I just wanted to share some statistics I gathered today after analyzing the entire AI Spam Report Reference Thread. Seems like our methodology has been fairly effective thus far as at least 62% of all accounts determined to have been using ChatGPT or another AI bot are no longer with us.
- 106 reported accounts still active or semi-active
- 11 accounts active with a red trust
- 118 accounts inactive
- 14 accounts inactive with a red trust
- 65 accounts banned
Several of the still-active accounts haven't posted in the last 1-3 months, and they will fall into "inactive" status shortly.
Topic: AI-generated post discussion thread: how to identify & report (Read 2717 times)
December 11, 2023, 07:21:45 AM
@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.
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
December 10, 2023, 06:47:20 AM
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.
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 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.
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/
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.
December 10, 2023, 06:29:00 AM
To achieve 100% accuracy check the content using Easy AI Cheker https://easyaichecker.com/
December 10, 2023, 06:21:48 AM
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
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.
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/
October 11, 2023, 02:15:40 PM
This is an interesting twist in terms of crypto related content that ChatGPT Plus can now generate. ChatGPT Plus, the version that works on a dataset that surpasses September 2021, and that has apparently moved on to include web browsing capabilities, can now connect to a plugin created by CoinMarketCap to interact with all their crypto related datasets.
The above, theoretically, gives ChatGPT better capacity to reference near real-time data, which can be used by some to further trick their way around here, citing real and recent data whilst not really having a clue themselves.
These are some of the examples that CoinMarketCap claims the combination can now respond to (although these examples do not strictly relate to close to or real time data):
See:
https://cointelegraph.com/news/coinmarketcap-launches-chatgpt-plugin
https://chainwire.org/2023/10/11/coinmarketcap-provides-a-personal-crypto-analyst-for-all-with-new-chatgpt-plugin/
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):
Quote
• "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?"
• "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/
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.
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.
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.
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.
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.
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:
Response:
Prompt:
Quote
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:
Quote
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.
...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:
Quote
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.
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.
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. 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.
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.
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.
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.
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.
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. 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.
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.
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?
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.
Jump to: