Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)F
Posts
6
Comments
742
Joined
3 yr. ago

  • LLM are just text predictions based on what people would say in available digital works (like comments). Its honestly a fascinating glimpse in online sociology.

  • Right! Like if we could honestly further enhance that feature its an incredible increase in compression tech!

  • This would be like playing DnD where you see a painting and describe what you would do next as if you were the painting and they an artists painted the next scene for you.

    The artists isn't rolling dice, following the rule book, or any actual game elements they ate just painting based on the last painting and your description of the next.

    Its incredibly nove approchl if not obviously a toy problem.

  • Honestly I thinkyour self driving example is something this could be really cool for. If the generation can exceed real time (I.e. 20 secs of future image prediction can happen in under 20 secs) then you can preemptively react with the self driving model and cache the results.

    If the compute costs can be managed maybe even run multiple models against each other to develop an array likely branch predictions (you know what I turned left)

    Its even cooler that player input helps predict the next image.

  • The project looks amazing! It looks like its initial use case maybe closer to SEL4 in the trusted computing space but if it can support containers I'm pumped to try and get RKE2 running on it.

    The thought put into DevX really is the nicest part to me though.

  • Better VR tracking here we come

  • Why does this and maybe something to replace the title with just an accurate thesis statement kind of titlesounds so good to me!

  • 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

  • Static? I mean for most of the web it honestly seems like the move. HTMX?

  • Makes sense when try to work through a complex logic flow that you just aren't sure about.

  • Annoyingly self reported chinease users I used to talk to would go dark after mention a certain square, tanks, and massacre. Since the push for misinformation instead of censorship its been less common but it also just seems like there are less people from China in my internet social circles now too. :/

  • It depends on how the immigration process works. Assimilation is a very real thing

  • Oh I guess the fact that ideology is not innate and change change just makes that a mitigatable issue to me.

  • They went out of there way to say "not race or ethnicity" so I guess I feel that should separate out normal immigration rhetoric in my mind.

    If taken in good faith

  • I agree with most points except immigration since the workers compete in the same global economy except corporation get to pick the workers and laws ala cart while workers get stuck where they are born with huge hurdles to change that.

  • I was really impressed by the lulzbot manual mentioning this! Its also important to consider that most 3d prints can be sensitive to water unless sealed too.

  • "How to rewrite your first rust project" meme is pretty funny. Maybe we just do some interopt and the eco system can gradually migrate as new and better ideas need programmed?

  • Thanks Brandon

    Honestly I'll hope reservations and congratulations till after we see how it goes, but the fact it's a limited pilot makes me optimistic.