Still working on enabling llms to generate structured videos with text and formulas over at https://videozero.ai but man the marketing side feels IMPOSSIBLE. Really struggling with that one…

There are a lot of old and new mobile applications doing this. If there is anyone doing some research in this space, maybe take a look at our "DisruptaBLE" implementation for delay tolerant networking on embedded devices: https://openreview.net/forum?id=xy3Y6cLOV2

I work as a freelancer, but I have been wanting to start something of my own. A couple of months ago, I started working on VideoZero.ai with the vision of generating videos that feature text, formulas, and graph elements without breaking after 10 seconds or weird artifacts. Instead of generating raw pixel values, we leverage Motion Canvas to create the video elements. Some results are quite cool, but some videos are quite crappy. We have a whole list of animations to explore here: https://videozero.ai/gallery

I really like the interactive elements and animations.

Small nit on the wording: "This continuous cycle enables self-sustaining, self-propagating electromagnetic waves"

The term “self-propagating” makes it sound like the fields are somehow pushing each other forward, but really they’re just coupled solutions of Maxwell’s equations.