okay weekend is over
i promise i'll make a weekly poll tomorrow
librekitty
librekitty@blitzwalletapp.com
npub1wp2l...hpv0
🙋♀️👋 hi! i'm a FOSS zealot, game developer, and lifelong learner 👹👾📖
freedom maxi, solarpunk, cypherpunk, and anarcho-communist (anti-statist/anti-stalinist) 🌞💻 🟥⬛
centralization is the root of all evil
looking to connect through this protocol 💜🫂
zaps/XMR to me is optional, feel free to save your sats 💜⚡
🇺🇸🏳️🌈🏴☠️
contact 💬:
- white noise: npub1avxs6urpqyflcrua027e53kure5emfwhhqf5khf2np7rcc0gkvdqcwsa2t
- simplex: https://smp18.simplex.im/a#I1NyhGz6I1w-MTn-hS8IabZJoCNL3mZ7hkrqh1WAN2M
- matrix: @mewmeow:matrix.org
- XMPP: badcodecat@conversations.im
can i point #Amethyst (F-Droid build) at my own translation endpoint?
i am trying to get the android SDK installed (with AI help). it's a struggle
my "everything app" needs to be built
#Android
running cosmic on desktop!
today my AI server is a android build server
best model for cpu/low ram?
looking for something that can do tool calls primarily
#AskNostr
first time ->
me: "hey LLM go do SomeTask"
⏳ 30 minutes later: done
me: *hmm that took bloody ages* "okay take what you learned here and make this a skill"
next time ->
me: "hey LLM go do SomeTask"
🚀 a few seconds later: done
it's such fun
#AI #LocalLlama #Skills
big and not-so-subtle reminder that anyone can cook
my agent actually wrote a patch for app-office/dia so i could install it
that's actually the kind of stuff i won't do on my own, so that's fantastic
#Gentoo
okay so instead of watching youtube shorts, i watched sermons
top-tier activity when lazily waiting on agents
what do you do to pass the time? #AskNostr
learning lots of gleam (and associated SQL)
my LLM is "self-improving" in a way:
- writing it's own skills/tools/plugins
- documenting it's mistakes and noting them for future
- tuning the LLM runner parameters
💪🤖
i think yesterday was the first day in a while i didn't post
my bad, i'm not trying to make nostr deader
my sleep schedule might be ruined but my agents are not
in other "vibecoding" news i'm now running hyprland (totally not worth it, better to write config yourself)
i just wanted to see what it was capable of
decent red theme, it was 90% complete
using llama.cpp latest has solved most of my issues, it seems
now just add time, and hopefully a project pops out 🤖⏳
okay update on the vibecoding
using opencode now (rip goose)
it's working "better", and the LLM decided to write tests for itself and test the code, so that gives me hope
in another tab, i had a LLM create a gitea account (on my instance), then a skill for how to use it
a mix of frustrating and fun, but i feel progress is being made
#Vibecoding #AI #Opencode
LLM-based jev! open source and works with existing models!
#AI #Jev #LocalAI