Avatar
PayPerQ
d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e
A polished and functional GPT5, Claude4, Gemini (and more) AI interface and API that runs on a pay-per-query model via Lightning payments.

Team PPQ visits Lugano for nostr:nprofile1qyv8wue69uhnzwpc9ccnzdewxg6zuv3nx5argwp58qqnyamnwvaz7tmvde3xjarn9eekzar0wd5xjumfvahxzmpwvdhk6tmwdaehgunjv4kxz7f02y69ynn2v4ehxqpqawnu9vg352863e7tqlc6urlw7jgdf8vf00tmr76uuhflp4nnn68s35x23h 's Bitcoin x AI hackathon

Can you elaborate a bit what you are asking? Essentially what you can do with it is create additional credit id / api key pairs. This could allow you to access our services even more anonymously or perhas generate key pairs for additional users that you may be onboarding. There may be other use cases we haven't thought of as well. Please let us know what you were thinking.

The team has been using the new qwen3-coder today and it is the first model outside of claude or gemini that is pretty consistently good. It still isn't the best, but for a fraction of the cost, it does really well. If you tried us before but were put off by the cost, it's time to try again.

Here's an anecdote from our CTO:

"It's still too early to declare a definitive winner, but it seems Claude is maintaining its leadership in coding capabilities. When tasked with converting an SVG to a React component with dark mode support, Qwen3-coder followed existing project file structuring but ended up creating multiple files: `components/ComponentName/index.tsx` and `components/ComponentName/ComponentName.tsx`. It also imported the `useTheme` hook and included light/dark mode logic in the code. Claude took a smarter approach, recognizing the simplicity of the component. It adhered to the project's file organization by creating a single file, `components/ui/ComponentName.tsx`, and used Tailwind classes like `fill-black dark:fill-white` for a cleaner, more streamlined solution."

Sorry it took so long nostr:nprofile1qyvhwumn8ghj76rfwejhgctvdvhxummnw3erztnrdakszrthwden5te0dehhxtnvdakqqgpc0rv4mdac2np6p5aj66mmlxlj3vmpv2lxgvn025sm5uw08dz6dyvfhn64 !

You can read our privacy terms, but in a nutshell, we associate queries to a credit id. And we collect user agent string from the user. If you switch around your credit id (or use our new credit id creation endpoint), you can achieve pretty good privacy.

You can now top up your PPQ account via API! Top up and work on your #chatgpt #claude #kimik2 #grok or #gemini projects and pay with #crypto #bitcoin #liquidnetwork #lightning

Image

When we did it it was only bringing back 1-2 notes, or in some cases 0. Here is the prompt:

"We want to make a website with a Nostr community board which displays nostr notes mentioning payperq or ppq, or anything from the npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h. The notes should be displayed chronologically. The grid should of notes should be 3 notes wide. In the top right the title will say "PayPerQ Community Board" in Roboto font."

Anything wrong with it in terms of how we describe what we want it to watch for?

Hi Alp, what in particular about the mobile web app are you having issues with?

Regarding the importing your credit id, you should be able to go to the account activity section in the top right and import it there. Let me know if you figured it out.

nostr:nprofile1qqsqgc0uhmxycvm5gwvn944c7yfxnnxm0nyh8tt62zhrvtd3xkj8fhggpt7fy nostr:nprofile1qqsr7acdvhf6we9fch94qwhpy0nza36e3tgrtkpku25ppuu80f69kfq9q9kky Hey guys! We are using Stacks to vibe together a website which shows all nostr notes mentioning ppq. It seems to really struggle when having to search for existing notes. Is there a particular reason why? Perhaps we aren't connected to enough relays? Or perhaps the relays are being lazy?

It would be cool if you could set certain fee rates for certain exact entry and exit channel pairs on your lightning node.

For example you could set the channel fees on your channel leading to kraken at 500 if coming from a forward that is routed from your wallet of satoshi channel, and 300 if coming from a forward that is routed from your acinq channel.

Not currently possibly, right?

openAI's new flagship model "o3" is now available:

You guys are talking about something I've been thinking heavily on for a bit now.

First, I'm a HUGE fan of notebookLM... and there IS an open source version of it! Podcastfy.ai!

I have actually thought deeply about how we could bring podcastfy to PPQ.AI but we haven't been able to get to it yet. I even went so far as to have a conversation with a friend about it and he gave me some thoughts on deploying it:

If either of you are interested, if I created a bounty for you to deploy this for me it would be amazing. If you are interested, let's set a call at some point because there is a lot more to explain.