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

[1714191745]

1714191745

[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.