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

  • 2 Posts
  • 51 Comments
Joined 1 year ago
Cake day: September 22nd, 2023
  • e0qdk@kbin.socialtoPython@programming.dev•Problems parsing a string with pyparsing
    3·
    11 months ago

    Haven’t used that particular library, but have written libraries that do similar sorts of things and have played with a few other similar libraries in C++ and Haskell. I’ve taken a quick glance at the documentation here, but since I don’t know this library specifically apologizes in advance if I make a mistake.

    For OneOrMore(Word(alphanums)) + OneOrMore(Char(printables)) it looks it matches as many alphanum Words as it can (whitespace sequences being an acceptable separator between tokens by default) and when it hits ( it cannot continue with that so tries to match the next expression in the sequence. (i.e. OneOrMore(Char(printables)))

    The documentation says:

    Char - a convenience form of Word that will match just a single character from a string of matching characters

    Presumably, that means it will not group the characters together, which is why you get individual character matches after that point for all the remaining non-whitespace characters. (Your result also seems to imply there was a semicolon at the end of your input?)

    For OneOrMore(Word(alphanums)) + OneOrMore(Char(string.punctuation)) it looks like it cannot match further than ( since 1 is not a punctuation character; so, you got the tokens for the parts of the string that matched. (If you chained the parser expression with something like + Word(alphanum) I’d expect you’d get another token [i.e. "1"] added onto the end of your result.) You may eventually want StringEnd/LineEnd or something like that – I’d expect they’d fail the parser expression if there’s unconsumed input (for error detection), but again, haven’t used this specific library, so it may work different than I expect.

    There appears to be a Combine class you can use to join string results together; that might be useful for future reference.

    i was trying to parse a string with pyparsing so all the words were separated from the punctuation signs

    Have not tested it (since I don’t have a copy of the library installed anywhere and can’t set up an environment for it easily right now) but perhaps something like OneOrMore(Word(alphanums)|Char(string.punctuation)) would be more like what you are looking for?

  • e0qdk@kbin.socialtoTechnology@lemmy.world•IBM releases first-ever 1,000-qubit quantum chip
    56·
    11 months ago

    The attached picture says 133 qubits, so whatever that chip is (edit: Heron) it’s not this thing.

    IBM’s post (that the article links) says:

    Breaking the 1,000-qubit barrier with Condor

    We have introduced IBM Condor, a 1,121 superconducting qubit quantum processor based on our cross-resonance gate technology. Condor pushes the limits of scale and yield in chip design with a 50% increase in qubit density, advances in qubit fabrication and laminate size, and includes over a mile of high-density cryogenic flex IO wiring within a single dilution refigerator.

    So, it sounds like this is actually another fridge sized system.

  • 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.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.