Isn't Shakespeare just nostr MCP platform for Claude + other small tweaks, like payment in bitcoin?

At it's most basic level, I guess you could say that, but I'd like to think that the code snippets, hooks, and components we created to build Nostr apps along with our own MCP are very valuable. And if you don't find value in that, perhaps you can find value in the ability to have user choice, more user choice than any other AI agent or tool that exists today. From which AI provider to use, to choice in LLM, to choice of deployment, to using a GUI or terminal or manual code editor, to switching LLMs, etc.

Deeper Nostr integration will only differentiate Shakespeare even more as the feature set grows. Imagine Nostr powered collab sessions with “no KYC” invite links! What about live-streaming built into the IDE for zap funding and for demo presentations! Nostr integration only opens more and more doors for every app!

Most of that is above a normies understanding though. Meaning Shakespeare's value, can't really be for people like myself. People just want to be able to tell ai what to build, and it just do it. Yesterday I had deepSeek spitting out 1800+ lines of code per reply, all day long. From 6am to about 8pm. And, changes just worked, no session limits, I didn't have to pay a sat, very minimal bugs, no webpage response errors when the chat gets long like I had with Claude, and lots of other minor stuff. It's pretty rudimentary, but for only telling ai what I wanted and having zero coding experience I was able to make my own lil game in a single Html file... Nspace.me Kinda goes into what I was talking about yesterday... They don't want to give us normies the tools to be able to do this for real. We would replace most things with stuff we built ourselves. They just want their data centers built so they can do it, while charging us to use it and limiting our ability.

that's the point, normies don't need to understand any of that. they don't need to know what's under the hood. they just need to see the end result.

I also remember hearing the name/word had something to do with, or originated from, shake the spear.

Right, i dont need to know whats going on under the hood....but from experience I've paid Shakespeare around $40 and got nothing burgers. Now I'm forced to look under the hood and see wtf is wrong.... And I saw that Shakespeare is just a nostr MCP platform sprinkled with niche features to draw folks in to generate income off people like myself. But bluntly, I got more done paying $20 once for Claude myself and using free Ai and I'm just trying to make sense of it. I still have like 3/4 of my weekly session time on Claude to boot....

I want Shakespeare to win, it's just not though based off my personally experience.

that's not true at all. it's way more than an MCP. there's actual code templates written that are part of the system prompt and part of the predefined code base so that you can just say build me a twitter like app or build me a bitcoin wallet, and for $3.61 worth of prompts, it builds it. you get what you pay for though. i won't use shakespeare with anything other than claude sonnet 4.5 as it's the top choice with the best production like results.

can you let me know what model you were using? and most importantly, can you share prompts that you've had issues with? i want to make it better for you and all non developers. and i can't do that unless i have specifics.

Sonnet 4.5. Basic prompts. As in this is what I want, please do it. Data collection is only bad if the data collected is used in a bad way. Ffs Vitor isn't even collecting anon data on amethysts most used features making it hard to actually improve long run.... 🙄 One Example, when I used Shakespeare to see if it could remake my now broken note scheduler. Buttons, wouldn't even be clickable. Then after spending $3 for buttons to be clickable, I notic3d the LN payment of 21 sats wasn't working and it ate the rest of my money thinking what to do about it, going over files, instead of just doing it.... Added more money for it to keep going. After, buttons where unlikable again and I couldn't even test the zap functionality it just ate all my money to "fix". Round about loops like this anytime I use it.

Send be some zaps and I’ll think about it. I’ll let you know when I need more zaps.

could you share your prompt? sometimes when things loop like this, it's best to start a new chat and start over.

The exact prompt was: lightning payments are not working. After a user pays the 21sats, the note scheduler page should come up for them to use. I should not have to start all over after a product/ service I pay for gets stuck in a money consuming loop. I didn't have to restart chats in deepSeek yesterday even with 1800+ lines of code in replies.... The product ot service just shouldn't get stuck in a money consumption loops... The ai thinking, shouldn't be a charge.

Yes.. This basically sums up my experience with Shakespeare any time I've used it.

thanks for the prompt. you can see deepseek with shakespeare if you feel it's better than sonnet. if it's spending tokens, it's a charge. that's not designated by us, that's designated by the ai provider. do you have a fully working version of this app that you built with deepseek?

I did my original note scheduler 100% free with deepSeek and chatGPT. All was working until something changed for LN o er the course of 5mo and now nothing I've made using it works. Like my rpg game with in game items you could by for sats. Everything works, except for using LN to buy said items.

Could the MCP part, (having the Ai go over nostr docs basically) be the cause of excessive token usage passed onto customers?

i don't believe so. it's the system prompt. it's massive. it's what teaches AI how to build nostr properly, amongst other things. we actually are working on skills, which will make the overall system prompt much leaner, which will in turn make building applications cheaper overall as you'd like use a skill (additional prompt, code, context, etc.) when you needed it.

I had a similar experience with a slot machine in Charles Town, WV.

looking back at your screenshot, this seems odd to me because Claude isn't a thinking model. this looks to me like it was GLM 4.6. we've seen this issue with GLM before, it's why we stopped using it as our own branded models and it's why i've stopped using it entirely. are you use you didn't originally try GLM because it was cheaper and then switch to Claude down below in the model selector. and did you try Claude after you switched to the more expensive model?

It could have been, I'm not 100% sure. It was my 2nd or 3rd project I tried. Others after this have been about the same but with "viewed" instead of "thinking". I just went to Shakespeare.diy to see what model is used as my default;

you can change that and it just remembers the last one you selected. i could be wrong but im wondering if what im guessing happend is what happened based on what im seeing on screen with the <thinking>. it just can't happen with Claude since it's not a thinking model and i've seen this output before with GLM. either way, i'll take this into consideration becuase we do want shakespeare to be the best it can be for non-devs. it's why we built it.

Can you please repost the link for cloning Shakespeare within Shakespeare? I have an idea.

Go here and scroll down:

Soapbox

App Showcase - Community-Submitted Apps Built with Soapbox Tools | Soapbox

Discover and submit applications built with Soapbox tools. Browse community-submitted projects, games, social platforms, and business applications....

Thanks. I also found out that I boosted the other post even. Now I was able to create this:

Shakespeare Act PEAR 🍐 - Open Source AI Builder

Build custom apps with AI assistance using Shakespeare Act PEAR 🍐, an open-source development environment

It couldn't create exactly William Shakespeare shaking a pear, but it has shaking pears as idle/loading animations. @Derek Ross @npub10qdp...arpj

That looks so cool!

I made this using Act PEAR by just prompting "Do something with pears.". https://pear-labs.shakespeare.wtf/