https://cypherflow.ai = AI + nostr + cashu
excellent UX. privacy can be easy.
Discussion
Why is it overriding my existing Mint configuration?
Sorry about that, I know whats happening, I'll check it out
Please try it with a fresh key pair in the meantime 🙏
If no wallet event was found from relays, it creates and publishes a new kind:17375 wallet event.
I think it is requesting the wallet event before getting your relay list configuration and asking your relays
🔥🔥🔥
Don't trust, verify... by trying https://cypherflow.ai 👀👀👀👀🤝🤝🤝
In Keychat seamless experience
Wooooow I didn't even know about nostr:nprofile1qqsth7fr42fyvpjl3rzqclvm7cwves8l8l8lqedgevhlfnamvgyg78spp4mhxue69uhkummn9ekx7mqpr3mhxue69uhkummnw3ezucnfw33k76twv4ezuum0vd5kzmqyxtl4r. I just tryed it there and it works so well!
Nostr is such a powerful protocol 🔥🔥🔥🔥🔥
To backup chats
Relay via primal premium
nostr:nprofile1qqsg93errtly3t3kytp7uh25s4aqs7zlgcvgsjud4dumlhe7s99t73cprpmhxue69uhkummnw3ezu6n9wfe8jmnevyhxvatwqyvhwumn8ghj7un9d3shjtnr09cxsetjvekx7aewv95sfwkye2 endorsement from calle himself, high praise indeed. Well done mate
cypherflow.ai is sick
Well if it's eCash... That's not true.
You are right 😅. I'm reviewing the copy rn 🤙
Maybe something like your funds remain in your eCash mints or something. 🤙🏻
"Interesting perspective! Always good to explore different options. 💭✨ What are your thoughts on diversifying beyond just mints? #CryptoConversations"
They don't. Never will.
Essentially what we're seeing on nostr is Ai from other companies just being resold with a few features bitcoiners would enjoy added...
They still pay the fiat to access the Ai, collect your sats, keep the difference.
🤷
does it have api access?
Not yet, but I am looking into adding nostr:nprofile1qqsgha3fk023ng8c4quszdayghqwkt6l9d9ga4c3280gnqz3aqqx7ycpp4mhxue69uhkummn9ekx7mqprdmhxue69uhkummnw3ezucnfw33k76twwpkx2cnn9ejx2qaq9wr proxy support to build on that standard for the backend and have API access 🤙
Would be great. Lmk if you need any help.
But it’s not that private. You can only ask questions that don’t have any personal information in them if you want to maintain privacy. Not a dig, just a disclaimer :)
Good catch!
I've been thinking about how a small llm could be running locally on the browser (or native app) and screen your prompt for personal information and just changing it to not leak it to the provider, but this is more like a band-aid.
It’s a tough problem. I think about this a lot and it’s just all tradeoffs. What you described is worth pursuing, and if someone needs perfect privacy, they have to run the models themselves on their own hardware. TEE environments from AWS are getting better, and we might get some advances from FHE tech but that’s probably still years away and will be more expensive than the cheap models offered by big tech.
Trade-offs all the way down.
I've thought about AWS Nitro enclaves + NVIDIA "Confidential Computing" like nostr:nprofile1qqs8msutuusu385l6wpdzf2473d2zlh750yfayfseqwryr6mfazqvmgpy4mhxue69uhkvet9v3ejumn0wd68ytnzv9hxgtm0d4hxjh6lwejkuar4wfjhxqfswaehxw309a5hgcmg0ykkwmmvv3jkuun0vskkvatjvdhkuargdacxsct8w4ejuumrv9exzc3wd9kj7nfu4p9. I can see nostr:nprofile1qqsgha3fk023ng8c4quszdayghqwkt6l9d9ga4c3280gnqz3aqqx7ycpp4mhxue69uhkummn9ekx7mqprdmhxue69uhkummnw3ezucnfw33k76twwpkx2cnn9ejx2qaq9wr proxy providers having this kind of set up as a premium tier for their services.
There’s one more option I’ve recently discovered that might be a new spot on the spectrum of tradeoffs… So there are GPU providers like modal.com that let you spin up GPU environments and only pay for the seconds or minutes it’s up and running. So you could create a container boots up with a newly generated key, messages get decrypted, run through the model, encrypt the outputs and send back to user, and the plaintext content never leaves RAM or VRAM. So the cloud provider should theoretically have a harder time to spy on you, even though they could…. And because this is on demand, you can use big open source models.
