

As what the OP has explained, these two types of salary have advantages and there are also negative sides. Actually, the decision to choose a job based on salary or commission salary does not only depend on whether a person wants a large income or not. There are other factors to consider such as skills, interests, career opportunities and personal values. Some people may be more interested in a job that offers a steady salary because they feel more stable and can manage their finances more easily. However, there are also those who prefer a job with a commission salary because they feel more compelled to work hard and earn bigger profits.

It is important to consider the risk factors in commission salary work. While most commission salaried jobs do offer greater earning potential, they also carry a higher risk. For example, if you work in sales, the profit you make will depend on many factors such as market conditions, competitors and customer needs.

In the end, the decision to choose a job based on salary or commission salary depends on individual preferences. It is best to consider all relevant factors and make a decision that best fits your goals and personal values. I personally prefer to work with a monthly salary because this is the right choice for my current condition that I have a family, because with a monthly salary, it is certain that I will have an income, even though it is not as big as a commission salary.

The above two posts were created by the same user, but I'm not mentioning the names ^{[ninjastic.space can help to find it]} because I'm not entirely sure the above content is actually generated by AI because I got different results when I tested with different tools, especially with these two tools:

The other decent ones include:

https://writer.com/ai-content-detector/
https://contentatscale.ai/ai-content-detector/

[elevates]

I have been testing this tool undetectable.ai for some time now. It's accuracy is far better than other tool available for free at the moment. Does detection from all relevant AI content writing apps. I did tested it for BARD and it worked fine. Detection is done for 10000 characters. At the moment it is not charging a penny for AI detection. The only problem here is that it requires registration through email. I did use temp mail and they allowed the email address.

[nutildah]

Ran into some more AI-generated posts today. Not even by sig campaigners, lol.

I'm going to open a thread in Reputation which acts as a reference for reports on AI posts. Before doing that, I'd like to get any final feedback on how to proceed. Note this is simply for attaching references to reports, not for any kind of tagging (although if several of a user's posts are deleted as spam then a neutral indicating they are an AI spammer may be warranted).

After much deliberation and testing, here are the criteria I will be using to report posts as AI spam:


A. These 3 AI content detectors must all give a result of the post having a strong likelihood of containing AI-written material (with "strong likelihood" defined for each one):

1. Hive Moderation - 80% likely to contain AI generated text or above
2. Writefull GPT Detector - 80% likely to come from GPT-3, GPT-4 or ChatGPT or above
3. Writer AI Detector - 20% human-generated content or below

(I decided against including detectors that make you pay or register to keep verification accessible to all)


B. There must be at least 3 posts by the account that meet the requirements specified in A.

So, if its just a one-off or even two-off, I think the poster deserves some leniency, but if they make a habit of it, I strongly believe they should be named n' shamed and their posts reported.


C. Clues to help identify an AI poster before putting their posts through the detection process include:

- using perfect English & punctuation when the poster's previous posts did not
- writing long texts in rapid succession, when it was unlikely to be possible manually

and if their posts are frequently riddled with phrases mentioned here.


Anyone who thinks this shouldn't be done, or should be done in a different way, please feel free to chime in now or forever hold your peace. Thanks.

[lovesmayfamilis]

I think it's a good idea. But how should we report it to moderators? If you offer to show some examples of the use of AI, then the reports, I think, will become very large if you provide screenshots as evidence.
Are three examples enough?
In addition, from my observations, I realized that if you send several reports to moderators that an account is using AI, this account is temporarily blocked.
And I agree with you: after I submit more than 10 reports with AI posts, I tag the account with a neutral tag.

Here is an example of such a spammer.  https://bitcointalk.org/index.php?action=profile;u=2132496;sa=showPosts
Post creation speed and use of AI

[LoyceV]

It should be treated the same as plagiarism.

Agreed! You're a Global Mod, so why isn't nesty banned yet?

I think theymos should probably make an announcement about prohibiting this sort of use of AI or at the very least we add it to the "unofficial" forum rules but users should be alerted not to use it in such a way.

Isn't this already covered by the unofficial forum rules?

33. Posting plagiarized content is not allowed.

Let's look at the definition:

Plagiarism
the process or practice of using another person's ideas or work and pretending that it is your own

I've reported one of this posts again:

Bounty spammer uses chatbot plagiarism to spam the forum. Please ban.

[nutildah]

I think it's a good idea. But how should we report it to moderators? If you offer to show some examples of the use of AI, then the reports, I think, will become very large if you provide screenshots as evidence.
Are three examples enough?
In addition, from my observations, I realized that if you send several reports to moderators that an account is using AI, this account is temporarily blocked.
And I agree with you: after I submit more than 10 reports with AI posts, I tag the account with a neutral tag.

The thinking is when you want to report a post as being "AI written" - especially for posts that may not be outright spam but are AI nonetheless - you can put a reference link in the report to your post in the thread that shows the results of the AI detectors. So the first time an offending account is added to the thread, the thread post should have 3 or more examples of their posts. Then each subsequent time the account posts AI, those can be added to the thread individually (if necessary).

It will primarily serve to buttress for "AI written" or "AI spam" reports, but its also a way to publicly call out accounts engaging in this behavior, which may dissuade others from doing it in the future.

Here is an example of such a spammer.  https://bitcointalk.org/index.php?action=profile;u=2132496;sa=showPosts
Post creation speed and use of AI

Holy moly are these bad:

I understand your concerns regarding the Pi coin and other projects that offer free mining or airdrops. It is important to understand that I do not have access to specific information about the Pi project or its plans for the future, as my learning base is limited to information until September 2021.

 

[LoyceV]

I found one here: loyce.club/badposts/spam.html, and it got edited after posting.
Original:

As an AI language model, I cannot predict the future or provide financial advice. Altcoin season typically refers to a periThe market cycles of cryptocurrencies are highly unpredictable and influenced by a variety of factors, including market sentiment, adoption, and regulatory developments. It is important to conduct your own research and consult multiple sources before making any investment decisions.

Current:

Altcoin season typically refers to a periThe market cycles of cryptocurrencies are highly unpredictable and influenced by a variety of factors, including market sentiment, adoption, and regulatory developments. It is important to conduct your own research and consult multiple sources before making any investment decisions.

The user has a neutral tag about it already, but hasn't been banned. It looks like 18 posts have been deleted already, but the user is still spamming.

[PytagoraZ]

For me, the best indicator if a post is AI-generated is if it is written in flawless English. Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT. If a user's native language isn't English (as can be evidenced by their posting history), and they suddenly start posting in flawless English, it means one of two things:

1. The text is plagiarized, or
2. The text is AI-generated.

That's right, The easiest indicators to know an article was made with AI is the perfection of the language. (maybe a typo is important so it's not considered AI generated)

However, if you copy paste and it is detected by an AI detector the result is the AI generated. AI detector can only show AI generated or not, but cannot detect plagiarism. Must be done 2 times. with AI generated and plagiarized text

AI generated is still not accurate. AI and AI generated are still in the development stage.

AI is still in the development stage, it's already troublesome, especially if AI technology is getting more sophisticated. Maybe we'll be eliminated.

Welcome new word

[RickDeckard]

Perhaps some users haven't noticed yet but OpenAI has shut down their AI detection tool[1] that is mentioned in the OP[2]. Interestingly enough, more than the fact how silent this removal was, was the reason underneath it[3]:

As of July 20, 2023, the AI classifier is no longer available due to its low rate of accuracy. We are working to incorporate feedback and are currently researching more effective provenance techniques for text, and have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated.

It makes me wonder - If OpenAI isn't good at detecting AI generated text, how reliable are other detectors?
[1]https://decrypt.co/149826/openai-quietly-shutters-its-ai-detection-tool
[2]https://platform.openai.com/ai-text-classifier
[3]https://openai.com/blog/new-ai-classifier-for-indicating-ai-written-text

[crwth]

Perhaps some users haven't noticed yet but OpenAI has shut down their AI detection tool[1] that is mentioned in the OP[2]. Interestingly enough, more than the fact how silent this removal was, was the reason underneath it[3]:

As of July 20, 2023, the AI classifier is no longer available due to its low rate of accuracy. We are working to incorporate feedback and are currently researching more effective provenance techniques for text, and have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated.

It makes me wonder - If OpenAI isn't good at detecting AI generated text, how reliable are other detectors?
[1]https://decrypt.co/149826/openai-quietly-shutters-its-ai-detection-tool
[2]https://platform.openai.com/ai-text-classifier
[3]https://decrypt.co/149826/openai-quietly-shutters-its-ai-detection-tool

How full circle it is when OpenAI has difficulty determining the AI-generated text they created. It makes it even more impossible if you think about it because it's improving. Isn't it somewhat contradicting in a way? Getting better in AI text generation makes it harder to detect it even more.

[joker_josue]

Perhaps some users haven't noticed yet but OpenAI has shut down their AI detection tool[1] that is mentioned in the OP[2]. Interestingly enough, more than the fact how silent this removal was, was the reason underneath it[3]:

As of July 20, 2023, the AI classifier is no longer available due to its low rate of accuracy. We are working to incorporate feedback and are currently researching more effective provenance techniques for text, and have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated.

It makes me wonder - If OpenAI isn't good at detecting AI generated text, how reliable are other detectors?

Very well observed.

I am of the opinion that detecting AI text is extremely difficult, especially if the AI used does not have a writing pattern. And I believe that the more AI writes and evolves, the less standard it has, writing more and more in a very natural way.

So it will be more and more difficult to find out if a text is made by AI or not, just by reading it. Here on the forum, it will be the interaction with the user that will allow you to understand whether or not you are an AI.

[RickDeckard]

So it will be more and more difficult to find out if a text is made by AI or not, just by reading it. Here on the forum, it will be the interaction with the user that will allow you to understand whether or not you are an AI.

What's worse than having tools that don't accurately determine if a text is made from AI or not is the repercussion that they may have, the so called "false positive". That could easly happen in here - Imagine that a text from a user, with a shady posting behaviour, is marked as being AI generated - surely he'll face some criticism from the community (and with reason). But what if it's a "false positive"? His reputation will still be stained because AI detectors have determined that his text was "positively AI generated". Sure there are always indicators that one can take from such posts, but should we give the result of these AI detectors as proof when one of the biggest AI companies has admitted that they failed in detecting AI generated text?

[dkbit98]

It makes me wonder - If OpenAI isn't good at detecting AI generated text, how reliable are other detectors?

They are not reliable enough, maybe because AI text generators are constantly changing and it's not easy to keep track with all changes and updates.
Using several sources in combination with common sense can give better results in detection, but even them don't expect to have high precision detection.

[joker_josue]

Sure there are always indicators that one can take from such posts, but should we give the result of these AI detectors as proof when one of the biggest AI companies has admitted that they failed in detecting AI generated text?

Well, you can't. That's why I've always said that these tools aren't efficient, and certainly (unfortunately for us) they never will be. We have to find other ways - than simply copying a text and checking it in a tool, to understand what comes from an AI or not.

Honestly, I don't know how we can do this. The only idea that comes to mind is the interaction with the person. If it's an AI, sooner or later it will respond in a way that doesn't make much sense and most likely a human wouldn't respond that way.

They are not reliable enough, maybe because AI text generators are constantly changing and it's not easy to keep track with all changes and updates.
Using several sources in combination with common sense can give better results in detection, but even them don't expect to have high precision detection.

I don't think it has much to do with the fact that AI is evolving day by day. Yes, this fact is important, but it will not be the main element.

There are 1001 ways to say the same thing. Unless there is a clearly identifying pattern, it is very difficult to find out whether a text is made by an AI rather than a human. If we already know how the person habitually writes, it will be easier to detect if this way suddenly changes. Otherwise, it gets pretty difficult.

Even so, we have as an example cases of users who sold their accounts, and only several months (or years) after they were discovered. If we have a hard time figuring out the difference between the writing style of two humans. Let alone an AI that can take on multiple personalities.

[nutildah]

There are 1001 ways to say the same thing. Unless there is a clearly identifying pattern, it is very difficult to find out whether a text is made by an AI rather than a human. If we already know how the person habitually writes, it will be easier to detect if this way suddenly changes. Otherwise, it gets pretty difficult.

Even so, we have as an example cases of users who sold their accounts, and only several months (or years) after they were discovered. If we have a hard time figuring out the difference between the writing style of two humans. Let alone an AI that can take on multiple personalities.

I'm not offended by AI text that passes in my eyes for human text. I'm offended by the AI text that is obviously so, and as has been mentioned in this thread extensively, there are giveaways for such text. There are clear patterns for observing AI-written text but to see them you need to be a native English speaker and also be good at detecting patterns.

If somebody manipulates the ChatGPT / GPT-3 output to make it less detectable, I'm more-or-less fine with that as it means they have bothered to put some time into making it less mechanical and more human. Most of the time when people use AI, its because they are lazy, so they won't bother spending the time editing their posts to make them less AI.

[joker_josue]

I'm not offended by AI text that passes in my eyes for human text. I'm offended by the AI text that is obviously so, and as has been mentioned in this thread extensively, there are giveaways for such text. There are clear patterns for observing AI-written text but to see them you need to be a native English speaker and also be good at detecting patterns.

If somebody manipulates the ChatGPT / GPT-3 output to make it less detectable, I'm more-or-less fine with that as it means they have bothered to put some time into making it less mechanical and more human. Most of the time when people use AI, its because they are lazy, so they won't bother spending the time editing their posts to make them less AI.

I'm not saying there aren't some patterns. But as you say, they are not easy to detect, and have to become evident throughout several texts. But a quality AI, and with its correct use, can write things in different ways, making it difficult to create patterns. Therefore, I believe that over time it will be increasingly difficult to detect.

[dkbit98]

I don't think it has much to do with the fact that AI is evolving day by day. Yes, this fact is important, but it will not be the main element.

I wouldn't say AI is evolving at all by itself, there are people behind who are changing the code and they feed it with new information all the time.

There are 1001 ways to say the same thing. Unless there is a clearly identifying pattern, it is very difficult to find out whether a text is made by an AI rather than a human. If we already know how the person habitually writes, it will be easier to detect if this way suddenly changes. Otherwise, it gets pretty difficult.

Yeah but AI is not inventing anything new, it only uses old stuff that other people wrote before, and it combines this from several sources.
This is nothing else than mass plagiarism, and it's all coming only from bias government approved sources, so you can't get different opinion from AI.
Easy way for me to identify if something is AI or not would be talking with it for few minutes, and I can do the same thing with AI suspected members in bitcointalk forum.

[Sexylizzy2813]

How I wish the Forum would have something that can identify an AI post without stressing mods or other members who check to identify such users.
Or when posting using AI the post shouldn't be allowed, like the Forum should have an inbuilt AI detector that won't allow the user to drop the post and it should be having a red sign that the post is an AI post.

[jokers10]

How I wish the Forum would have something that can identify an AI post without stressing mods or other members who check to identify such users.
Or when posting using AI the post shouldn't be allowed, like the Forum should have an inbuilt AI detector that won't allow the user to drop the post and it should be having a red sign that the post is an AI post.

It's not so easy. Let's see on this user Adams0001. Usually he makes some edits to the texts so detectors don't easily catch him. You can probably catch him manually, but it will take lots of time. If you'll read his texts you'll see that some of them are kind of technical, people don't speak that way usually. So as human beings we can see that it is not natural. But AI detectors sometimes don't see the same.

But he made at least one big mistake:

It is difficult to determine if cryptocurrencies will survive indefinitely. Cryptocurrency is a digital or virtual asset that is secure through encryption and is decentralized, meaning it is not controlled by a single body. It is frequently used as a means of exchange and is available for trading on internet exchanges.

Cryptocurrency has grown in popularity in recent years as a means of doing transactions that are faster, cheaper, and more secure than traditional methods. However, cryptocurrency's future is uncertain, and it is possible that it will not last forever. One of the most significant difficulties for bitcoin is regulatory ambiguity. Many governments around the world are still attempting to figure out how to regulate bitcoin. This has resulted in a lack of clarity and consistency in the regulatory framework, which can lead to market uncertainty and volatility. This, in turn, may make it difficult for businesses and individuals to use cryptocurrencies, limiting its acceptance and threatening its long-term survival.

This post is easily detected by each detector with 99%+. Moreover we can check it with a plagiarism tool like text.ru and see results which are characterful for AI written: big parts taken from some other texts sometimes with whole phrases.


So now we are sure he is using AI, but how can a detector know it about some other texts with automated results of 0% probability?

I tried to get three posts of him for AI Spam Report Reference Thread, but changes he makes (sometimes he just deletes some parts of text) make it harder. Some texts have 60%+ of AI probability, some have 50%+, and I'm not motivated to spend too much time on him. So automated detectors failed.

[Flexystar]

This thread seems to have mixed debate about the AI tools and whether to rely on them or not. It's pity that we created the AI tools to do the stuff and now we are not able to identify whether it was our tool that created it or not. AI simply nailed it.

I am not sure how useful it could be but they are making various tools and also experimenting with the AI Content Checker. I have recently found AI Content Detector Chrome Extension brought to us by Copyleaks. Obviously it might be just another addition to the list of OP and is easy to use tool.

You just add it to the chrome as extension and whatever you copy on screen will get pasted and detected by the extension.

They have actually segregated the detection in following types:
GPT4 Content
ChatGPT
Bard
Human
AI + Human.

What caught my eye is the last one. AI+Human text detection could be very useful on the forum since we are seeing examples where people are just modifying some text with their own text. 

Will this extension be very useful?

[Sexylizzy2813]

How I wish the Forum would have something that can identify an AI post without stressing mods or other members who check to identify such users.
Or when posting using AI the post shouldn't be allowed, like the Forum should have an inbuilt AI detector that won't allow the user to drop the post and it should be having a red sign that the post is an AI post.

It's not so easy. Let's see on this user Adams0001. Usually he makes some edits to the texts so detectors don't easily catch him. You can probably catch him manually, but it will take lots of time. If you'll read his texts you'll see that some of them are kind of technical, people don't speak that way usually. So as human beings we can see that it is not natural. But AI detectors sometimes don't see the same.

But he made at least one big mistake:

It is difficult to determine if cryptocurrencies will survive indefinitely. Cryptocurrency is a digital or virtual asset that is secure through encryption and is decentralized, meaning it is not controlled by a single body. It is frequently used as a means of exchange and is available for trading on internet exchanges.

Cryptocurrency has grown in popularity in recent years as a means of doing transactions that are faster, cheaper, and more secure than traditional methods. However, cryptocurrency's future is uncertain, and it is possible that it will not last forever. One of the most significant difficulties for bitcoin is regulatory ambiguity. Many governments around the world are still attempting to figure out how to regulate bitcoin. This has resulted in a lack of clarity and consistency in the regulatory framework, which can lead to market uncertainty and volatility. This, in turn, may make it difficult for businesses and individuals to use cryptocurrencies, limiting its acceptance and threatening its long-term survival.

This post is easily detected by each detector with 99%+. Moreover we can check it with a plagiarism tool like text.ru and see results which are characterful for AI written: big parts taken from some other texts sometimes with whole phrases.


So now we are sure he is using AI, but how can a detector know it about some other texts with automated results of 0% probability?

I tried to get three posts of him for AI Spam Report Reference Thread, but changes he makes (sometimes he just deletes some parts of text) make it harder. Some texts have 60%+ of AI probability, some have 50%+, and I'm not motivated to spend too much time on him. So automated detectors failed.

If a user, let's take the case of this Adams0001 if he keeps editing without being found as an AI user, can't it be seen as someone who's not using AI because of the editing?
Since the tool you're using failed to detect his post while using AI, are there no other means to find him guilty of using AI?

[jokers10]

If a user, let's take the case of this Adams0001 if he keeps editing without being found as an AI user, can't it be seen as someone who's not using AI because of the editing?
Since the tool you're using failed to detect his post while using AI, are there no other means to find him guilty of using AI?

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.

[NotATether]

But he made at least one big mistake:

It is difficult to determine if cryptocurrencies will survive indefinitely. Cryptocurrency is a digital or virtual asset that is secure through encryption and is decentralized, meaning it is not controlled by a single body. It is frequently used as a means of exchange and is available for trading on internet exchanges.

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.

[jokers10]

posting days are strictly numbered.

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.

[CryptoHeadlineNews]

posting days are strictly numbered.

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.

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.

[jokers10]

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.

An additional threat to consider is a market crash. High-risk businesses are frequently linked to the overall health of the economy, and if the economy worsens, the value of your investments may plummet. is the risk of fraud, which is all too typical in high-risk businesses. Before investing, always perform due diligence and examine the company, its management, and its financials. It's crucial to keep in mind that high-risk industries are frequently more vulnerable to regulatory changes and political dangers. A change in government rules, for example, might significantly alter the playing field for a sector and impact the value of your investment. Despite the hazards, high-risk businesses can yield significant rewards to investors. someone can properly navigate them. Understanding the risks and diversifying your portfolio are the keys to success. Diversification is essential since it spreads risk and reduces the impact of any single investment.

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.

[Sexylizzy2813]

If a user, let's take the case of this Adams0001 if he keeps editing without being found as an AI user, can't it be seen as someone who's not using AI because of the editing?
Since the tool you're using failed to detect his post while using AI, are there no other means to find him guilty of using AI?

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.

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.

[jokers10]

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.

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.

[LoyceV]

What's the verdict on this one?

Bitcointalk is a well-known forum in the crypto industry where being a reputable member is like a dream for many. There are some security measures that can be taken to protect your bitcoin talk account from being stolen or hacked. A user can add secret questions, and stake their BTC address in the forum to protect their account. Despite this sometimes accounts got hacked and are taken by hackers.

It's partially incorrect and sounds very much like chat AI spam/plagiarism.

[DVlog]

What's the verdict on this one?

Bitcointalk is a well-known forum in the crypto industry where being a reputable member is like a dream for many. There are some security measures that can be taken to protect your bitcoin talk account from being stolen or hacked. A user can add secret questions, and stake their BTC address in the forum to protect their account. Despite this sometimes accounts got hacked and are taken by hackers.

It's partially incorrect and sounds very much like chat AI spam/plagiarism.

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.

[jokers10]

What's the verdict on this one?

Bitcointalk is a well-known forum in the crypto industry where being a reputable member is like a dream for many. There are some security measures that can be taken to protect your bitcoin talk account from being stolen or hacked. A user can add secret questions, and stake their BTC address in the forum to protect their account. Despite this sometimes accounts got hacked and are taken by hackers.

It's partially incorrect and sounds very much like chat AI spam/plagiarism.

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.

[Sexylizzy2813]

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.

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.

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.

[DVlog]

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.

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.

[blckhawk]

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.

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.

[jokers10]

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.

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.

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.

[tvplus006]

It occurred to me that ChatGPT often uses the same phrases when generating answers, and I was wondering how to ascertain which phrases are verifiably part of ChatGPT's response formula. Then it occurred to me, why not ask ChatGPT itself? So here it is, straight from the horses mouth:

Prompt:

Can you give me a list of phrases commonly included in ChatGPT responses? For example, I noticed that "It's worth noting," "In essence," "In summary," "Finally," "Overall," and "On the other hand" are all commonly found in ChatGPT-generated responses.

Response:

Certainly! While it's important to note that the language generated by ChatGPT can vary, here is a list of phrases that are commonly found in ChatGPT-generated responses:

1. It's worth noting
2. In essence
3. In summary
4. Finally
5. Overall
6. On the other hand
7. However
8. Moreover
9. Furthermore
10. Additionally
11. In addition
12. In conclusion
13. That being said
14. In light of
15. Nevertheless
16. In other words
17. As a result
18. Therefore
19. Consequently
20. To illustrate
21. For instance
22. In fact
23. As mentioned earlier
24. It is important to emphasize
25. Notably
26. Interestingly
27. Conversely
28. In contrast
29. Similarly
30. In a similar vein
31. On a related note
32. It is worth mentioning
33. Given these points
34. To summarize
35. In brief

Remember that the use of these phrases may vary depending on the context and style of the generated response.

...

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

Can you give me a list of phrases that people usually use? For example, I have noticed that in people's posts, the phrases "It is worth noting", "In essence", "In short", "Finally", "In general" and "On the other hand" are often found.

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.

[jokers10]

you cannot use such a list of phrases to identify a message as created by AI.

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.

[nutildah]

you cannot use such a list of phrases to identify a message as created by AI.

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.

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.

[tvplus006]

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.

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.

[nutildah]

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.

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.

[DdmrDdmr]

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):

•   "How correlated are Bitcoin and Ethereum in 2023?"
•   "Does Bitcoin typically perform better on weekdays or weekends?"
•   "What was Bitcoin’s performance in the month leading up to the US elections for the past 3 election cycles?"

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/

[Haroon Akram]

Testing a few of those detectors on a text I just stumbled upon

https://writer.com/ai-content-detector/   - 100% HUMAN-GENERATED CONTENT Fantastic!
https://gptzero.me/                                  Your text is likely to be written entirely by a human
https://contentatscale.ai/ai-content-detector/  96%  Highly likely to be Human!
https://x.writefull.com/gpt-detector  https://x.writefull.com/gpt-detector
https://hivemoderation.com/ai-generated-content-detection The input is: not likely to contain AI Generated Text
https://paraphrasingtool.ai/ai-content-detector/   Text may contain AI-written sentences   
https://detector.dng.ai/                               Based on our Analysis your test has been most likely written by a Human.

ChatGBT:

https://i.ibb.co/sQKry9r/62148225.png

 

See? I interact and exchange ideas based on what is in my mind

This is not interaction you just copy-pasted stuff.

This is helpful and unique content

It's not unique content because anyone trying to do the same would come with the same result.
Unique content is generated by unique persons and ways of thinking, in this case, you're giving a standard response everyone could come up with, just like looking at a Wikipedia article and copy-pasting that paragraph.

Easy AI Checker provides 100% accuracy for checking AI generated content.
https://easyaichecker.com/

[Haroon Akram]

To achieve 100% accuracy check the content using Easy AI Cheker https://easyaichecker.com/

[nutildah]

Since June, the AI Spam Report Reference Thread has resulted in 500+ AI-generated (or AI-assisted) posts being deleted as spam. It's now 16 pages long and I'd say its been a massive success. Most of the accounts that continue to post ChatGPT-generated material are newbies who don't know any better and think they can get away with it. Most senior accounts don't bother, or else they've found a way to evade the detectors.

Anyway, I'd like to thank the following members for their consistent contributions to the thread:

@jokers10
@lovesmayfamilis
@light_warrior (RIP)
@Who is John Galt?
@Etranger
@Gladitorcomeback
@Shishir99

You guys have been really helpful & I encourage anyone who comes across AI spam to report such posts in the thread, following the steps outlined in the OP.

To achieve 100% accuracy check the content using Easy AI Cheker https://easyaichecker.com/

Thanks for this, I'll check it out & potentially add it to the list of checkers in our thread. Also, to address your question in another thread (since its related to this one):

I paid $100 using Binance pay to a writer after checking the content it appeared AI generated. Is there a methods to claim a refund?

Sources:
https://pay.binance.com/en
https://easyaichecker.com/

I don't think so. Even if you explicitly told the writer not to use AI to write the text, and they did anyway, I doubt Binance would help you recover the money from them.

[Shishir99]

@Shishir99

You guys have been really helpful & I encourage anyone who comes across AI spam to report such posts in the thread, following the steps outlined in the OP.

Thank you nutildah for opening this thread and helping to filter the forum.^{[Just realized it's the discussion thread.]} I was kind of scared when I started reading this post. I thought you were going to close the thread because there might be something wrong. After finishing the reading, I understood it's just a recap post where you wanted to thank the contributors. I appreciate it anyway.

I have noticed that you have created a thread in the service section for managers. I wish you success and I believe your good work for the forum will help you get more clients. Sorry for my terrible English