• 0 Posts
  • 64 Comments
Joined 1 year ago
cake
Cake day: August 11th, 2023

help-circle










  • I will say part of problem is knowledgeable volunteers will almost always want to just cp and paste a command string over the docs needed to walk someone through doing it in the current version of GUI.

    I’ve done both. Repeatable user instructions for GUIs IS NOT FUN. Maybe if we can get some automation to turn vague directions into detailed ones and better yet testable (supporting something like OpenQA) it might help lower the burden for a project to do so.


  • “Do not let has been burden what could be.” /s

    I agree though, other common UX replication options would help user meet the OS where they are more. I also agree that most common system administration and user UX should be doable in a full GUI, they are just so nice for when you don’t know what you are wanting but will once you see it.

    I also think VUI (voice user interfaces) would bridge the gap for a lot people and NLP would cover most of the worlds population.

    Honestly people keep working on and it ebs and flows in progress. Its just a lot fing work to do it well. One day we will get to doing most functions with multimodal interface support (GUI/CLI/API/VUI/NLP/BCI?).


  • I have a mention in forward with a note being “the only documention left was a series of desperate sounding emails that the documentation was still on the now quarenteened work computers and something about a README”

    THIS HAS HAPPENED TWICE TO ME, like I appreciate my bosses and PMs being chill and not wanting to overwork me on my way out but seriously guys I needed to hand this off to someone and put it somewhere. shrug








  • Very much pro Open Source AI. Especially as a concept digital public good. With https://petals.dev/ being the most promising option that regard (imagine something like RAG for the arch wiki with very large models supported by the community!).

    It feel very enthusiasts right now. Where I feel like I’m just on the cusp of having usable set up.

    I personally really want a full Dev that just takes gitlab issues and runs codes against tests until it passes, and then cycles between attempting to explain what it doing and refactoring until that explanation is reasonably simple, then submit PR.

    At the moment I am trying to use it as a copilot (ollama lama3, continue, and devonAI vscode plugins) all on my MacBook (my Linux machine were too small gpu wise, at least first time I attempted). That said it ok for questions no real luck on a decent experience for actually making anything.

    The next step to me for it to move from enthusiast to hobbiest would be:

    1. Models that just work on my machine. I had to do a lot of trial and error just get performant models.
    2. Models just my use case. I don’t know what model support tooling, or multimodal inputs. What models are actually optimized for programing, for actions (ala openinterpretor), for reviewing documents, etc.
    3. For federated (like pedals.dev) I feel like I need some sane data guardrails. I don’t want my medical documents anywhere near “bittorrent style” anything, but would absolutely love to leverage it for better outcome on opensource projects without secrets file. This also feeds into point 2 to me.
    4. More sane RAG. Maybe even IPFS links to caches or DBs for popular data sources (like code docs for example).

    I feel like there has to be a better way for this. Maybe its just selinux rules for data tags for locking down my local system and some routing config file at the root of my projects. Idk tbh