• 3 Posts
  • 16 Comments
Joined 3 years ago
cake
Cake day: September 6th, 2023

help-circle





  • Hardware: I have a custom setup with a bunch of amd graphics cards. I will do a writeup about that sometime this year.

    I use opencode exclusively. It’s probably not the best harness but it’s the one that gives users the most control and I like that.

    The actual models I used for this work are Qwen3.8 27b - FP8 and Qwen3.8 - Flash - Next UD_Q6_K.

    I wrote my own agents with duty separation. Flash is the orchestrator and long-horizon guide. While 27b is the faster, more expandable worker. This combination feels about as smart as an opus 4.8 with maybe not as great token efficiency. For simple tasks, i use the worker directly. I have a ton of repo documentation and my agents have access to read and write to Forgejo, both for git and api (issues and PRs respectively)

    Maybe I need to write an article about this…





  • what zener_diode said.

    when i was setting up this version of my homelab (this is v2), i had to contend with how to run docker. The general concensus is that the “best” way to run it is Proxmox>VM>Docker. Proxmox>LXC>Docker is supposed to be viable too. Proxmox>Docker is possible but is not recommend.

    I have 20 active docker services with about 30 containers running all sorts of services and they’re extremely reliable under this setup. The only time I’ve had problems is when I ran out of disk space (128gb) because stale docker images weren’t pruned.









  • afk_strats@lemmy.worldtolinuxmemes@lemmy.world•1337 h4x0r
    link
    fedilink
    English
    arrow-up
    50
    ·
    1 year ago

    This is so on point.

    I get not wanting to compile your code. Its extra work and, if you’re already catering to a very thech-savvy crowd, you can let them deal with the variance and extra compile time.

    BUT if you’re releasing your code for others TO USE and you don’t provide reproducible instructions, what’s the point?!?