Yeah, for all the talk of Sora building an internal “world model” that could be a building block for AGI… this seems to suffer from all the same glitches as the Will Smith spaghetti video, just with much, much more polish.
I don’t think it’s that much worse than what OpenAI showed off earlier in the year when you consider that those examples were very cherry-picked, though. These new videos don’t make it seem like a bad model, they’re just a bit more realistically mediocre.
Anyone who works closely with diffusion models knows the "world model" thing was hype. Diffusion models are really good at faking, starting with nonsensical large-scale structure and forcing it towards plausibility with lots of nice details.
Yeah, I'm struggling to understand what the use case of this is. These videos aren't tricking anybody who's used a cameraphone. Just shooting video with phone costs nearly nothing. People don't particularly seem to want to generate films of places they aren't.
https://runwayml.com/
https://klingai.com/
https://hailuoai.video/
https://lumalabs.ai/
https://pika.art/
https://viggle.ai/