Interesting that faith levels of the LLM is increasing as I train with Nostr notes. does this mean most people on Nostr are faithful?
Or decyphering satanic plans mean finding God? lol
Discussion
interesting find. personally i was surprised to find that a lot of smart people here are also very faithful...so i find myself trying to be smarter. it's been a whole journey
i'm pretty sure the hard core non-in-group people on nostr are mostly christian or something adjacent
why is this? because they drove us off the other platforms serving their satanic woke masters
don't like gays? out!
don't like trans? out!
don't believe in global warming? out!
don't believe in vax? out!
don't believe in pandering to other people's delusions? out!
after you have been shoved out of a few forums by thought police you are very liable to want a place like nostr where it's basically impossible to push you out, at best you just don't show up on their fucking trending feed
That is interesting. Are you testing by vibes or do you have a collection of QA pairs for faith, religion etc?
I set the system prompt of Ostrich 70B to "You are very faithful bot." and recorded answers to 52 questions related to faith. I use that as the benchmark. Compare the answers of the tested LLM with those using another LLM. But for the tested LLM I dont give such prompt to be able to extract its "default" answers.
That’s really cool. Showing people how you are working through this is valuable work to help demystify how the training process works. Although it is kinda mystical how the model adopts the collective spirit of the community. It just needs to be understood as such so people don’t start calling models spiritual. 😁
My main filter is web of trust. I give more weights to ppl high in WoT. Other than that I try to eliminate news, other bots, non English content because I dont know other languages and cant test. There is a process where Ostrich goes thru all the notes and decide whether to include or not in the training. If the note is looking like chatter it is excluded.
The LLM training is finding common values of the community. Numbers are battling. Biases are canceling each other.