Attached: 1 video

Someone secure the hot pants!!!

Edit: as pointed out in the comments, this might be AI generated. Judge for yourself.

  • qaz@lemmy.world
    shield
    M
    link
    fedilink
    English
    arrow-up
    56
    ·
    edit-2
    24 hours ago

    @abbadon420@sh.itjust.works are you sure this video hasn’t been generated with AI? In that case please tag it as required by rule 9

    As @DarkTimez@lemmy.blahaj.zone pointed out, the channel seems to only post generated content

    The video looks consistent so it’s hard to tell for sure. It could be that they copied real footage from somewhere else and posted it with the rest.

    Timeline:

    1. The first mention I could find was the AI channel on 7 November: https://www.youtube.com/shorts/tyjwfPPyxuo
    2. Then it was posted on X on 8 November: https://x.com/skithedream_/status/2119550533258387809
    3. The AI channel posted a short with a similar situation on 9 November: https://www.youtube.com/shorts/eNeKJ8vhm34
    4. It was posted to 9Gag on 10 November https://9gag.com/gag/aj7YDwx

    I also find a similar video posted on Facebook https://www.facebook.com/61594683694701/videos/ocean/1395503672656845/

    So far I think it’s AI generated. Keeping this up for a bit longer to see if anyone else can spot a definitive sign it’s fake and as warning of how realistic AI content has gotten.

    • apparia@discuss.tchncs.de
      link
      fedilink
      English
      arrow-up
      17
      ·
      20 hours ago

      I’m no expert on image editing in general and even less so with AI image generation, but I’m pretty sure there’s some weirdness where the foreground of the boat interacts with the background of the water.

      The railing (which dips in and out of view suggesting the ship is flexing in a way that may or may not be one of those “engineering is actually just absurd” things) seems to be overlapped by the background in a manner that looks plausibly like a compression artefact except for the way it moves:

      You can also see that some of the specks in the glass (which are consistent from the video start) appear to get “lost” in the background and/or picked up and carried away by it. Particularly note the one in the top left that “flashes” as it passes a brighter area of the background, but the flash starts several frames before they actually overlap.

      There are some other slop-ish but non-definitive aspects like this thingy and its wobbly outline:

      But in general this is very convincing.

      I should stop nerd sniping myself investigating these things.