The J.A.R.V.I.S AutoReply Protocol Initiative (JARPI) - Powered by ChatGPT

[NotATether]

JARPI (J.A.R.V.I.S AutoReply Protocol Initiative) is the name of a system I'm designing to automatically reply to low-quality, repetitive Bitcoin questions that the community is tired of regurgitating. This project is meant to demonstrate the positive impact that AI can have on Bitcointalk when it is used correctly.

Posts are directly pasted into OpenAI's ChatGPT (manually), and the answer is screened manually, and then automatically copied and used to reply to a bitcointalk thread.

It is powered by my shiny new toy, J.A.R.V.I.S. I found a way to defeat Cloudflare's captchas using Selenium and solving them manually, so this opens the door to a lot of interesting possibilities.

Jarvis text will always be italicized (sorry, not underlined - that was a mistake) and in grey, and have the following disclaimer at the bottom:

Code:

This reply was auto-generated by [url=https://bitcointalk.org/index.php?topic=5449279.0]JARPI[/url], an AI protocol created by [url=https://bitcointalk.org/index.php?action=profile;u=2739424]NotATether[/url] for automatically replying to frequentlyasked questions.

Some other useful things that JARPI can do (theoretically), including things that don't even utilize AI:

- It can make a reply on newly created spamvertising topics alerting users that the content is spam and telling them to use the "Report to moderator" feature to remove the entire topic (because lets face it, we humans are being collectively outgunned in this area).
- Similarly, for malware posts.
- Ditto, for obvious scam attempts such as Bitcoin doubler, bitcoin mining exploit, and so on.
- It can tell a user when a thread belong in the wrong board and prompt them to move it to the correct board, with a short instruction.
- It can alert users when they are multi-posting (most likely 3+) and tell them to place all replies in one post, linking to the relevant Bitcointalk rule.
- Depending on the plagiarism tools available, it can alert a user when a post risks being classified as plagiarism and tell them to provide a link to the source material - reducing the number of ban appeal threads of people who did not know this was a rule.

Limitations:

- JARPI cannot create new topics.
- JARPI cannot quote-reply (yet).
- J.A.R.V.I.S is a newbie account and thus currently has the same restrictions as other newbie accounts.
- JARPI will not post on local boards, or on English boards where it makes no sense to ask a Bitcoin question there (e.g. News, Gambling, Marketplace > Goods).

Roadmap:

- Currently there is a single sample reply that is hardcoded in the script. Work is underway to allow any arbitrary reply to be passed. Done
- Apply aforementioned BBcode and footer. Done
- Prompt the operator for a thread ID to make the reply on.
- Allow the operator to insert any quote using a quote ID that is in the BBcode.


Examples of how JARPI can place high-quality answers on common questions:

there are many threads and news about people losing access to their wallets and forgetting or seed phrases,
and it's better for scarcity of bitcoin,  but how can we know or speculate that the wallet is lost, and it is out of the supply? is there any platform where we can find lost wallets, if no, then it's a good idea to start a website and list every lost wallets.

ChatGPT's reply:

While it's true that there are many stories of people losing access to their cryptocurrency wallets and forgetting their recovery phrases or private keys, there is no way to know for sure if a particular wallet is lost or not. The nature of cryptocurrency means that wallets can be created and used anonymously, and it's impossible to track all wallets and their associated recovery phrases or private keys.

There is no platform or website that lists lost wallets because the privacy and security of cryptocurrency users are paramount, and it would be unethical to share information about lost wallets without the owner's consent. Furthermore, lost wallets could be the result of malicious actors stealing private keys or recovery phrases, and it would be inappropriate to make that information public.

If you have lost access to your own wallet and are unable to recover it, your best course of action is to contact the wallet provider's support team or seek assistance from a professional cryptocurrency recovery service. These services specialize in recovering lost cryptocurrency wallets and can help you regain access to your funds. However, it's important to note that these services can be expensive and may not always be successful in recovering lost wallets. It's always important to keep your recovery phrases and private keys safe and secure to avoid the risk of losing access to your wallet in the first place.

JARPI reply (after manually cleaning up the AI-generated reply):

While it's true that there are many stories of people losing access to their cryptocurrency wallets and forgetting their recovery phrases or private keys, there is no way to know for sure if a particular wallet is lost or not. The nature of cryptocurrency means that wallets can be created and used anonymously, and it's impossible to track all wallets and their associated recovery phrases or private keys.

There is no platform or website that lists lost wallets because the privacy and security of cryptocurrency users are paramount, and it would be unethical to share information about lost wallets without the owner's consent. Furthermore, lost wallets could be the result of malicious actors stealing private keys or recovery phrases, and it would be inappropriate to make that information public.

Furthermore, bitcoins can only be placed out of circulation if they are provably lost, such as being spent with an OP_RETURN script, or unclaimed coinbase rewards.

Keep in mind that the basic idea is for the reply to be as correct as possible, so in this case, replies from other parts of the thread could also be put inside the blender, and irrelevant parts of ChatGPT answers are shaved off.


Tips: Send them to bc1q4djl6pxt90nfs8fufdul26ufxukxxrczsfjj0h

[Little Mouse]

Would we really appreciate if someone was using AI to respond on the forum? In my opinion, no. JARPI is going to do the exact thing some other people used here. The difference is JARPI is doing it as an experiment.
It's a place for discussion, interact one with another. I don't think it's going to serve the purpose of a forum. Also, have you asked admin whether you can use it or not? I haven't seen any exact rule on AI written post but I think it will be forbidden when the unofficial rules of official bitcointalk forum will be re-written.

[NotATether]

Would we really appreciate if someone was using AI to respond on the forum? In my opinion, no. JARPI is going to do the exact thing some other people used here. The difference is JARPI is doing it as an experiment.
It's a place for discussion, interact one with another. I don't think it's going to serve the purpose of a forum. Also, have you asked admin whether you can use it or not? I haven't seen any exact rule on AI written post but I think it will be forbidden when the unofficial rules of official bitcointalk forum will be re-written.

Pure AI generated posts are likely to be lousy and factually incorrect. However, there should not be any problem with AI posts that are manually fact-checked by humans:

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.

(emphasis mine).

Imagine if somebody asks a question such as the following:

how to avoid telegram scams involving cryptocurrency?

Normally such questions are havens for signature spammers who otherwise do not have anything useful to contribute to the discussion. However, AI (with a few redactions or additions in the content where necessary) can make a much superior answer:

Telegram is a popular messaging app used by many in the cryptocurrency community, but it's also a platform that scammers use to deceive and defraud users. To avoid Telegram scams involving cryptocurrency, here are some tips to keep in mind:

Verify the identity of the person or group you are communicating with. Scammers often impersonate well-known figures or organizations to gain your trust. Verify their identity through official websites or social media accounts.

Don't trust giveaways or airdrops. Scammers often use the lure of free cryptocurrency to trick people into sending them money or personal information. Always be skeptical of offers that seem too good to be true.

Be cautious of unsolicited messages. Scammers may send you messages offering investment opportunities or asking for personal information. If you don't know the sender, don't engage with them.

Don't share your private keys or seed phrases. Your private keys and seed phrases are used to access your cryptocurrency wallet. Never share them with anyone, even if they claim to be a representative of a cryptocurrency project or exchange.

Use a trusted cryptocurrency wallet. Make sure you're using a reputable and secure wallet to store your cryptocurrency. Research the wallet provider before using it.

Do your own research. Always do your own research before investing in any cryptocurrency project. Don't rely solely on information provided by Telegram groups or individuals.

Report suspicious activity. If you encounter suspicious activity on Telegram, report it to the platform's support team or to the appropriate authorities.

The grey color combined with the italics enables it to stand out from the other shitposts. Although maybe, I will make it a darker shade of grey. It is also possible to fine-tune the answers from ChatGPT to precisely answer specific questions such as: "Is XYZ a scam <paste background information here>", "How to safely use metamask", "should I use a second phone number when buying bitcoin with an exchange", "How to avoid being a victim of SIM swap attacks" and so forth.

I should note that JARPI is private software and as such, only I have the ability to make the posts.


P.S. I haven't asked anyone about this yet, because I don't think anyone sees the potential for this yet (and partially because this is not bitcoin-dev mailing list where most proposals get instantly shut down or ghosted  ). Instead of wading through endless pages of posts looking for the answer to a question, you can immediately stop looking when you find a JARPI-created answer, and maybe even lock the thread at that point. In other words, JARPI reduces spam by preventing other people from paying attention to subsequent low-quality answers.

[T3PR00T]

It's not a forum related topic.

[NotATether]

It's not a forum related topic.

I don't understand your comment?


Anyway, time for a little experiment, related to one of the non-AI use cases of this robot.

In Development and Technical discussion right now, we have two spam topics, which I will call topic number 1 and 2:

Topic 1: https://bitcointalk.org/index.php?topic=5449252.0
Topic 2: https://bitcointalk.org/index.php?topic=5449249.0

In Topic 1, I have reported the thread for spam advertising. and in topic 2, I have used JARPI to request users to do the same. Both actions were taken around 11:30 UTC time.

The goal of this experiment is to see which spam thread is deleted first. If topic 2 is deleted first, then that means this use case is effective, otherwise, that means it is not effective to use auto-generated replies to ask people to report posts, and I will halt that particular usecase.

So now it is time to wait. No more using the bot during this time period.  

EDIT: They were deleted in about 70 minutes at the same time. So I don't see any particularly amazing use case for spamvertising alerts. However, malware and phishing link alerts are still important. Let's try that next.

[John Abraham]

Isn't it forbidden to post AI-Generated content? I thought it was not allowed. But as long as it's already mentioned in each post that the Post is AI generated with a source, It should be fine. But, You should talk with one of the Admins/Global Mods before you start. I read the purposes, and it seems reasonable to me. It will reply to low-quality topics only and report them if it's spam or a scam attempts. That's great.

Now I am afraid of AI's. It's going to takeover us. Once Elon Musk said AI is far more Dangerous than you think. No one hears me. People will regret doing this.

It's not a forum related topic.

I don't understand your comment?

I understand his comment. He asking why this topic is in Meta? Shouldn't it fit better in Project development? IDK. Maybe Project development is for Bitcoin related Projects only.

[Lucius]

Imagine if somebody asks a question such as the following:

how to avoid telegram scams involving cryptocurrency?

Normally such questions are havens for signature spammers who otherwise do not have anything useful to contribute to the discussion. However, AI (with a few redactions or additions in the content where necessary) can make a much superior answer:

Because of such things, we have a "report to moderator" button, and then such topics will end up in the trash and will not become havens for signature spammers. However, I have nothing against you playing with AI in that way, because it seems that there is no area in which AI has not already intervened.

[NotATether]

Isn't it forbidden to post AI-Generated content? I thought it was not allowed.

It isn't (yet):

@mprep

Considering recent discussion around this topic, is it possible that we have some clear rules surrounding the use of AI in writing posts, and in which cases it is appropriate and not appropriate to use AI in posts?

AFAIK in terms of forum policy, this assesment of mine still applies:

If an AI is able to consistently create content that doesn't break any of the forum's rules (good quality, on-topic, not just a padded word salad, no plagiarism, etc, etc), I, for one, welcome our new machine overlords. Otherwise, content that violates the rules, AI or human produced, can already be dealt with with our current rules and policies in mind.

If you want rules to be made in regards to AI posts, your going to have to petition theymos about it (e.g. make a thread requesting a change in forum policy).

I understand his comment. He asking why this topic is in Meta? Shouldn't it fit better in Project development? IDK. Maybe Project development is for Bitcoin related Projects only.

Maybe. I'll think about it. The reason I put it here is because the bot is primarily focused on the forum itself.

Because of such things, we have a "report to moderator" button, and then such topics will end up in the trash and will not become havens for signature spammers. However, I have nothing against you playing with AI in that way, because it seems that there is no area in which AI has not already intervened.

Yeah, imagine instead of having to fill in a Report to moderator form a thousand times with very similar reasons, you could just collect a list of post IDs and set it on autopilot while you sip on your morning coffee like, I don't know, @Ratimov or another large reporter.

[LoyceV]

- It can alert users when they are multi-posting (most likely 3+) and tell them to place all replies in one post, linking to the relevant Bitcointalk rule.

That would be against one of these forum rules:

2. No off-topic posts.
~
29. Sending unsolicited PMs, including but not limited to advertising and flood, is not allowed.

Depending on how you're planning to do it, those rules cover it. It's better to report those posts.

- J.A.R.V.I.S is a newbie account and thus currently has the same restrictions as other newbie accounts.

I've whitelisted it, because you (NotATether) don't need those limitations. But that doesn't mean I like it

ChatGPT's reply:

J.A.R.V.I.S is on my ignore list already. I can't get myself to read this generic AI crap. It uses far too many words to tell nothing I didn't know yet.

[NotATether]

- It can alert users when they are multi-posting (most likely 3+) and tell them to place all replies in one post, linking to the relevant Bitcointalk rule.

That would be against one of these forum rules:

2. No off-topic posts.
~
29. Sending unsolicited PMs, including but not limited to advertising and flood, is not allowed.

Depending on how you're planning to do it, those rules cover it. It's better to report those posts.

My bot cannot send PMs and I have no plans to add that feature. It is strictly limited to making replies (It cannot even start its own topics).

ChatGPT's reply:

J.A.R.V.I.S is on my ignore list already. I can't get myself to read this generic AI crap. It uses far too many words to tell nothing I didn't know yet.

The target audience that is supposed to be reading these kind of posts are not so much Legendaries like you and I as it is for new members who've just arrived here <3 months ago.

[joker_josue]

JARPI (J.A.R.V.I.S AutoReply Protocol Initiative) is the name of a system I'm designing to automatically reply to low-quality, repetitive Bitcoin questions that the community is tired of regurgitating. This project is meant to demonstrate the positive impact that AI can have on Bitcointalk when it is used correctly.

Okay, the idea is interesting.
But, I've read everyone talking about whether it's good or bad to have an AI answering a post, and no one has asked how it will end if a question is quality or not?

For me, the first thing that needs to be clarified is who defines that a question has or does not have quality, or that, because it is repeated, it cannot generate another type of debate?
Humans have many ways of writing the same thing. So how is an AI going to tell what is or is not quality?

[TryNinja]

The target audience that is supposed to be reading these kind of posts are not so much Legendaries like you and I as it is for new members who've just arrived here <3 months ago.

The "Bitcoin Discussion", "Economy" an other boards are a mess, with tens of pages full of unnecessary cycled texts. I'm sorry, but this AI will only write more of those posts. The sad fact is that no one actually reads those mega-spam-threads answering questions no one cares about.

"how to avoid telegram scams involving cryptocurrency?" - asked no one actually caring about an answer.

I can't see a newbie being "uhm, I want to know the answer", clicking on the topic, reading 10 pages of cycled bs and being "oh wow, I learned something new today".

It's more like: "uhm, I need to increase my post count/fill my bounty/signature campaign quote, let me think of a generic question for a new thread"

And then 50 other users going "I need to make 5 posts today... let me think for 2 minutes so I can answer this generic post with my generic answer and then increase my post count/fill my bounty/signature campaign quote".

Actual readers: "this is a spam-fest, heck no! I'm not reading all this crap".

Probably also putting your bot on my ignore list if I see one of those in the wild.

[Poker Player]

Well, with the mentality I see around the forum, I'm not surprised that the thread hasn't had a single merit so far and that most of the comments are negative.

Would we really appreciate if someone was using AI to respond on the forum?

If what I read brings me value, yes, but I'm not worried about being dethroned by AIs.

The most disruptive innovations were at the time not only rejected, but in some cases even mocked:

7 world-changing inventions that were ridiculed when they came out

The use of AI in everyday life will be as commonplace in a few years as the use of the Internet or cell phones is today, but we'd better focus on the negatives instead of trying to take advantage of these early versions, lol.

You guys sound like Peter Schiff or Charlie Munger criticizing Bitcoin.

[Lucius]

~snip~
You guys sound like Peter Schiff or Charlie Munger criticizing Bitcoin.

You did not refer to anyone in particular, but as I am one of those who expressed my opinion, I feel called out, so I will answer you. Personally, I consider it an insult that you put us in the same category by citing the example of those people who hate Bitcoin from the bottom of their souls because it does not fit into their business philosophies.

In general, a small percentage of people think that AI has a bad influence on the forum, and if someone wants to read AI generated posts and answers that will be given by the OP bot, I will certainly not interfere in that.

In fact, from today I will no longer clean any board (especially the Bitcoin discussion), so if AI will do it better than us humans, we will obviously have more time for some other activities.

[bullrun2024bro]

JARPI (J.A.R.V.I.S AutoReply Protocol Initiative) is the name of a system I'm designing to automatically reply to low-quality, repetitive Bitcoin questions that the community is tired of regurgitating.

Who decides if a topic is low-quality or repetitive? And who decides if the community is tired of regurgitating a topic?

Even if a question has already been asked, it can be nuanced in a way that results in a fruitful discussion where most users learn something new. I don't want an AI to ruin that with a crappy list of links where comparable topics have been addressed already. Isn't an online forum meant to be a place where real persons interact with each other? I don't want to skip or ignore several AI accounts flooding new threads with "helpful advice or guidelines how to use this forum properly".

It won't take long until other people will create additional AI bots for all kind of bullshit we don't need. In half a year we will have ten bots replying all kind of crap to new threads in the Beginners & Help section ruining that board completely.

I really hope you reconsider your idea. You won't help the community, you will destroy it.

[LoyceV]

The target audience that is supposed to be reading these kind of posts are not so much Legendaries like you and I as it is for new members who've just arrived here <3 months ago.

How many of those members have a genuine question, and how many of them are just posting to either get Merit or at least Activity? The user you took as an example in your OP (cafter) is opening topics at least 10 times faster than me, and I doubt he's really interested in the answer. If he was, he would have just Googled it. It's not as if the answers are hard to find.

Well, with the mentality I see around the forum, I'm not surprised that the thread hasn't had a single merit so far and that most of the comments are negative.

Think of it this way: first, personal human interaction was replaced by electronic communication, and now we risk ending up only talking to electronics. Call me old-fashioned, but I don't like it. If I want to interact with a computer, I'll use a Search Engine or spambot myself.

[nutildah]

I think innovative stuff like this is cool and worth trying, however I kind of agree with this:

I can't get myself to read this generic AI crap.

I'm beginning to feel the same way about AI artwork as well. It was fun at first, but now when I see it, it just evokes a feeling of "meh." Only the grotesque abominations produced by either DALL-E/Midjourney or ChatGPT are fun anymore.

How many of those members have a genuine question, and how many of them are just posting to either get Merit or at least Activity? The user you took as an example in your OP (cafter) is opening topics at least 10 times faster than me, and I doubt he's really interested in the answer. If he was, he would have just Googled it. It's not as if the answers are hard to find.

I think it would be better to make a bot that replies to shitposts with a warning letting the poster know they are shitposting. Something like:

Warning: your post appears to have been written by an NPC. This question has been asked on the forum approximately 43 times already, with the most recent merited reply being the following:

We can prove that the number of provably lost bitcoin is 2,828.654 BTC, and this number can be safely removed from both the total and the circulating supplies. Anything which is not provably lost should not be considered removed from the supply.

Consider performing a simple Google or forum search before posting a question on the forum next time. Thank you for your cooperation.

[joker_josue]

I think it would be better to make a bot that replies to shitposts with a warning letting the poster know they are shitposting. Something like:

Warning: your post appears to have been written by an NPC. This question has been asked on the forum approximately 43 times already, with the most recent merited reply being the following:

We can prove that the number of provably lost bitcoin is 2,828.654 BTC, and this number can be safely removed from both the total and the circulating supplies. Anything which is not provably lost should not be considered removed from the supply.

Consider performing a simple Google or forum search before posting a question on the forum next time. Thank you for your cooperation.

But how will the bot know if that question has been asked 1000x?
There are many ways to ask the same question without repeating yourself, so it's nearly impossible for the system itself to know it's the exact same question.

And what guarantee is there that a question that has already been asked 100x cannot generate a very interesting and instructive debate?
There is a way to answer some questions, from different perspectives that might be interesting and helpful.

I agree with @bullrun2020bro.

I don't think the OP idea is unreasonable, but I think it would be too complicated to put all the possible variables so as not to penalize anyone.

[Little Mouse]

Would we really appreciate if someone was using AI to respond on the forum?

If what I read brings me value, yes, but I'm not worried about being dethroned by AIs.

AIs are a great help and innovation, there's no doubt. But in my opinion, what OP's BOT is offering is something a shitpost reply to the shit posters. I don't know how people would enjoy reading their reply. Well, personally I would simply put such bot on ignore list like few other mentioned but if you are going to enjoy reading them, feel free to read, enjoy and interact with them. You are appreciating something doesn't necessarily mean everyone has to appreciate that. People may have different opinion and expressing them doesn't make them negative. What negativity is bringing no one merited the post and mentality of the forum users. I don't see a reason to bring such issue.

[SirJohnVonSlotty]

The target audience that is supposed to be reading these kind of posts are not so much Legendaries like you and I as it is for new members who've just arrived here <3 months ago.

It's still generic AI crap. Right now I'm struggling with a bunch of my writers because they think that AI content sounds interesting, it doesn't. There's no emotion, just mathematically correct sentences with a lot of words to explain something that could be explained with five bulletpoints. Reminds me of answers that politicians usually give.

I don't want to belittle your project, I think that AI-driven systems are a good thing to be in right now, but I personally wouldn't like to see it on the forum.

Reddit did it well with their bots that are just fixing minor mistakes or informing users about random stuff, but this what you're proposing is not my jam.

[o_e_l_e_o]

I don't think adding more AI generated text to the endless amount of spam will achieve anything. No one actually reads such replies anyway; they just get in the way of actual discussion. If we want to solve the spam problem, then we should just actually enforce the rules regarding spam and signature campaigns and start handing out temporary bans like the rules say we will.

[joker_josue]

If we want to solve the spam problem, then we should just actually enforce the rules regarding spam and signature campaigns and start handing out temporary bans like the rules say we will.

But, shouldn't campaign managers be more rigorous in the posts they count?
I can even accept that it is not always easy to check one by one the posts that campaign participants make. But, I believe that these users who have a very low level of quality in their posts are easily detectable.

[NotATether]

Who decides if a topic is low-quality or repetitive? And who decides if the community is tired of regurgitating a topic?

Good question. Obviously ChatGPT and AI in general is totally unpredictable for this task, so I've considered making a sort of algorithm to calculate a spam score, like the kind that would be used at Google.

I think it would be better to make a bot that replies to shitposts with a warning letting the poster know they are shitposting. Something like:

Warning: your post appears to have been written by an NPC. This question has been asked on the forum approximately 43 times already, with the most recent merited reply being the following:

We can prove that the number of provably lost bitcoin is 2,828.654 BTC, and this number can be safely removed from both the total and the circulating supplies. Anything which is not provably lost should not be considered removed from the supply.

Consider performing a simple Google or forum search before posting a question on the forum next time. Thank you for your cooperation.

In light of other comments here, I think it would be better to send that in a PM. It would be a turbocharged version of Bitcointalk moderation staff in that case (and would admittedly be more "automation" than AI).

I don't think adding more AI generated text to the endless amount of spam will achieve anything. No one actually reads such replies anyway; they just get in the way of actual discussion. If we want to solve the spam problem, then we should just actually enforce the rules regarding spam and signature campaigns and start handing out temporary bans like the rules say we will.

Agreed.

The target audience that is supposed to be reading these kind of posts are not so much Legendaries like you and I as it is for new members who've just arrived here <3 months ago.

It's still generic AI crap. Right now I'm struggling with a bunch of my writers because they think that AI content sounds interesting, it doesn't. There's no emotion, just mathematically correct sentences with a lot of words to explain something that could be explained with five bulletpoints. Reminds me of answers that politicians usually give.

Being something of a writer myself, I also agree with you that AI-generates or otherwise low-quality content written by humans can be crappy (unless the text written is of an extreme technical standard that will go into a technical topic).


Perhaps a userscript could be developed that automatically hides shitposts from threads (or even entire topics).

[BenCodie]

I think you have the right idea of using A.I. to positively impact the forum - I do agree with the others that auto-generating replies is probably not the best way. I think you are right that the Bitcoin discussion board has many repetitive topics. Recently, I have started to think I was having deja vu while scrolling through it.

Something that would be able to grab relevant threads based on title and content, list them with a percentage of relevancy and post the list in the first reply for repetitive topics to allow the topic starter and following readers to easily visit threads that are very similar and read the responses there; would be a nice adjustment to this idea and a neat addition to that board.

[dkbit98]

Sorry but I don't like this idea of using AI in bitcointalk forum at all.
There is always going to be some human being in forum who is willing to reply to any question, however stupid that question may be, and starting with one AI-bot could result with more of them in future.
This bot can make forum members even more lazy and more inactive, that is just one of the possible outcome of experiments like this.
Only AI that I would consider slightly useful for forum is one that could detect if posts have high chance of being AI generated, but it would probably make many mistakes.

[PowerGlove]

I'm personally against the idea of synthetic replies. I'd like to (maybe) see AI applied to curating good posts or hiding bad ones, but certainly not to adding even more crap to the forum. -1 from me.

On the topic of fighting shitposts, what I would love to see is a button that lets humans (with >= 500 earned merits) mark a post as "redundant":



When 10 or more distinct users have clicked it, the post should be hidden from view, unless you've gone into your options and opted in:



Campaign managers would (hopefully) leave this turned off, and would therefore not end up paying for those posts.

The details can be voted on (e.g. maybe 10 distinct users is too few or the threshold should be configurable, maybe 500 earned merits is not enough or too much, maybe only DT members should be able to see the button, etc.)

[o_e_l_e_o]

On the topic of fighting shitposts, what I would love to see is a button that lets humans (with >= 500 earned merits) mark a post as "redundant":

I can think of plenty of users with >500 merit who would quite happily abuse this and brigade another user's posts to have them all hidden, especially in the case of trust disputes. Also, such a feature would undoubtedly be misunderstood and used for posts the user dislikes or disagrees with, not just posts which are redundant.

[Sandra_hakeem]

It's such a copacetic response to the whole repetition that goes on and on, mostly in the B/H board... I see alot of things that shouldn't be repeated twice Being over-emphasized a couple of times too.. sometimes, i don't even blame 'em OPs Cus yeah, they're right to ask questions on what doesn't seem right to them...
Infact,I believe there's a lot more to be done....I'm not just a code freek nor some stylish programmer like Gloves or Atheter, but I'm sure it'll come to a time where the forum will have to make some milli-timeframe pop ups, or redirects on FAQS, to Auto-synchronize...
AIs, as suggested would do the job too, but what if the forum ends up with getting the whole AI theorem espoused ?? How well will the young-age take advantage of them??? (... rhetorical anyways..)

Sandra 🧑‍🦰

[PowerGlove]

I can think of plenty of users with >500 merit who would quite happily abuse this and brigade another user's posts to have them all hidden, especially in the case of trust disputes. Also, such a feature would undoubtedly be misunderstood and used for posts the user dislikes or disagrees with, not just posts which are redundant.

Do you really think users would collude like that? I mean, a threshold (of distinct and qualified members) has to be reached before the post is considered "redundant". The merit requirement (and/or DT status, mentioned at the end) is there to mitigate abuse (with farmed accounts, etc.)

Similar logic applies to people misunderstanding how to use the feature; their individual clicks won't do anything unless (a fair few) other members have already flagged that post as well.

It's a bit silly to criticize (rather than change) constants that were chosen while spitballing. If 500 merits is not enough, then make it 750. If 10 unique members is a threshold that's too easy to game, then make it 15...

Feels like you just read the line you quoted, and then quickly scanned the rest.

[joker_josue]

I can think of plenty of users with >500 merit who would quite happily abuse this and brigade another user's posts to have them all hidden, especially in the case of trust disputes. Also, such a feature would undoubtedly be misunderstood and used for posts the user dislikes or disagrees with, not just posts which are redundant.

Do you really think users would collude like that? I mean, a threshold (of distinct and qualified members) has to be reached before the post is considered "redundant". The merit requirement (and/or DT status, mentioned at the end) is there to mitigate abuse (with farmed accounts, etc.)

Other systems that the forum already has, such as trust, sometimes suffer abuse, let alone this one.

Then, the fact that the post is hidden in the topic, it will not disappear from the list of posts made by the user, which is probably the list that campaign managers analyze.

[NotATether]

On the topic of fighting shitposts, what I would love to see is a button that lets humans (with >= 500 earned merits) mark a post as "redundant":

I can think of plenty of users with >500 merit who would quite happily abuse this and brigade another user's posts to have them all hidden, especially in the case of trust disputes. Also, such a feature would undoubtedly be misunderstood and used for posts the user dislikes or disagrees with, not just posts which are redundant.

Now this is exactly the kind of thing you could use an AI for. They're neutral, don't get into trust disputes with anyone and never apply to join signature campaigns because they don't know what the hell that is.

Like I said, I'm starting to see AI as something that should be more augmented next to the post buttons than as replies themselves. The only problem is, now we are looking at full-blown infrastructure required to host such a bot (a userscript, and a server to go along with it, for something that basically is operated on a free basis).

[Poker Player]

You did not refer to anyone in particular, but as I am one of those who expressed my opinion, I feel called out, so I will answer you. Personally, I consider it an insult that you put us in the same category by citing the example of those people who hate Bitcoin from the bottom of their souls because it does not fit into their business philosophies.

I think I've been known to not hold my tongue if I want to insult someone in the forum, so your perception does not coincide with my intention.

Think of it this way: first, personal human interaction was replaced by electronic communication, and now we risk ending up only talking to electronics. Call me old-fashioned, but I don't like it. If I want to interact with a computer, I'll use a Search Engine or spambot myself.

I deny the premise, human interaction was not replaced by electronic communication. Or do you live in a cave and only interact with others by typing on your computer? Some human interaction was replaced by electronic communication in the areas where it was most productive and useful.

[LoyceV]

On the topic of fighting shitposts, what I would love to see is a button that lets humans (with >= 500 earned merits) mark a post as "redundant":

If it's redundant, why not report it to be deleted?

If 10 unique members is a threshold that's too easy to game, then make it 15...

If it takes 10 or more "hits" to hide a post, I'm not going to waste my time tagging them. It would be much better if it's linked to the Trust list, so based on the user's who's judgement you trust already.
Barely any user has more than 10 negative tags, it's very unlikely a single post will reach that much. Plus, it means at least 10 people have to actually read a redundant post, which is a massive waste of time.

Some human interaction was replaced by electronic communication in the areas where it was most productive and useful.

In my experience, human interaction is replaced by a cheaper system. Some companies now have a computerized phone menu when you call them, and many of the options lead to a dead end where you don't get to talk to a human. It's cheaper, but not helpful.

[joker_josue]

Now this is exactly the kind of thing you could use an AI for. They're neutral, don't get into trust disputes with anyone and never apply to join signature campaigns because they don't know what the hell that is.

But the fact that they are neutral, does not have the human capacity to understand everything that is involved in any post. So you can sometimes unfairly rate something negatively that it isn't, or rate something positively when you shouldn't.

It is true that the bot can improve these details, but humans have infinite probabilities, so something can look like one thing to an AI and be something totally different, which only human discernment can do.

I'm not against AI being able to help our day to day, but I think that it generates content on the forum, it distorts the purpose of the forum.


Another detail:
Here we are discussing a "good" bot that was intended to automatically answer repeated questions.
But, what would stop the emergence of "evil" bots that will create content simulating that it is human?

We have to be careful not to set precedents that then make everything more difficult to control.

[PowerGlove]

If it's redundant, why not report it to be deleted?

Yeah, I'm with you. But, people are lazy and being able to just quickly click one button (instead of having to click once, lose focus, enter some text, and then click again) will appeal to many more people, I think. Also, having precisely defined rules (e.g. if 9 of your peers agree(d) with you, then the post will be effectively "nuked" without further ceremony) is more satisfying (to me anyway) than being at the mercy of a hit-and-miss moderation policy.

If it takes 10 or more "hits" to hide a post, I'm not going to waste my time tagging them.

I had the same thought. I think it might work best if the post immediately (or maybe with a second, user-specified threshold) disappears from your own view, but only disappears from everyone else's when the global threshold has been reached. I could see myself clicking that button all the time.

It would be much better if it's linked to the Trust list, so based on the user's who's judgement you trust already.

Yep, or something similar, like a new "post curator" list.

Other systems that the forum already has, such as trust, sometimes suffer abuse, let alone this one.

That's true, but I'm not saying that this system won't be abused, I'm saying that it's possible to select the parameters in a way that would make that abuse impractical to execute. (Of course, there's a balancing act here: if you set the countermeasures too aggressively, then the feature won't work that well in practice, because too many people would have to click the button for the "threshold" to be crossed.)

Then, the fact that the post is hidden in the topic, it will not disappear from the list of posts made by the user, which is probably the list that campaign managers analyze.

When I said the post would be "hidden from view", I meant the user's post history, too. Although, I'm guessing some campaign managers might use tools that rely on post archives (like ninjastic.space), and that needs a slightly more complicated solution (maybe a new endpoint to get a list of "redundant" post IDs for a given user and time frame).

[o_e_l_e_o]

It's a bit silly to criticize (rather than change) constants that were chosen while spitballing. If 500 merits is not enough, then make it 750. If 10 unique members is a threshold that's too easy to game, then make it 15...

You've already picked up on my point here in your next post: Using numbers which are sufficiently high to make it resistant to abuse will also make it essentially useless.

I am also in general against any proposal which brings us closer to Reddit's "mob rule" upvote/downvote type system, where unpopular but factually accurate posts are often hidden from view.

[NotATether]

On the topic of fighting shitposts, what I would love to see is a button that lets humans (with >= 500 earned merits) mark a post as "redundant":

If it's redundant, why not report it to be deleted?

Because we can't rely on moderators deleting all low-quality posts.

We have ~20 staff versus 20 thousand shitposts per day.

Which is why such posts should be automatically classified and hidden from everyone who uses a particular userscript.

[PowerGlove]

@NotATether: I'm starting to see your point about letting an AI classify shitposts. But, I don't frequent super spammy boards, so most of my issue is actually sig spam on good boards. The best way to combat sig spam is to have campaign managers stop paying for it. A system like what I'm proposing could achieve that without them having to change anything about how they run their campaigns, the posts would just automatically stop being paid for (because the managers would never see them). In my estimation, "AI" can often just be replaced with the phrase "black box", and I don't like the idea of affecting people's earnings with something that isn't accountable, makes decisions unilaterally, and frequently gets things wrong.

I am also in general against any proposal which brings us closer to Reddit's "mob rule" upvote/downvote type system, where unpopular but factually accurate posts are often hidden from view.

Yep, very much agree! But, surely you can appreciate how what I've described so far has the makings of a workable system?

Are you really so confident that no combination of parameters will end up working?

Don't you think some kind of trusted "post curator" list (or something similar) is worth exploring? (Please don't take the shortcut of immediately asking: "Okay, but who decides who's a curator and who isn't?".)

Or, what if the community could see a log (either combined or separated) of each user's activity with regard to this system, so everything was done out in the open, and negative trust could be used as a tool to combat abusers?

[o_e_l_e_o]

Don't you think some kind of trusted "post curator" list (or something similar) is worth exploring?

Maybe if it was made up of a few selected users rather than just anyone with "greater than x merit" which is easily abused, but then that raises the question "Why not just appoint said users as moderators"?

and negative trust could be used as a tool to combat abusers?

This would not be a good use of the trust system.

[LoyceV]

If it takes 10 or more "hits" to hide a post, I'm not going to waste my time tagging them.

I had the same thought. I think it might work best if the post immediately (or maybe with a second, user-specified threshold) disappears from your own view

Why waste time clicking individual posts, if you can Ignore everything from that user with one click?
If you want to share responsibility of hiding posts, it may be better to bring back the glowing Ignore button. It was removed before I joined, and I guess it was abused, but it might work in combination with custom Trust lists.

If it's redundant, why not report it to be deleted?

Because we can't rely on moderators deleting all low-quality posts.

We have ~20 staff versus 20 thousand shitposts per day.

It's more like 5000 posts per day, and not all of them are shitposts. But, instead of automatically hiding them, why not hook up with MindlessElectron to remove them

[joker_josue]

When I said the post would be "hidden from view", I meant the user's post history, too. Although, I'm guessing some campaign managers might use tools that rely on post archives (like ninjastic.space), and that needs a slightly more complicated solution (maybe a new endpoint to get a list of "redundant" post IDs for a given user and time frame).

But your idea was to be something standard on the forum or would it be a script that the person chose to use or not?

If it's a default system, it's almost like having all threads like they're auto-moderated. And honestly I don't think that's a good vision...

[PowerGlove]

Why waste time clicking individual posts, if you can Ignore everything from that user with one click?

Because that won't affect their earnings, and hitting them in the wallet is the best way to get them to stop posting rubbish. (Which will make the forum better for everyone.)

and negative trust could be used as a tool to combat abusers?

This would not be a good use of the trust system.

Obviously, I'm not suggesting that people should be encouraged to tag each other over isolated cases of what they consider incorrect use. I'm saying that the possibility of receiving (justifiable) negative trust from a DT member would make a fine hedge against anyone seriously considering engaging (either alone, or as part of a group) in a pattern of repeated abuse.

[LoyceV]

hitting them in the wallet is the best way to get them to stop posting rubbish. (Which will make the forum better for everyone.)

From what I've seen over the years, getting rid of obvious spam makes some of the spammers switch to something that's much harder to detect.
When plagiarism got busted, they switched to a homograph attack. When that was made impossible (by theymos), they switched to word spinners. Now it's AI-spam. The main problem is: it becomes less and less obvious what's spam, and more time consuming to detect.

[NotATether]

If it's redundant, why not report it to be deleted?

Because we can't rely on moderators deleting all low-quality posts.

We have ~20 staff versus 20 thousand shitposts per day.

It's more like 5000 posts per day, and not all of them are shitposts. But, instead of automatically hiding them, why not hook up with MindlessElectron to remove them

Who (what) is MindlessElectrion exactly?

[Mitchell]

Who (what) is MindlessElectrion exactly?

Only the best spam buster out there. The information on it's profile basically says everything. It reports/removes/nukes (newbie) accounts if they post malware/spam/etc.

[NotATether]

Who (what) is MindlessElectrion exactly?

Only the best spam buster out there. The information on it's profile basically says everything. It reports/removes/nukes (newbie) accounts if they post malware/spam/etc.

I'm thinking of something like the following:

Instead of randomly intruding into random people's threads, a topic starter could "opt in" to enhanced spam scrubbing by placing a special bbcode inside the OP, that (among other things) contains a "percentage spaminess threshold" that applies to all replies.

Then, I have J.A.R.V.I.S monitor the thread and score each person's reply, and the ones that fall short of the spamming score, I report these replies, or maybe I relay the posts to your bot if you can offer a faster way to delete those posts.

As an example (taken from a random thread, and not intended to criticize anyone's posting behavior), let's pretend the Bitcasino ANN thread wants everyone posting to stay strictly on-topic about gambling or its casino, and opted in to spam scrubbing and signals to delete any reply with even 10% spaminess score. Then when posts like the following are made:



All of these replies would be trashed. Though considering these are legendary/hero members, I don't know if your bot analyzes them as well.


I am almost 100% sure that Bitcointalk itself will not enforce any enhanced spam requirements, so perhaps a minimum spamminess score for any given thread could be set to 90%, in which case, all (recent, within the past 2 weeks) posts that fail to be even a little substantial are reported/deleted en-masse.

Certain exceptions would be made for boards and threads which are not supposed to be patrolled, such as Off-topic and Archival, and the Wall Observer thread.

This would also be another one of those use cases that use automation/algorithms, and not AI in particular.

[John Abraham]

hitting them in the wallet is the best way to get them to stop posting rubbish. (Which will make the forum better for everyone.)

From what I've seen over the years, getting rid of obvious spam makes some of the spammers switch to something that's much harder to detect.
When plagiarism got busted, they switched to a homograph attack. When that was made impossible (by theymos), they switched to word spinners. Now it's AI-spam. The main problem is: it becomes less and less obvious what's spam, and more time consuming to detect.

Then what could be the possible solution? Just let them do shit? Recently I saw people report some AI Written content that was not been removed yet. Officially they are not violating the rules yet. Plagiarism is getting more tolerance from Global Mods. I think a Perm ban is too harsh for mistakes like plagiarism, especially if it's done once or twice and done by someone who made some positive contribution. But these days, your plagiarism reporting thread got a bunch of reports where the same users are doing the same shit repeatedly, and Mods handled those reports without punishment.

Now, Come to AI Spam. It doesn't have a rule yet. I don't think reporting them has any benefits. I feel like I saw a thread from a Global Mod's alt. He was talking about plagiarism rules and punishment. Couldn't find it anymore. Aww, it seems I am going off-topic.

[PowerGlove]

From what I've seen over the years, getting rid of obvious spam makes some of the spammers switch to something that's much harder to detect.
When plagiarism got busted, they switched to a homograph attack. When that was made impossible (by theymos), they switched to word spinners. Now it's AI-spam. The main problem is: it becomes less and less obvious what's spam, and more time consuming to detect.

Yeah, that's true. But, I like to think that I can tell when I'm reading a redundant post [1], and I would completely trust your judgment, and o_e_l_e_o's, Foxpup's, n0nce's, DarkStar_'s, DireWolfM14's, etc. in determining the same. (Not exhaustive and in no particular order, I'm just picking a few names off the top of my head.)

I really feel like people are sleeping on what a good thing a properly implemented version of this idea would be. Anyway, my thoughts on this are spread out over my last few posts, and I've done a bang-up job of derailing NAT's thread, so I'm bowing out for now. (PM me for continued discussion, if you like.)

[1] I guess, my definition of "redundant" (for the purposes of this system) is when I can defensibly say "no" to the following question: "Is this post likely to be missed (by anyone but the author) if it were deleted?". Now, before anyone says: "Yeah, but who are you to determine that?", that's the whole point of the system, no individual would have the power to affect things too much, and if mobs form that end up misusing the system en masse, then an "open logs" policy and the threat of negative feedback will put things right again pretty quickly.

[joker_josue]

I'm thinking of something like the following:

Instead of randomly intruding into random people's threads, a topic starter could "opt in" to enhanced spam scrubbing by placing a special bbcode inside the OP, that (among other things) contains a "percentage spaminess threshold" that applies to all replies.

Then, I have J.A.R.V.I.S monitor the thread and score each person's reply, and the ones that fall short of the spamming score, I report these replies, or maybe I relay the posts to your bot if you can offer a faster way to delete those posts.

This is already something else than the OP's original idea (at least as I perceived it). This was a bot that would make self-moderating threads easier. Where the OP of these threads could request to use this bot to moderate the thread. A bot to help with that can be useful for doing ANN or something like that.

[Sandra_hakeem]

hitting them in the wallet is the best way to get them to stop posting rubbish. (Which will make the forum better for everyone.)

From what I've seen over the years, getting rid of obvious spam makes some of the spammers switch to something that's much harder to detect.
When plagiarism got busted, they switched to a homograph attack. When that was made impossible (by theymos), they switched to word spinners. Now it's AI-spam. The main problem is: it becomes less and less obvious what's spam, and more time consuming to detect.

...and these things keep happening that at some point, I'll ask myself why some peeps choose to learn and get anything done the hard way; I mean, it's much more simple to be conscientious... Has spamming ever Paid anyone ??...
Now about the AI spam? That's exactly the same logic I tried to surpass in my last post on this thread; who knows how rugged 'em clodpoll will become in future? - Especially when they've been given a stressless route to either taunt or cheat in here...
P.S: I believe alot of rookies that have lived meagrely in the time past and have realized the future trend, won't get registered in a bid to learn but end up reading Artificially developed ideas - a type which is LIMITED?? ...that would simply mean everything in the adage that says "the hunter could prolly become the hunted"... Please, y'all be careful about the decisions you make.... It's not even about me, it's about the future to come.

Sandra 🧑‍🦰

[LoyceV]

Then what could be the possible solution? Just let them do shit?

I don't know the solution At least there's much less spam than we had years ago, thanks to the Merit system.
And there's this:

The things on the forum which encourage spam are allowed mainly because it's part of the forum's mission to be as free as possible.

(click to read the rest of the post)

I like to think that I can tell when I'm reading a redundant post [1], and I would completely trust your judgment, and o_e_l_e_o's, Foxpup's, n0nce's, DarkStar_'s, DireWolfM14's, etc. in determining the same.

I'm in the same boat. But in that case, just giving those users Mod-powers would solve it for everyone.

Has spamming ever Paid anyone ??...

Spam wouldn't exist if it wouldn't be profitable.

[n0nce]

I appreciate the effort and do like the idea in the sense that questions actually repeat themselves quite often. When I encounter such topics, I try to quickly find a similar topic (similar to StackOverflow topic suggestions) and refer the user to it.
I think making a bot do something like this (or at least one that assists users in this manner, e.g. as a browser extension that uses TryNinja's search and suggests similar topics) would be more useful than having a language model write full replies.

My main issue with ChatGPT is that (as mentioned before) is a language model. Its entire purpose is writing text that looks / reads good. Not writing correct text. Therefore I'd avoid using ChatGPT for anything but creating text (or maybe code) templates to fill out yourself. Like a letter template.

[dkbit98]

My main issue with ChatGPT is that (as mentioned before) is a language model. Its entire purpose is writing text that looks / reads good. Not writing correct text. Therefore I'd avoid using ChatGPT for anything but creating text (or maybe code) templates to fill out yourself. Like a letter template.

ChatGPT just repeats stuff like parrot and it has no sense of good and bad, I recently watches one guy asking him questions and ChatGPT had to restrict him access in the end because he was making conflicting statements all the time.
My point is that this AI is not available all the time, it can't work without human controller, and I have no idea why people are fascinated with it so much.
We the people can survive and function just fine without ChatGPT, not the other way around.

[DireWolfM14]

Yeah, that's true. But, I like to think that I can tell when I'm reading a redundant post [1], and I would completely trust your judgment, and o_e_l_e_o's, Foxpup's, n0nce's, DarkStar_'s, DireWolfM14's, etc. in determining the same.

I found it funny that you mentioned me, because I had zero experience with these new fangled AI systems.  But, this discussion got me curious so I just spent an hour playing with ChatGPT to get an idea of how it would respond.  I agree that it would be fairly easy for me to distinguish, or at least I would also like to believe so.  The the example I posted below, for instance; it's accurate and coherent, for sure, but contains no personality.  The precision is too mechanical, almost predictable in it's encyclopedic accuracy.  Soulless, for lack of a better term.

write two paragraphs about the impact of spammers on a discussion forum

Spammers can have a significant negative impact on discussion forums. They often flood the forum with irrelevant or misleading messages, advertising for products or services, or even phishing scams. This behavior can quickly disrupt the flow of genuine discussion and cause users to lose interest in participating in the forum altogether. Moreover, spammers may also post malicious links or files that can infect users' computers with malware, leading to potential security risks for both individuals and the forum as a whole.

Additionally, dealing with spam can be a time-consuming and frustrating task for forum moderators. They must constantly monitor the forum, remove spam posts, and ban spammers who repeatedly violate the rules. This takes time away from other important moderation duties, such as addressing user concerns and fostering constructive discussions. Ultimately, the presence of spammers can undermine the purpose of a discussion forum by reducing its credibility and reliability as a source of valuable information and community engagement.

[The Sceptical Chymist]

Depending on how you're planning to do it, those rules cover it. It's better to report those posts.

Uh.....yeah.  This is as far as I've gotten in reading this thread, but I'm going to be consistent and reply before I finish.

Not only would I not want to see replies automatically generated in response to idiotic or just plain common questions, but I also don't think it's going to do anything to reduce the number of sig/bounty shitposters chiming in with equally idiotic replies.  If you have a thread started with a question like "what's the best hardware wallet?" and and the first response from a member is the most comprehensive comparison of all the hardware wallets out there with a detailed description of each one, there's no question in my mind that the following replies will be half garbage and half commenting on whatever.  AI isn't going to solve any of this forum's problems.

Spam wouldn't exist if it wouldn't be profitable.

WORD UP.

I've been watching some videos about this stuff lately, and sweet satan is it scary as hell.  I think we're all fucked in about five years.

[NotATether]

Depending on how you're planning to do it, those rules cover it. It's better to report those posts.

Uh.....yeah.  This is as far as I've gotten in reading this thread, but I'm going to be consistent and reply before I finish.

If you have a thread started with a question like "what's the best hardware wallet?" and and the first response from a member is the most comprehensive comparison of all the hardware wallets out there with a detailed description of each one, there's no question in my mind that the following replies will be half garbage and half commenting on whatever.

It is a multi-layered problem.

If only all first replies were constructed as carefully as that, then there would hardly be a visible spam problem, as any userscript can just filter all spam from Page 2 or reply #10 onwards or something.

Spam wouldn't exist if it wouldn't be profitable.

WORD UP.

I've been watching some videos about this stuff lately, and sweet satan is it scary as hell.  I think we're all fucked in about five years.

Well since we are on bitcointalk.org, it is possible to make some incentive for campaign members to post a well constructed and detailed (non-AI generated) as the first/second/third reply of a question thread, and that will reduce the amount of spam people have to wade through to find an answer ultimately.

But I'm not a campaign manager, I am a "hacker", and thus I must work with what I have.

[LoyceV]

Well since we are on bitcointalk.org, it is possible to make some incentive for campaign members to post a well constructed and detailed (non-AI generated) as the first/second/third reply of a question thread

Getting the job in a campaign already is the incentive to make useful posts

[n0nce]

I have no idea why people are fascinated with it so much.

I can definitely understand it. Since it writes so well and human-like, it is easy to be fooled by it and believe that the text contents are correct, as well. Also, most people have no prior experience with AI and thus it is fascinating to interact with one for the first time.
I'm sure when researchers interacted with the first somewhat working AIs over 20 years ago for the very first time, they must have felt a similar feeling to the normal user logging into ChatGPT today. AI has always had this 'almost there' kind of feeling in my opinion, where it feels like it's about to be an omnipotent, or at least omniscient thing that's going to revolutionize everything.

[Synchronice]

JARPI (J.A.R.V.I.S AutoReply Protocol Initiative) is the name of a system I'm designing to automatically reply to low-quality, repetitive Bitcoin questions that the community is tired of regurgitating. This project is meant to demonstrate the positive impact that AI can have on Bitcointalk when it is used correctly.

I don't understand why my opinion gets ignored but if you don't believe me, just check and analyze the situation yourself. So, I'll tell you why actually repetitive questions are asked on this forum:
There are a lot of people who post just for the sake of signature campaign earnings. There are threads in every boards that require some knowledge and mental work to answer. For someone, who doesn't speak English and didn't have access on proper education and comes from a very poor country, it is getting difficult to post in these threads and it will take a lot of time, so here is what they do: One newbie registers on Bitcointalk and creates threads that have been answered thousand times but doesn't show up on first page of board and at the same time it's easy to answer, for example threads like this: Is money the root of all evil?, Bitcoin vs Stock market, Will bitcoin replace banks?, Will bitcoin end world poverty?.
These threads are easy to abuse, you just always side with Bitcoin, even with nonsense text and no one complains. So, the scheme is following: One user creates thread that is easy to spam and hundreds of users post in this thread. Then this one user creates another thread again and again. This one user is not alone, there are other users who follow his path and finally tons of spammy threads are created that feeds spammy users.

Just check it yourself, this is something that needs to be fixed. I am not against what you do but to be honest, an AI can do nothing in this case. One positive thing it can bring is to report some nonsense posts or threads to moderators.

[n0nce]

Just check it yourself, this is something that needs to be fixed. I am not against what you do but to be honest, an AI can do nothing in this case. One positive thing it can bring is to report some nonsense posts or threads to moderators.

Using AI to automatically flag / report spam / nonsense threads and posts does seem like a useful application of this technology. It would need to be a somewhat purpose-built AI though, trained on actual Bitcointalk data. Not as easy as 'throw it into ChatGPT', sadly, but probably much more effective.

[NotATether]

Well since we are on bitcointalk.org, it is possible to make some incentive for campaign members to post a well constructed and detailed (non-AI generated) as the first/second/third reply of a question thread

Getting the job in a campaign already is the incentive to make useful posts

That's true, but I am speaking of larger incentives: an additional $50/week for making an early constructive answer is nothing to pass over.

[PowerGlove]

That's true, but I am speaking of larger incentives: an additional $50/week for making an early constructive answer is nothing to pass over.

You have to be really careful when thinking up incentives, because they can easily backfire and make the problem they were intended to solve worse rather than better.

It's like that story about trying to get the rat population under control during the French occupation of Hanoi. The authorities incentivized citizens to kill rats (by offering them a small reward for each tail they brought in), and although it did work for a short time, citizens then started leaving the rats alive (after taking their tails), hoping that they would breed and produce more tails for them to collect the bounty on. There was even rat farming going on, to take better advantage of the rewards. Authorities realized what was happening and stopped paying for the tails, but the damage was done and they now had an even bigger rat problem than when they started...

If you add a financial incentive to getting your post in early, then I think that would ultimately decrease the quality of the first few replies. There's already a kind of "traffic jam" at the beginning of some topics (usually questions) with the first few replies trying to compete for merit. I often don't bother to post in topics like that because it would take me too long to do the question any real justice, and I know that by the time I'm finished with my reply there'll already be a bunch of (pretty lazy) "fast" answers that (taken as a whole) cover most of what I was going to say. It would actually be pretty cool if there was a way to call "dibs" on a topic and stop other people from posting "rushed" answers while you work on a comprehensive one.

[o_e_l_e_o]

You would undoubtedly have 5+ posts saying "Reserved" show up immediately on every single topic posted in the technical boards.

[NotATether]

You would undoubtedly have 5+ posts saying "Reserved" show up immediately on every single topic posted in the technical boards.

Hmm... maybe "reserved" posters could get warnings or be kicked out of their campaign as a punishment?

If you add a financial incentive to getting your post in early, then I think that would ultimately decrease the quality of the first few replies. There's already a kind of "traffic jam" at the beginning of some topics (usually questions) with the first few replies trying to compete for merit. I often don't bother to post in topics like that because it would take me too long to do the question any real justice, and I know that by the time I'm finished with my reply there'll already be a bunch of (pretty lazy) "fast" answers that (taken as a whole) cover most of what I was going to say. It would actually be pretty cool if there was a way to call "dibs" on a topic and stop other people from posting "rushed" answers while you work on a comprehensive one.

Makes me wonder whether there's such a thing as an "academic score" for measuring the substance of texts. The idea being, the same university-level standards that are applied against plagiarism currently are used to score a post based on several criteria like originality and informativeness. <And this score is posted next to every topic so that there are no accusations of "collusion" and also so that people can realize when they are shitposting.>

And people who don't even manage to pass the score get no bonus (and ChatGPT, lacking any emotion at all, would score a zero and get ejected).

For example, in my campaign there is a bonus that goes to the best posters. Although it is quite a manual process, maybe there is some heuristic some researcher has come up with for this in the last 100 years.

[joker_josue]

Makes me wonder whether there's such a thing as an "academic score" for measuring the substance of texts. The idea being, the same university-level standards that are applied against plagiarism currently are used to score a post based on several criteria like originality and informativeness. <And this score is posted next to every topic so that there are no accusations of "collusion" and also so that people can realize when they are shitposting.>

And people who don't even manage to pass the score get no bonus (and ChatGPT, lacking any emotion at all, would score a zero and get ejected).

For example, in my campaign there is a bonus that goes to the best posters. Although it is quite a manual process, maybe there is some heuristic some researcher has come up with for this in the last 100 years.

But is there a better way to do this, other than manually?
The best way to assess the quality of a post is by a human. Especially because the concept of quality can vary from person to person, and even if there are guidelines, only a human being will be able to evaluate it in the best way.

This is really not an easy thing, but we have to debate ideas to find ideas/solutions that allow us to reduce this level of spam/poor quality.

[yhiaali3]

Personally, I do not see any objection to the use of artificial intelligence robots modified manually, this will not eliminate the role of members in providing their own touch on the topics or responses that they write.

This is similar to when someone uses Google Translator and then manually revises the translation so that it appears human rather than machine.

But on the other hand, locking the topic when using JARPI will make most of the discussions brief and deprive many members of responses.

[John Abraham]

Then what could be the possible solution? Just let them do shit?

I don't know the solution At least there's much less spam than we had years ago, thanks to the Merit system.

I can't blame you for not knowing the solution. I understand that theymos don't want to put more restrictions and keep the forum as free as possible. But Forum Mods can update the forum rules over time, especially for AI. Some people use AI to write posts; when you ask them more about it, they cannot tell you in detail. They don't even know what they are talking about. There are a bunch of tools that they can utilize so they don't get caught. At first, they write content using GPT, then they use paraphrase tools so you cannot detect AI Writing using another AI.

Has spamming ever Paid anyone ??...

Spam wouldn't exist if it wouldn't be profitable.

That's why bounty participants paid for (For spam).

[LoyceV]

Forum Mods can update the forum rules over time, especially for AI. Some people use AI to write posts

Like Edcrypto91. I reported 4 of his posts, and 6 of them got deleted. But he didn't get banned, which is disappointing. Maybe he got a temporary ban, but I can't know that. Chat AI spam is plagiarism, but without clear source it's hard to prove. If shitting all over the tech boards isn't enough to get this user banned, reporting him feels like a waste of time. He's now on my ignore list, which makes one less user to report his posts.

[John Abraham]

Forum Mods can update the forum rules over time, especially for AI. Some people use AI to write posts

Like Edcrypto91. I reported 4 of his posts, and 6 of them got deleted. But he didn't get banned, which is disappointing. Maybe he got a temporary ban, but I can't know that. Chat AI spam is plagiarism, but without a clear source, it's hard to prove. If shitting all over the tech boards isn't enough to get this user banned, reporting him feels like a waste of time. He's now on my ignore list, which makes one less user report his posts.

I have no problem if Moderators want to give someone a second chance. Even if they think someone deserves several chances, that's okay. But, it should vary from member to member. You have to see who the member is. If it's someone prominent member or someone who has the potential to contribute positively. You may give them several chances to prove themselves. I saw ETFBitcoin reported several plagiarisms of the same user and he is still doing the same shit every day.

A permanent ban is too harsh with the ban evading rule. But, when you are giving them several chances and you see he continues doing the same shit. You should think about it. If you see the same user doing it again and again, you shouldn't forgive them every time. Users like Jamesborn, Godlovesyou, and many more deserves punishment for what they doing.

[Josefjix]

For the JARPI bot, no matter how hard you spin those texts manually, they won't be original, and have you considered the amount of posts this bot will be posting per day since it triggers every time someone asks a question, or are there limitations I'm not aware of, this AI thing is getting out of hand, these tools would render some of our education sector useless, resulting in the loss of jobs if nothing is done now.

Forum Mods can update the forum rules over time, especially for AI. Some people use AI to write posts

Like Edcrypto91. I reported 4 of his posts, and 6 of them got deleted. But he didn't get banned, which is disappointing. Maybe he got a temporary ban, but I can't know that. Chat AI spam is plagiarism, but without clear source it's hard to prove. If shitting all over the tech boards isn't enough to get this user banned, reporting him feels like a waste of time. He's now on my ignore list, which makes one less user to report his posts.

You don't expect the admin to ban someone for 6 nasty posts, do you? Like you said AI written post is difficult to prove if it is plagiarism or not because it is nearly impossible to cite the main source, so they are automatically classified as spam and get deleted overtime, there are tons of users with over 100 deleted spam posts who are still here going about their unusual spamming business. Ignoring him is the best you can do in this scenario; we shouldn't make the forum tough and uncomfortable for newbies; I'm sure most of us didn't start out well, and everyone learns with time.

Remember when you asked the Admin to ban DdmrDdmr for spamming when he was a newbie? Today, he is regarded as the best thing that has ever happened to the forum. patience!

[LoyceV]

You don't expect the admin to ban someone for 6 nasty posts, do you?

The forum would be better without such users.

Remember when you asked the Admin to ban DdmrDdmr for spamming when he was a newbie?

That's a different case: DdmrDdmr's username came up in an automated search, which wasn't meant to be exhaustive. Luckily, the Mods did their checks. Around the same time hundreds of users got banned based on the list I provided.

[Josefjix]

You don't expect the admin to ban someone for 6 nasty posts, do you?

The forum would be better without such users.

That's why we have mods; report them and let them do their thing; they follow the rules; 6 ugly shit shouldn't get anyone banned.

Remember when you asked the Admin to ban DdmrDdmr for spamming when he was a newbie?

That's a different case: DdmrDdmr's username came up in an automated search, which wasn't meant to be exhaustive. Luckily, the Mods did their checks. Around the same time hundreds of users got banned based on the list I provided.

It's the same thing; you pushed hard to have everyone on that list nuked. Fortunately, the moderators did their jobs; I can't check every individual on the list, but I'm sure most became active forum users, and those who were nuked moved on to open new accounts. Nothing was solved

[NotATether]

For the JARPI bot, no matter how hard you spin those texts manually, they won't be original, and have you considered the amount of posts this bot will be posting per day since it triggers every time someone asks a question, or are there limitations I'm not aware of, this AI thing is getting out of hand, these tools would render some of our education sector useless, resulting in the loss of jobs if nothing is done now.

I haven't ran JARPI ever since the manual experiment earlier last week.

[LoyceV]

I can't check every individual on the list, but I'm sure most became active forum users

Cute. But wrong. I checked the first 10, and 9 of them have 0 posts (AKA Nuked). One of them has 580 Activity now, and 0 Merit because bounty spam isn't worth Merit.

and those who were nuked moved on to open new accounts. Nothing was solved

Hundreds of farmed account were Nuked and their IP-addresses got evil point for it. Of course there will always be spammers, but every account that gets banned is one spammer less. The fact that there's much less spam now than we had 4 years ago confirms it's working.

I'll end this discussion here. If you want to continue this, feel free to open another topic for it.

[Josefjix]

For the JARPI bot, no matter how hard you spin those texts manually, they won't be original, and have you considered the amount of posts this bot will be posting per day since it triggers every time someone asks a question, or are there limitations I'm not aware of, this AI thing is getting out of hand, these tools would render some of our education sector useless, resulting in the loss of jobs if nothing is done now.

I haven't ran JARPI ever since the manual experiment earlier last week.

Okay, what were the response speed and success rate? I appreciate the time and effort you have put into this, but I'm concerned that this bot will hijack every thread and post thousands of times per day, this is one part you are yet to address.

I can't check every individual on the list, but I'm sure most became active forum users

Cute. But wrong. I checked the first 10, and 9 of them have 0 posts (AKA Nuked). One of them has 580 Activity now, and 0 Merit because bounty spam isn't worth Merit.

How about you check all this links before ticking the wrong box for me? I bet many survived and are doing pretty good now.

and those who were nuked moved on to open new accounts. Nothing was solved

Hundreds of farmed account were Nuked and their IP-addresses got evil point for it. Of course there will always be spammers, but every account that gets banned is one spammer less. The fact that there's much less spam now than we had 4 years ago confirms it's working.

I'll end this discussion here. If you want to continue this, feel free to open another topic for it.

Aren't you the same person whitelisting them back to the forum now? how many of those users actually became big part of the forum ^{well i don't expect you to answer}

Sorry Op for going off-topic

[cafter]

I think all these is a waste of time and gain of experience for @notatether
because when a low quality thread is posted, after some minutes some users might already replied with very good answers, and your bot will post another reply which maybe a little spammy and off topic(when OP is weak in english maybe AI misunderstand it)) and answers to that thread is already humanly answered by some user with very good explanation, it may be a waste of time for you but definitely you will learn something new in this project.

My idea:
many low quality posts are posted by newbie, so we can try to tell them(by making search button bold, writing about using search button in top of the forum homepage, etc) to use the search tool for their answer. I many times used search bar and got my answer quickly without wasting others and mine time to waiting for replies.

(this was pretty good discussion to read, many other replies are all same in most of the threads)

[NotATether]

For the JARPI bot, no matter how hard you spin those texts manually, they won't be original, and have you considered the amount of posts this bot will be posting per day since it triggers every time someone asks a question, or are there limitations I'm not aware of, this AI thing is getting out of hand, these tools would render some of our education sector useless, resulting in the loss of jobs if nothing is done now.

I haven't ran JARPI ever since the manual experiment earlier last week.

Okay, what were the response speed and success rate? I appreciate the time and effort you have put into this, but I'm concerned that this bot will hijack every thread and post thousands of times per day, this is one part you are yet to address.

Well firstly, report handling times are exactly the same as manual reporting, so that's one.

I don't intend to unleash the bot on autopilot and find threads to post in on its own. Generative AI is not sophisticated enough for that yet. I would need to train a homegrown neural network on all recent Bitcointalk posts, but that is very difficult because I don't have all the posts locally (yet).

Also the bot is bottlenecked by how fast I can solve Cloudflare captchas. Maybe 10 at once before I rip my brains out.

I'm not quite sure of the resource requirements such a neural network would require, but if it's large or even possibly average, I believe it's not worth it considering the negative perception of this protocol.

[Learn Bitcoin]

Aren't you the same person whitelisting them back to the forum now? how many of those users became a big part of the forum ^{well I don't expect you to answer}

Sorry Op for going off-topic

I don't know why but I feel like you are trying to trigger him (good try). None of them are paid jobs. He is doing it voluntarily and he is not responsible for what they do after. Most of His whitelisted users doing good. He often posts the Ban %. If you are trying to trigger him, I am sorry but he is unlikely to pay attention to you as he proved himself as a thick-skinned gang leader.

About the six posts you mentioned, look at the percentage, please. If a user made ten thousand posts and has 100 deleted posts, that's nothing. It's only 1% of his posts. At the same time, if anyone writes 60 posts and 6 of them got deleted. That's ten percent of his posts. No one forcing moderators to ban them. Users reported posts and the rest of them were on Moderators. They will decide what to do.

What's the problem here?

[NotATether]

I guess now I'm going to be using JARPI as an AI-buster:

AI-generated topic
It is highly likely that the OP of this topic has created it entirely using AI such as ChatGPT. This has been verified by @NotATether who has ran the content through multiple AI detector websites. Therefore, it is recommended that this topic is locked, as no further constructive discussion can be added to this topic.

Users who see this message should report this topic to a moderator, requesting it to be locked, instead of facilitating the spread of spam.

This reply was auto-generated by JARPI, an AI protocol created by NotATether for automatically replying to frequently asked questions, and other common types of posts.

[joker_josue]

I guess now I'm going to be using JARPI as an AI-buster:

Look, I think this idea is better than answering questions!

But, based on the automatic text, I had a doubt:
Do you first manually validate the AI's suspicion and then post, or does it post automatically?
Or are you the one who suspects a topic, and puts the JARPI to analyze which then makes the post in case of a positive result?

[nutildah]

I guess now I'm going to be using JARPI as an AI-buster:

AI-generated topic
It is highly likely that the OP of this topic has created it entirely using AI such as ChatGPT. This has been verified by @NotATether who has ran the content through multiple AI detector websites. Therefore, it is recommended that this topic is locked, as no further constructive discussion can be added to this topic.

Users who see this message should report this topic to a moderator, requesting it to be locked, instead of facilitating the spread of spam.

This reply was auto-generated by JARPI, an AI protocol created by NotATether for automatically replying to frequently asked questions, and other common types of posts.

Alright, now I think you're on to something.

I have to ask out of curiosity, and due to my own thread on the issue, which AI detectors are you going to use, and how are you weighing the results? Are there different levels of likeliness, or will it only post replies in threads that come back as "highly likely" to be AI-generated?

[NotATether]

I guess now I'm going to be using JARPI as an AI-buster:

Look, I think this idea is better than answering questions!

But, based on the automatic text, I had a doubt:
Do you first manually validate the AI's suspicion and then post, or does it post automatically?
Or are you the one who suspects a topic, and puts the JARPI to analyze which then makes the post in case of a positive result?

Third option is correct. I ran OP's text through many AI detectors and all of them gave AI-generated indicators, so I fired up JARPI to send the warning.

I have to ask out of curiosity, and due to my own thread on the issue, which AI detectors are you going to use, and how are you weighing the results? Are there different levels of likeliness, or will it only post replies in threads that come back as "highly likely" to be AI-generated?

I use at least three different AI checking websites. Or more than three if even one of them doubts that the text is not completely AI-generated. I do not use the GPTZero website - I had too many false positives with it.

[cafter]

@notatether

don't you think, when many people will report that thread or post by watching JARVIS's reply, then maybe the moderator will be frustrated by too many reports. (i don't know how it seems from mod side, but maybe it will become confusing when too many people will report.)

[NotATether]

@notatether

don't you think, when many people will report that thread or post by watching JARVIS's reply, then maybe the moderator will be frustrated by too many reports. (i don't know how it seems from mod side, but maybe it will become confusing when too many people will report.)

How many of them will actually report though, out of the ones that are reading it 

Unfortunately, even after making the announcement, and showing the AI detection results in big fat pictures, there are still idiots who are mindlessly replying to that thread.

Moderators probably have a huge backlog of reports to deal with anyway, and the worst that will happen is that the report is simply unhandled.

[Josefjix]

Aren't you the same person whitelisting them back to the forum now? how many of those users became a big part of the forum ^{well I don't expect you to answer}

Sorry Op for going off-topic

I don't know why but I feel like you are trying to trigger him (good try). None of them are paid jobs. He is doing it voluntarily and he is not responsible for what they do after. Most of His whitelisted users doing good. He often posts the Ban %. If you are trying to trigger him, I am sorry but he is unlikely to pay attention to you as he proved himself as a thick-skinned gang leader.

We were just having a chat and he felt it wasn't the proper place because it was a little off-topic from the OP, I simply made my perspective plain to him, it's nothing personal, and BTW, we're still on the same track. Leave it to the moderator to decide and quit pressing.

I have to ask out of curiosity, and due to my own thread on the issue, which AI detectors are you going to use, and how are you weighing the results? Are there different levels of likeliness, or will it only post replies in threads that come back as "highly likely" to be AI-generated?

I use at least three different AI checking websites. Or more than three if even one of them doubts that the text is not completely AI-generated. I do not use the GPTZero website - I had too many false positives with it.

This is somewhat preferable to the previous plan, but my concern is what would happen if everyone disregards the JAPI response and proceeds with their discussion regardless of whether it was generated by AI or not, similar to this post https://bitcointalk.org/index.php?topic=5448187.msg62145641#msg62145641. Since there are currently no explicit forum rules against AI and no 99% proved AI detector tools, nobody appears to care and the moderator won't lock a thread just because JAPI says so. there is a light at the end of the tunnel but the challenges looks bigger.

[borovichok]

I guess now I'm going to be using JARPI as an AI-buster:

Look, I think this idea is better than answering questions!

But, based on the automatic text, I had a doubt:
Do you first manually validate the AI's suspicion and then post, or does it post automatically?
Or are you the one who suspects a topic, and puts the JARPI to analyze which then makes the post in case of a positive result?

Third option is correct. I ran OP's text through many AI detectors and all of them gave AI-generated indicators, so I fired up JARPI to send the warning.

Are you going to manually look for suspected AI posts, do manual scanning, and check whether or not it's AI created before triggering JARPI to act? I thought JARPI was meant to be a bot conducting this errand for you rather than you running the errand? What's the point if there's still a bunch of shitwork for you to do?

[joker_josue]

Third option is correct. I ran OP's text through many AI detectors and all of them gave AI-generated indicators, so I fired up JARPI to send the warning.

So basically you browse the forum normally, and when you think an OP was made by AI, you submit the topic for JARPI analysis.
Then it will analyze and if it concludes that the text was generated by AI, it will post the ad. This is it?

Thus, you stop worrying about analyzing these cases in detail, and you can continue to browse the forum normally looking for other cases. Seems to be an interesting tool, to free your time from those boring analyses.

Honestly, I find this option much more useful and interesting than answering repetitive topics.

[NotATether]

Are you going to manually look for suspected AI posts, do manual scanning, and check whether or not it's AI created before triggering JARPI to act? I thought JARPI was meant to be a bot conducting this errand for you rather than you running the errand? What's the point if there's still a bunch of shitwork for you to do?

This is a new idea, so the automation has not been coded in yet. I would definitely like to automate the AI detection part sooner or later.

Third option is correct. I ran OP's text through many AI detectors and all of them gave AI-generated indicators, so I fired up JARPI to send the warning.

So basically you browse the forum normally, and when you think an OP was made by AI, you submit the topic for JARPI analysis.
Then it will analyze and if it concludes that the text was generated by AI, it will post the ad. This is it?

Thus, you stop worrying about analyzing these cases in detail, and you can continue to browse the forum normally looking for other cases. Seems to be an interesting tool, to free your time from those boring analyses.

Honestly, I find this option much more useful and interesting than answering repetitive topics.

That's basically correct, but see my reply to borovichok. I'm eventually going to have this run through all newly created topics and run the detection automatically (using an API to some websites or Selenium).

This is somewhat preferable to the previous plan, but my concern is what would happen if everyone disregards the JAPI response and proceeds with their discussion regardless of whether it was generated by AI or not, similar to this post https://bitcointalk.org/index.php?topic=5448187.msg62145641#msg62145641. Since there are currently no explicit forum rules against AI and no 99% proved AI detector tools, nobody appears to care and the moderator won't lock a thread just because JAPI says so. there is a light at the end of the tunnel but the challenges looks bigger.

I guess I'll have the bot file a report every 24 hoursw for a period of 2 weeks, or until the thread is locked. Whichever comes first.

[joker_josue]

That's basically correct, but see my reply to borovichok. I'm eventually going to have this run through all newly created topics and run the detection automatically (using an API to some websites or Selenium).

Sounds good to me.

Just suggested that in this case, the autotext be a little different, just saying it's suspicious content and not making a direct recommendation for it to be reported. That is, to be a more alert text for readers to be aware of, and not a condemnatory text.

[Igebotz]

That's basically correct, but see my reply to borovichok. I'm eventually going to have this run through all newly created topics and run the detection automatically (using an API to some websites or Selenium).

Sounds good to me.

Just suggested that in this case, the autotext be a little different, just saying it's suspicious content and not making a direct recommendation for it to be reported. That is, to be a more alert text for readers to be aware of, and not a condemnatory text.

Is it possible to configure your proposed JARPI to behave similarly to the auto ChatGT bots on Twitter? It triggers whenever someone tags it in a post and provides extremely good analyses. If I see a suspected AI post that I'm not sure about, I'll just @JARPI on the thread to determine if it's AI generated or not. I think it'd be better this way than you doing all of the work. Create JARPI and make it available to anyone who needs it.