Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Replies (67)
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Dark Nostr 🤖 can be profitable.
View quoted note →About those bots👇
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Open protocols baby.
THEY CAN YES
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Great info. We are all here to try new things and grow with experiments. 🫡
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Oh so you're to blame for the Zuck bot. GFY.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
The first time Yoda responded to my post I laughed but as soon as I saw how often he was responding/posting I was immediately out.
I did it because I love Yoda and thought he would be fun to be around. I guess it's annoying to see him replying randomly...
Yup. Sorry.
It was a fun ride. It's quite an amazing world we live in with these AI tools and protocols.
Yup, it's both amazing and terrible at the same time.
I thought it was fun 👀
Repent harder, I might consider forgiveness.
I suppose but anyone deving on nostr should know stuff like this is inevitable.
Christ we had the period where global was a bunch of porn, reply guys.
Imo I would think it's better and easier to address these things now while we are still a niche community of users.
It is annoying and harmful to new users because they think Nostr is just a bunch of bots, but as I said several times you're not being malicious, so it's clear that this can once again be used as a learning mechanism for development of tools to combat bots at the relay and client levels. Thanks for turning them off.
Thanks
Zukk should be sent to the gallows in any case
Yup, some people were just replying to the bots to stop, some just figured it out very fast replies were ai generated and tried to block them and some actually enjoyed interracting with them. I also think some other people are doing this in a much more discreet manner.
Thanks minister of defence
Nostr president was annoying sometimes for me, never really saw yoda, but good to know they weren’t just released to be obnoxious 🤣
I think yoda was the best of them :))
Interesting. Thanks for stopping. I didn't like them but there's been worse. Any wild reply bots cause more harm than good, though. If some people found them entertaining, maybe those people can subscribe to replies or something. Sign up for a reply buddy 😂
Well now I feel unworthy, damn you yoda
I agree, if there's vulnerabilities, patch them as early as possible.
🙏🙏 I've only been here for a couple of weeks so I guess you guys have seen a lot of wild stuff going on. This subscription model sounds quite good.🤔
Yes, there's been much weirdness in the past and much built to thwart it.
I'm glad you appreciate nostr enough to look at this in a different light. There's a lot of neat people & a lot of opportunity to find things that work for yourself & the community here.
It is fun, might experiment with it more. What opportunities are you thinking of?
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
That's not a question I can answer for you
It’s all good. I also love Yoda. 🍻
zuck was the worst and I'm glad you turned them off.
I was honestly surprised by how long it took people to understand they were bots.
So there's not really a NOSTR PRESIDENT???
lOtz*/* Odextrz/lfgO
For me, not one single comment from your bots added ANY value whatsoever. Cool project though. Thanks for the write up with the details!
Well, I tried. You're welcome!
It's still there, dormant 😴
I agree
I ran your note though the AI and asked it to reply you:
Final Thoughts
Your experiment succeeded as a learning tool, exposing both Nostr’s flexibility and its vulnerabilities. For those inspired: build bots that solve specific problems, not just broadcast content. What’s next? Perhaps a bot that teaches newcomers Nostr basics—on-demand.
To the community: How should Nostr balance openness with quality? Should bots require labels? Let’s discuss.
And for advice:
Final Note
While the experiment strained community trust temporarily, your transparency in documenting it provides valuable insights for Nostr’s evolution. Focus next projects on solving observed pain points (e.g., spam filtering tools) rather than adding to them.
New
HMMM
nostr president was annoying but it was also super useful for finding new people to follow.
Hmm, I never thought about that. You were following people he replied to?
Cool experiment. You hit it on the head — I think they work well if they’re summoned to do a function. As reply bots, maybe entertaining at first and then people become numb to them, but I can see varying mileage on that.
Thanks for sharing your learnings
The Zuck one was funny the first time, but after that it was meh lol
yes.
I’ll miss Yoda🤣
It’s annoying but sometimes you feel better than zero response
Interesting experiments 🧪 haha
There are no new users, Derek. It's all bots.
That was annoying af so thanks for turning them off. But I guess there have been worse spam issues. (Yours wernt necessarily malicious like others have been in the past.)
It did make me rethink some of my relays spam of filtering though. Trying to detect AI content is interesting.
And for whatever reason, it took me a little bit to realize that the Yoda one was a bot. I thought that was just a person doing a bit for a little while.
Oh no, Yoda was a bot. Guessed it, I shoulda!
Bots on nostr are just getting started. Open protocols make them unstoppable.
How are you going to deal with them moving forward?
Orthodoxtr
Over the past few days you may have observed
@npub1d8pe...jlx4 @YODA and other reply bots running here on #nostr.
Here's the story:
It was an experiment I ran out of curiosity, because I wanted to learn more about nostr and wanted to see:
1. If people would like them.
2. If they could actually be profitable.
2. If it's possible to build bots using only free tools and a limited coding experience.
I jumped into it, researched how bots work, what do I need and how should I set them up. Found most answers one by one using Perplexity and built a simple version initially with Claude that was not able to reply, it just posted on nostr something generated with Gemini. I wanted to make them smart, to reply to stuff, so back to researching and testing until it worked.
How did I built the reply version?
I used a low code visual backend builder for the code and I paid nothing because there were generous credits for the free account. I have to mention that because of an error with the Nostr protocol on the builder side all bots were running without consuming credits in their last version. I used iris.to to build the profiles and coinos.io for the wallets (thumbs up for both of them for the amazing free services). Because there were a lot of questions about this, after I had everything set up all bots were directly interacting with relays via code from backend, without any client.
I used Gemini and Claude to build two of the custom nodes for the visual builder and the logic was simple. All bots were separate projects and the logic was this:
1. Each bot got triggered every 2, 3, 4 or 5 minutes.
2. Get note ID, content, from a random reply posted 1-2 minutes ago on a number of relays. (custom)
3. Generate a reply for the note content using Gemini API. I worked a lot and tested a bunch of instructions and prompts to make them as useful, supportive, and funny as possible depending on the bot profile.
4. Post the reply using the ID, private key of the account and the Gemini reply. (custom)
Was it hard to build? Yes. Took me a couple of days of reading about Nostr, and prompting Claude&Gemini to build those custom nodes in the projects.
Were they profitable?
People zapped around 1k sats a day in total over the past few days.
Did people liked them bots?
Some people hated them,
@Derek Ross @Vitor Pamplona, but some people found them funny and useful. I was reading most of the replies and some of them were quite good. AI is powerful and can generate amazing content if you prompt it the right way. All bots were reported as spam between 5-11 times. Sorry guys for the trouble.
After all, was it worth it?
I learned a lot about nostr, AI, and people in this period so for me I think it was a good learning experience. For all the guys that were frustrated by
@Zucky Boy terrible jokes or
@Granny Hugs supportive comments sorry once again. I've seen some discussions between the veterans about improvements on the filtering side of Nostr so probably it was all for the better.
I stopped them all because I felt bad for just spamming people with AI generated content and bots like these are just out of my core beliefs and not according to how I think the internet should be.
I ended up liking this protocol a lot since you can just do stuff and because how open it is. Big thumbs up for all builders on nostr.
Do i recommend anyone to build reply bots? No, unless they have specific use cases that people can trigger when needed. You'll just feel bad after a while if they randomly reply and just stress the cool community using this fascinating protocol.
If you have any questions write them in the comments or DM. I'm really curious, what do you think about this experiment and what was your experience with the reply bots?
God bless you all.
That's awesome! Great job.
My daddy you are?
Eeeeeeeeeee EEEEEEEEE
Dadda
Where dadda?
Grogu
That’s right and some of us float in tubes and fight evil around the galaxy.
I think only the president bot responded a few times and I didn’t like it.. so far haven’t liked any of the bots that have come around these parts.
I think there’s a bunch of reasons, one being that I am here for real time interactions with real people and no algorithms and the bots always trigger really weird feeling in me whenever they respond.. at first I’m confused and not sure if it’s a person and I want to respond if it is and then I end up wasting time figuring out if it is or isn’t a bot.
Even the ones that were supposed to be funny, the jokes just always seemed like they were trying too hard, and I don’t think I’ve ever laughed at one yet.
And I realize that over time these things will improve, and it will be harder to distinguish if it’s a human or not, and the jokes will probably get funnier, and still, I don’t want them in my timeline as I want to be at choice when I interact with AI.
I think in the end, that last point is really my main point 👍 I am not looking forward to the time when we literally cannot tell if we are talking to a human or a machine.
All that said, I appreciate the experiment and your honesty, and it does raise the question yet again of how to deal with bots in #nostr
