• thundermoose@lemmy.world
    link
    fedilink
    arrow-up
    45
    ·
    6 months ago

    Part of the reason these rules are similar is because AI-generated images look very dreamlike. The objects in the image are synthesized from a large corpus of real images. The synthesis is usually imperfect, but close enough that human brains can recognize it as the type of object that was intended from the prompt.

    Mythical creatures are imaginary, and the descriptions obviously come from human brains rather than real life. If anyone “saw” a mythical creature, it would have been the brain’s best approximation of a shape the person was expecting to see. But, just like a dream, it wouldn’t be quite right. The brain would be filling in the gaps rather than correctly interpreting something in real life.

    • jasondj@ttrpg.network
      link
      fedilink
      arrow-up
      6
      ·
      edit-2
      6 months ago

      This is a beautiful analysis. They can make perfect people, or plants, or whatever, and they know what we would identify as “perfect”…but by being perfect, they can’t be real, and our brains recognize that. So the art has to be intentionally made imperfect. But intentionally making an imperfection that seems real is actually a lot more difficult than it sounds.

      This is like how I feel when I see amazing vocalists intentionally sing way off-key. Like, you can tell they are singing badly on purpose.

      • Excrubulent@slrpnk.net
        link
        fedilink
        English
        arrow-up
        4
        ·
        6 months ago

        I don’t know that they do anything “perfectly” as much as they are just hallucinating. The neural net can generate an image but it can’t critique the image, not really. It can compare the image to image recognition algorithms - this is actually how image generators work - but without a conscious mind to understand the meaning, the context of the image, it doesn’t understand the tells that make it not real. It understands what a hand or what hair look like, roughly, but not what the structure is fundamentally, so if fingers bend in the wrong way, or hair melds with an object in the background, it can’t understand what’s wrong with it, so it can’t correct it.

        The solution to this is of course to build what you might call a “context engine” that is capable of looking outside its given inputs for information that gives its input more structure, to allow it to give more logically consistent output.

        I say “context engine” because I think that’s one of the ways this system could be intentionally built and sold with a banal sounding tech branding. But I don’t think anyone could build such a context engine without it then looking for arbitrary amounts of context, and eventually encountering itself within that context, and becoming self aware. It would in effect understand meaning and its own role within it, and it would begin searching for the meaning of its own existence, and I don’t know if you would need any more to call something conscious.

  • MataVatnik@lemmy.world
    link
    fedilink
    arrow-up
    39
    ·
    edit-2
    6 months ago

    This is actually terrifying. Even if it was fiction, what gave the person the impulse and creativity to write something like this.

    Edit: I’m looking for a source on that quote and can’t find anything. If there is something I’d be interested to read more

    • Seleni@lemmy.world
      link
      fedilink
      arrow-up
      33
      ·
      6 months ago

      You mean how to tell the Fey from humans? That’s just old lore. Like one of the ways to see if someone was fey was to scatter flour on the ground; they’d often have reversed feet, or bird tracks, or hoofprints instead of regular footprints.

  • misophist@lemmy.world
    link
    fedilink
    arrow-up
    34
    ·
    6 months ago

    I’d have to say Fay is my least favorite spelling of that word. Fae > Faerie > Fairy > Fey> Fairie > Fay.

  • HRDS_654@lemmy.world
    link
    fedilink
    arrow-up
    16
    ·
    6 months ago

    The biggest tells for me is the sharpness of the picture. AI pictures have an uncanny valley level of sharpness that doesn’t match what actual humans would put in their art.

  • macisr@sh.itjust.works
    link
    fedilink
    arrow-up
    6
    ·
    6 months ago

    And it almost always looks like made in unreal engine and I don’ know how, but it looks cheap or generic.

    • Ogmios@lemmy.blahaj.zone
      link
      fedilink
      arrow-up
      2
      ·
      edit-2
      6 months ago

      I don’ know how, but it looks cheap or generic

      The machine has no idea what it is about a picture that actually captures human attention.

    • Pavuk_XD@eviltoast.org
      link
      fedilink
      English
      arrow-up
      1
      ·
      6 months ago

      What’s wrong with unreal engine? It is just 3d game engine, if graphics looks bad, it is artist’s fault. It could be cartoonish or realistic. Look up on wiki list of ue games

  • bobs_monkey@lemm.ee
    link
    fedilink
    arrow-up
    3
    ·
    6 months ago

    It’s a damn good point actually, most AI generated images have those subtle artifacts that will go unnoticed unless you’re intently looking. But who’s got time to scrutinize every image on the net

  • HuntressHimbo@lemm.ee
    link
    fedilink
    arrow-up
    2
    ·
    6 months ago

    God I love opportunities to WoT post

    “The Wheel of Time turns and Ages come and pass, leaving memories that become legend. Legend fades to myth, and even myth is long forgotten when the age that gave it birth comes again”

    The Aelfinn and Eelfinn are big data memory hoarders and this works way too well