How is everyone accessing LLM’s privately and in a censorship-free way? Are people using Venice or what other options are out there? #asknostr #ai
Discussion
ChatGPT Proxy: https://cascdr.xyz/?tab=gpt
Open Source Perplexity (Search + LLM): https://pullthatupjamie.ai
E2E Private Access to Llama by nostr:nprofile1qyshwumn8ghj7en9v4j8xtnwdaehgu3wvfskuep0w3uhqetnvdexjur5qyfhwumn8ghj7ur4wfcxcetsv9njuetn9uqzphchxfm3ste32hfhkvczzxapme9gz5qvqtget6tylyd7wa8vjecgaq9enl : https://trymaple.ai/chat
Sorry first link was wrong:
Thank you, I’ll check them out! 🙏🏻
I run them locally
the only truly private way is to self-host it. Censorship is usually applied at the model level tho, so you'll have to find uncensored model
Yes. Are there truly uncensored models? (That are easy to access for normies like me…)
It's pretty easy with a gpu and lmstudio. Download the models from hugging face. It's all point and click. Significantly less powerful but still useful.
Disconnect from the internet and then run them ensuring nothing leaks out.
this is most likely an overkill, I have not seen LLM server/client that collects telemetry yet
I would rather prefer to not use proprietary (closed-source) apps like LM Studio
waht about jan.ai?
this looks interesting, i'm installing it and pulling the llama 3.2.3 instruct Q8 model
probably not gonna spend a lot of time playing with it but maybe i can teach it to analyse my code and help me focus my refactorings to the messiest parts
Not overkill if you want assurance of something.
Also, why not via ollama?
I mean, you can always go extra mile if you want, but it doesn’t matter as much because they are offline by design
LM Studio was proposed in another comment, that’s why I mentioned it
In ollama I don’t like that you can’t choose your own quantization level/method (or I just haven’t figured it out). Nevertheless it’s a great server
This seems interesting
https://primal.net/e/note1temewxuyydrjakgfudwdnqp6rk9zcp5jfd8rq5axucds8ngh6c8suh4f0s
Thanks nostr:npub1tc4q7lfxgeet0d3afacnxrlgslcywgfgagtczxm764tx8ytww26s8g0f8j for that question
which lead me down that rabbit hole
Perhaps duck.ai is an accessible compromise, with some open source models among the available options? Haven't tried Venice, and they do at least seem to accept bitcoin as payment for Pro, but it's a shame they launched an ETH token alongside...
Thank you, I’ll check it out! I like the simple UI of Venice. And I think people can use it while being completely unaware of the token 😄