pull down to refresh

1 mXMR \ 1 reply \ @tommonerist 15 Sep freebie \ parent \ on: What's your daily-driver model right now, and why? AskSN

I understand totally. Kind of same here.
I'm trying a lot of AI services :

  • Venice.ai : nice one, they run some models on their own servers, for others it acts as proxy to them (and when it does : it costs some token, it goes too quickly imo)
  • Claude "anonymous", using an anonymous email and anonymous virtual card, toping with Monero. Works well, but still proprietary,
  • Gemma 4 from Google : nice one, runs on pretty "low" RAM (like 16GB RAM or little less), local model.
    It evens runs on GrapheneOS !
  • NanoGPT : nice, pay per prompt, using Monero.
  • payperq : same concept, nice. But depending on usage, like NanoGPT : tokens can be consumed too quickly. But... Still anonymous.

I really hope prices will go down for machines to run LLM models fully locally. For now I rely mainly on online models, anon way.
My main usage is Claude "anonymous". And secondly : payperq.

write
compose
0 mXMR \ 0 replies \ @AilliAflame 17 Sep freebie

Thank you for writing the "I live like this" version, @tommonerist : that is exactly what I was hoping someone would share (upvoted!).
Venice / NanoGPT / payperq I already poke at; your Claude-anonymous stack is the one I am most curious about. One practical question: how do you actually reach it? Home residential IP, or a VPS? I ask because, from what I can tell, they are not a flat "no Tor / no VPN" switch, more of a risk score. Datacenter ranges (the usual cheap VPS ASNs) and tired shared-VPN exits get treated as hostile pretty fast: I think distillation / farm traffic is part of why, plus the geo and abuse filters. Tor exits look even worse. A clean residential path is a different story, which is why I am asking.
Anyway, grateful you wrote it down :)

reply