Comment by neom

1 day ago

There is a woman on twitter who makes seedance videos of her and Dario from anthropic, they're kinda weird but generally pretty high quality: https://x.com/CuiMao/status/2058458683781365873 (full collection: https://x.com/CuiMao/status/2082740754380984373) - seeing them was the first time I'd been impressed with AI video gen.

46 comments

neom

Reply
dotancohen  17 hours ago

For first of us without twitter:

https://xcancel.com/CuiMao/status/2058458683781365873

I can not believe how good the AI video has gotten. In one spot the written letters were obvious AI. Other than that - I couldn't find a thing.

  • prodigycorp  17 hours ago

    the thing that upped the immersion was the the way it emulated the optical zoom when switching from the 1x lense to the 3x lense

  • efficax  6 hours ago

    there aren't a lot of the obvious AI glitches but it still looks wrong, stiff and unnatural, eyes aren't right, faces move weird, it's all in the uncanny valley still to me

  • globular-toast  16 hours ago

    There were tons of continuity errors, but I suppose bad film makers make those too and often get away with it. The worst was the gift that was boxed in one shot, then open and containing a gift that didn't fit in the box. Another more subtle one was after they bumped into each other they were standing in front of a wall suggesting she just ran out from the wall.

    • raisedbyninjas  8 hours ago

      It's usually background stuff. Like the statue of liberty is behind both of them when arguing face to face. Vehicle traffic sometimes driving the wrong way. Tassels hanging from random sides of the mortarboards.

throwatdem12311  1 day ago

This is deeply disturbing…for so…so so many reasons.

sumedh  1 day ago

I dont normally like AI videos but this was just amazing, by next year the tech will be perfect, cheaper, we are going to AI videos everywhere whether anyone likes it or not.

  • deadbabe  1 day ago

    people like it. Maybe not older generations, but we're about to get a fresh new generation of people that will not have a lifetime of experience looking at human generated content, and so have no real bias against AI content.

    And then every generation after that will be born into increasingly a AI-video rich world.

    • ipsum2  21 hours ago

      Older generations absolutely love AI slop. If you haven't used Facebook recently, it's all old people sharing fake videos of animals doing silly things.

      1 reply →

    • dbspin  8 hours ago

      Hilariously out of touch take. In the West AI video is popular almost exclusively amongst boomers (and of course tech company employees). Gen Z absolutely loath it. Filmmaking is yet another future career that's being made impossible for them.

      1 reply →

    • weitendorf  1 day ago

      Right now we're going through multiple concurrent but slightly non-overlapping transitions where AI is almost good enough for something, and seeing a predictable surge of spam/bad quality crap people don't like, followed by a whiplash effect when it reaches human or superhuman levels of performance.

      I think most developers would agree that the Cursor vibe-code era sentiment towards AI for coding was right in the sense that it wasn't that useful then, and a lot of people did and do stupid things with it, but it really did deliver quite substantially on its promise just a couple years after the "consensus" was often "that's never going to work".

      It's very strange to me how consistently public opinion shifts on this problem. In the long run we're all dead but whether it takes one or five years, you probably will be there to live through it. I assume whoever is downvoting you is just thinking with their consumer-brain or "I don't want that" (the way it is now) rather than that this will be no different than video games, or wasn't a child who watched youtubepoop or other weird stuff because it was funny.

    • kwanbix  1 day ago

      Sad. Wish there was a huge library of human generated content they can look at.

weitendorf  1 day ago

People are still figuring out the social norms surrounding "deepfakes" and I'm convinced there are some versions of the future where it becomes normalized for content under essentially fair use/free speech doctrine, and many where it's used to restrict free speech in the small number of jurisdictions where public figures would currently be allowed to be featured in this content.

Obviously there are a lot of ways it shouldn't be used but I want to live in the future where it's something we use to have fun, where reasonable, rather than a dangerous/sketchy taboo

noisy_boy  21 hours ago

I can't make up my mind if the simplistic narrative typical of Chinese romcom shorts is more funny or more weird.

cortesoft  1 day ago

The scene that says “Stanford University” looks a lot like UCLA.

  • jedbrooke  19 hours ago

    UCLA is often used as a stand in for many colleges in movie sets (notably Harvard, as one of the buildings in UCLA has the Harvard crest on it specifically for this purpose) due to its proximity to Hollywood. It likely ended up in the training data that way

    • cortesoft  19 hours ago

      Yep, I notice it all the time in movies and tv shows. They were filming the movie "Old School" my freshman year there, I thought it was so cool. Makes sense it is in a lot of the training data

vitorgrs  17 hours ago

There is a ton of vertical dramas now (Duanju) made purely of AI. Even on chinese streaming services you find it.

konart  16 hours ago

The whole damm Makoto Shinkai based dorama style too!

This is blessed and cursed timeline at the same time.