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

[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...

[1714957896]

1714957896

[1714957896]

1714957896

[1714957896]

1714957896

[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.