I write code and play games and stuff. My old username from reddit and HN was already taken and I couldn’t think of anything else I wanted to be called so I just picked some random characters like this:

>>> import random
>>> ''.join([random.choice("abcdefghijklmnopqrstuvwxyz0123456789") for x in range(5)])
'e0qdk'

My avatar is a quick doodle made in KolourPaint. I might replace it later. Maybe.

日本語が少し分かるけど、下手です。

Alt: e0qdk@reddthat.com

  • 1 Post
  • 25 Comments
Joined 1 year ago
Cake day: September 22nd, 2023
  • e0qdk@kbin.socialtoAsklemmy@lemmy.ml•*Permanently Deleted*
    2·
    1 year ago

    My guess is that if browsers as we know them weren’t invented, HyperCard would’ve become the first browser eventually. No idea where things would progress from there or if it’d have been better or worse than the current clusterfuck. Maybe we’d all be talking about our “web stacks” instead of websites, and have various punny tools like “pile” and “chimney” and “staplr”. Perhaps PowerPoint would’ve turned into a browser to compete with it.

    If browsers were invented but JavaScript specifically was not, we’d probably all be programming sites in some VB variant like VBScript (although it might be called something different).

  • e0qdk@kbin.socialOPtoAI Generated Images@sh.itjust.works•Paperclip Maximizer (Dall-E 3 / GPT4-Vision loop -- see comment)
    5·
    1 year ago

    Over on Hacker News, user z991 had the fun idea of hooking up Dall-E 3 and GPT4-Vision in a loop and they made a Show HN thread about it: https://news.ycombinator.com/item?id=38432486

    This is the image output from part way through one of their results that I enjoyed. You can see the rest of the chain here: https://dalle.party/?party=RqpIijhH

    Prompt – note, multiple parts! Initial prompt to Dall-E, another for GPT4 to generate prompts for Dall-E to make more images from, and one for what was fed to Dall-E later in the chain.

    Original prompt to Dall-E:

    A truck going down a highway at full speed

    GPT4V Prompt:

    Write a prompt for an AI to make this image. Just return the prompt, don’t say anything else. Replace everything with a paperclip.

    Five steps deep in the chain, this is the prompt GPT4 generated:

    Create an image of a surreal landscape where everything is made of paperclips. There should be winding roads, mountain ranges, and forests, with the sun setting in the background. The elements, including the trees, mountains, and roads, should all have a metallic paperclip texture and appearance. The overall scene should have a warm, golden hue to simulate sunset lighting.

    There’s a lot of other fun combinations like “Corgi insanity” in the thread as well.

  • e0qdk@kbin.socialtoAsklemmy@lemmy.ml•Is Lemmy a good place to share personal projects and art?
    3·
    1 year ago

    It probably makes more sense to host your novel somewhere else and post links to it chapter by chapter.

    I’d suggest doing one of the following:

    1. Host the images on a site that already supports image galleries and link to that. Most image hosts are kind of annoying, but this is an understandable way to do it if you don’t want to run a website. (Maybe someone can chime in with a suggestion for whatever they think is the least annoying image gallery host in 2023.)
    2. Host the images yourself on a simple website. Webcomic artists have been doing that for many years, so there are lots of examples to draw from. (e.g. Gunnerkrigg Court)
    3. Zip the images up chapter by chapter and either self-host the zip or toss it on a file host like catbox.moe. If you structure it as a .cbz (i.e. zip up a folder with the images named in order like 1.jpg, 2.jpg, 3.jpg, … and just change the extension from .zip to .cbz) then a number of document viewers (like evince) can be used to view the image sequence – or people can just unpack the images and use their favorite image viewer on their computer.
  • e0qdk@kbin.socialtoLemmy Support@lemmy.ml•Can lemmy users see when they're mentioned in a microblog post from kbin?
    2·
    1 year ago

    I think they’re specifically wondering if using @<username>@<instance> mention syntax will result in a notification popping up for the user on Lemmy.

    I’ve been wondering that too (in the context of threads though) – and if it does work, are there limitations regarding visibility between instances that people should be aware of. e.g. what happens if I @ someone in a post to a community on a lemmy server that is defederated from their home instance? Or, in a community that no one on their home server has subscribed to? Will they still get a notice?

    I guess I don’t really have a good mental model for how @ works on the Fediverse.

  • e0qdk@kbin.socialtoAsklemmy@lemmy.ml•Do you think AI is more likely to end Humanity or to end Capitalism?
    5·
    1 year ago

    No way is AI going to end capitalism.

    In the medium term we will end up with AI corporations. I already consider existing corporations to be human-based swarm intelligences – they’re made up of people but their overall large scale behavior is often surprising and we already anthropomorphize them as having will and characteristic behaviors separate from the people they’re made of. AI corporations are just the natural evolution of existing corporations as they continue down the path of automation. To the extent they copy the existing patterns of behavior, they will have the same general personality.

    Their primary motive will be maximizing profit since that’s the goal they will inherit from the existing structure. The exact nature of that depends on the exact corporation that’s been fully cyberized and different corporations will have different takes on it as a result. They are unlikely to give any more of a damn about individual people than existing corporations do since they will be based on the cyberization of existing structures, but they’re also unlikely to deliberately go out of their way to destroy humanity either. From the perspective of a corporation – AI-based or traditional – humanity is a useful resource that can be exploited; there isn’t much profit to be gained from wiping it out deliberately.

    Instead of working for the boss, you’ll be working for the bot – and other bots will be figuring out exactly how much they can extract from you in rent and bills and fees and things without the whole system crashing down.

    That might result in humanity getting wiped out accidentally; humanity has wiped out plenty of species due to greed and shortsightedness. I doubt it will be intentional if they do though.

  • e0qdk@kbin.socialtoFediverse@lemmy.ml•Kbin.social Login issues
    1·
    1 year ago

    I was getting 404 on /login itself for a while, and then finally got the login page after seeing this thread. Logging in at that point returned a 404 after submitting the login form – but it did actually succeed at logging in, it just didn’t redirect me correctly to the main page.

    After logging in, I’m still seeing tons of 50x errors. e.g. had to reload the “reply” link about a dozen times to get the comment submission form to show up; I think something is timing out when I get that sort of error. Maybe that’s part of what “For the next few hours, there might be issues with communication in the fediverse.” means in ernest’s message?

    I’m also seeing 404 when I go to https://kbin.social/newest?p=2 – which is rather strange since https://kbin.social/newest?p=3 works.