Pages:
Author

Topic: AI-generated post discussion thread: how to identify & report - page 3. (Read 2717 times)

legendary
Activity: 3010
Merit: 8114
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://bitcointalksearch.org/user/miner1448-2132496
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.

 Cheesy
legendary
Activity: 3290
Merit: 16489
Thick-Skinned Gang Leader and Golden Feather 2021
It should be treated the same as plagiarism.
Agreed! You're a Global Mod, so why isn't nesty banned yet?

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:
Quote
Bounty spammer uses chatbot plagiarism to spam the forum. Please ban.
legendary
Activity: 2072
Merit: 4265
✿♥‿♥✿
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://bitcointalksearch.org/user/miner1448-2132496
Post creation speed and use of AI

legendary
Activity: 3010
Merit: 8114
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.
sr. member
Activity: 756
Merit: 390
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.
legendary
Activity: 1064
Merit: 1228
Playgram - The Telegram Casino
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.

Quote
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.
Quote
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:

Quote
legendary
Activity: 3010
Merit: 8114
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.
hero member
Activity: 2366
Merit: 793
Bitcoin = Financial freedom
.
.
.

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.
jr. member
Activity: 56
Merit: 19
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.

global moderator
Activity: 4018
Merit: 2728
Join the world-leading crypto sportsbook NOW!
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://bitcointalksearch.org/user/nesty-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.
legendary
Activity: 1862
Merit: 5154
**In BTC since 2013**
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.
legendary
Activity: 3010
Merit: 8114
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:
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.

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.
legendary
Activity: 3010
Merit: 8114
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.
jr. member
Activity: 56
Merit: 19
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://bitcointalksearch.org/topic/m.62129192) 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.
legendary
Activity: 2072
Merit: 4265
✿♥‿♥✿
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


full member
Activity: 1092
Merit: 227
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?  Grin

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.  Smiley

***
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.
legendary
Activity: 2576
Merit: 1655
Another AI generated post, here. archived

But the thing is that somewhat is it being hide under the pretense of a Poll.  Wink
jr. member
Activity: 56
Merit: 19
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.
legendary
Activity: 3010
Merit: 8114
So, does this mean that we have a situation where chatGPT was caught both plagiarizing and lying about its claim?  Grin

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:

Quote
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.

 Huh

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:

Quote
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."
hero member
Activity: 882
Merit: 792
Watch Bitcoin Documentary - https://t.ly/v0Nim
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:
Quote
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.
Pages:
Jump to: