Skip Navigation

Posts
43
Comments
937
Joined
2 yr. ago

Interests: programming, video games, anime, music composition

I used to be on kbin as e0qdk@kbin.social before it broke down.

  • He writes out the entire code, and it works every time.

    Well, I'm not sure if they're entirely human if it actually works the first time every time -- but they're definitely not any of the LLMs I've encountered... :-)

    I'm thinking obsessive about work (never mutes their phone type) and using AI tools. Politely check (preferably in person) to make sure you're not waking them up in the middle of the night with off hour requests; there are some people who feel compelled to respond to everything immediately instead of getting back to you the next day.

  • May the Fourth be with you

  • Yes. htop does it, for example.

  • I have only the most basic experience digging into that stuff -- from quite a while ago -- but the keywords I think you need to search for to find out more info about this are: escape codes, TUI (i.e. Text User Interface), and curses.

    The last is an old library for implementing TUIs. There's successors like ncurses as well. I don't know what people actually use currently though.

  • Miku/Teto version:

  • Or you mean local HTTP?

    Yes, I mean local HTTP. ollama listens on port 11434 and responds to HTTP requests by default. I'm not sure what llama-server uses by default, but like I said, I'm pretty sure you can do the same (or at least something very similar) with it.

    I was actually asking more model type.

    OK, I see what you mean. I'm still too new to LLMs myself to have a good answer then on that beyond saying that I know it works with qwen3.6 and gemma4 from having actually experimented with those specifically.

    I did a little nlp

    I mean, something like:

     
            result = result.replace("json", "").replace("","")
    
    
      

    is good enough in practice for the kinds of things I've been doing. (I'm dealing with cases where triple backticks should never appear in the output though; you might have to get more creative if you want a result that has that kind of quoting embedded in something else...)

  • Edit: Alternatively, does anyone have thoughts on the requirements on the model side of things to make this?

    If you're talking to a model accessible via HTTP you can interact with it via a chat API. You track the messages sent back and forth yourself and post the whole conversation to the end-point each turn so that it has context. I've been experimenting with this using ollama, but I'm pretty sure you can do it with llama-server too.

    I'm not sure if I know how to get the LLM to give me reliably parsable output...

    Prompt engineering + sanity checks in the client side code + retries. There are options for requesting structured output specifically too. They might or might not work... I've had decent success getting qwen models to output JSON with prompts that include things like "Output strictly valid json. No extra text." or similar. Sometimes it will quote things with triple backticks or triple backticks + "json" at the top of the reply -- which is easily fixed by string manipulation on the client. Occasionally -- especially with complicated prompts -- it will go off the rails and give me junk that I've either needed to fix by hand or automatically retry later. It works well enough that I've been able to do image analysis in batches with it successfully.

    I don't know anything about the specifics of LibreOffice extensions though -- never worked with those personally before.

    Edit: If you don't want to go to all the effort of writing a whole extension for it, you can also just paste the context into the model running in the terminal. Put the whole document early on in the session (quoted with backticks). Then ask for refinement by quoting snippets with the comments for revision you want to do. I haven't done this for English language editing, but I have tried it for sanity checking my own hand written Python code. Sometimes it gives good suggestions (e.g. it caught a few typos I hadn't noticed yet when I tried this yesterday) and sometimes it doesn't -- your own judgement is, of course, very important.

    Edit 2: I've found it's sometimes useful when I'm providing lots of text to include a description of what info I'm providing, then an instruction like "Say 'OK' to proceed." followed by something like "The whole file is: ...". That way I can provide context into the session without it wasting a lot of time trying to deduce what I want to do with it before I'm ready in a strictly user/assistant/user/assistant/... chat conversation mode.

  • Generally the professor in charge of the research group.

  • Is BotBall still a thing? They had that (waaay) back when I was in high school, at least.

  • Congrats. I groaned IRL.

  • ~2011?

    2016 or later for MHA anime.

  • Is the path a file or something? On my system the corresponding path is a directory with a bunch of symlinks in it. The directory has user/group matching my account with permissions set to 755. (i.e. rwxr-xr-x)

  • I'm not really sure what to make of that other that guessing that something's gone wrong with podman's internal state handling. Did something you ran recently crash maybe? (I'm assuming podman ps used to work for you, right?)

    My kneejerk reaction is "try rebooting". If it persists there might be something odd going on with file permissions perhaps?

  • Judging by OP's history, the title seems to be missing the critical words Davinci Resolve for what they want to get working.

    I haven't tried to use that program before, but their website says they have a Linux version. It's not clear to me what distros they actually support though -- it just says "Linux" on their downloader and then pops up a registration form which isn't very helpful for trying to provide assistance...

    I did a search and found a thread from ~2 years ago about running on Mint specifically with an AMD card that might be worth a look if you're running similar hardware: https://forums.linuxmint.com/viewtopic.php?t=426123 -- probably not relevant with an NVIDIA card though.

    If you can't get it to work natively, you could try running the Windows installer under Lutris or Heroic or similar (treating it like a video game) and see what happens, I guess.

  • Hmm. So... how long do you think before we start seeing news stories about their DRM servers getting hit with DDOS attacks (or other network fuckery) and no one being able to play their PS4/PS5 games? 😛️

  • I deal with a lot of scientific imagery for work and I've recently started experimenting with what I can do with local vision capable LLMs (e.g. qwen3.6, gemma4) to cut down on some of the really tedious parts of the work and improve maintenance processes. The fact that they can just do OCR automatically on labels burned into the image and then combine that with a comparison to additional images and output a judgement is very useful...

  • Better out-of-the-box text-to-speech voices would be very welcome. The defaults are pretty painfully robotic... (Try spd-say "Hello world" if you don't know what I mean.)

    Trivial to use on-device dictation software could also be useful.

    The capabilities of models like qwen3.6 to do things like on-device image analysis are pretty incredible if you have hardware capable of running it -- I've run it on a Framework Desktop -- but I have no desire to expose my systems directly to AI agents. That's just asking for trouble... If an AI agent can fuck up, it will fuck up eventually, and I'd rather it not have the ability to delete my files when it does.

  • Check https://vndb.org/ if you're looking for something with particular themes.

    If you just want something straightforward, Yuzusoft makes decent moe dating VNs -- good art, decent music, voice acted, fairly polished (and configurable) UI. Kind of weak on the writing though, unfortunately. I've played Cafe Stella and Riddle Joker (plus Parquet from their all-ages imprint, but that one's a bit different). I've heard good things about Sanoba Witch in particular, but haven't played that one yet myself.

    Next on my list of moe VNs when I'm in the mood for this stuff again (I've been out of it for a bit too) is Ao no Kanata no Four Rhythm. That seems to be fairly highly regarded, but I haven't played it yet (beyond opening it up once to confirm it works on my system -- the intro song is pretty good) so I can't give personal thoughts. It's a fantasy-sports drama (flying shoes)/moe dating VN, IIRC?

    If you want to try something non-anime, Being a DIK was pretty entertaining. It's a "college movie" in VN form with some mini-game elements reminiscient of Bully. S1+S2 is pretty lengthy and worth playing as-is, but the story is still incomplete FYI.

    Outside of dating sim and moege VNs there's quite a bit of other works with varying levels of gameplay that often get lumped into the VN category. e.g. Ace Attorney, Danganronpa, 999, AI: Somnium Files, etc. are pretty entertaining. If you want something with AO/sexual content in this VN-adjacent category, maybe try Evenicle?

  • Isn't there also a chemical method to do it? I'm not a chicken farmer though. Maybe even with that it doesn't make sense economically.

    Still though, it feels like there's an opportunity there that a creative marketing campaign could exploit to transform what's currently a waste product into something more valuable. If not "Premium Chicken" then maybe "Ethical Rooster Meat" or an "Eat the patriarchy!" angle or something. Selling the sizzle rather than the steak, so to speak...

  • Touch Fluffy Tail @ani.social

    Touch Fluffy... Tails? (slyger ex)

  • Anime and Pics @reddthat.com

    Task Failed Successfully (naoyuki arts)

  • Anime and Pics @reddthat.com

    6:21 (Bad Morning every humanity.) -- by muni rice

  • Offbeat @lemmy.ca

    Giant underground pipe mysteriously rises over 30 feet, bursting through road in Japan: "I can't believe this"

    www.cbsnews.com /news/giant-pipe-mysteriously-rises-30-feet-japan/
  • World of JRPGs @lemmy.zip

    Final Fantasy VII released on GOG

    www.gog.com /en/news/final_fantasy_vii_is_now_out_with_a_limitedtime_discount_alongside_classic_final_fantasy_deals
  • KemonoMoe @ani.social

    Wolf Girl (by flippy (cripine111))

  • Programming @programming.dev

    Critical Security Vulnerability in React Server Components

    react.dev /blog/2025/12/03/critical-security-vulnerability-in-react-server-components
  • Anime and Pics @reddthat.com

    Rainy Day (hakusyokuto)

  • Anime and Pics @reddthat.com

    What's on your mind? (sat0 manga)

  • Anime and Pics @reddthat.com

    Pinky promise? (test norma1)

  • Anime and Pics @reddthat.com

    Commute (tensen_(dotted_line))

  • MidriffMoe @ani.social

    おへそ (by mahcdai)

  • Anime and Pics @reddthat.com

    Fish (onoconokoko0625)

  • Anime and Pics @reddthat.com

    For you... 🌹️(catzz)

  • 196 @lemmy.world

    Rule

  • Anime and Pics @reddthat.com

    Redline x FLCL (tiagoom)

  • Hollow Knight: Silksong @redlemmy.com

    I... finally did it. I beat Silksong.

  • Anime and Pics @reddthat.com

    Kirbey (watanabe itsuki)

  • Megumin @ani.social

    Hey, Kazuma... (yilx)

  • SmolMoe @ani.social

    Link and Romani (nshi)