Generative UI for education

https://academa.ai

We think videos are special. There is a reason why Khan Academy, Coursera, etc. are essentially video libraries. A lecture video is a recording of a teaching performance, a form of presentation where someone explains while controlling what you see and when you see it.

Also, you’re not chatting with the transcript; you’re chatting with the video. The AI has much more than the transcript in its context. See this, for example: https://academa.ai/lectures/diffusion-models-learning-to-den...

And in the coming months, we’ll make the answers themselves real-time videos, which is kind of trivial for us at this point. We’ll ask the LLM to answer by writing code, and our software will render that code and show you the response directly as a video.

Thank you!

Actually, the economics are quite good.

We’re not using video generation models. We ask an LLM to write the lecture as code, then render it deterministically with computer graphics and TTS.

So the main costs are the LLM call, TTS, and some cloud GPU time for rendering. That ends up being much cheaper than generating long form video directly with video models.

You can attempt to do it, but you'll see that it won't work. We've built the underlying "lectures as code" technology to make this work.

You just said in another comment that you use Claude Opus 5 to generate the video in a single shot. What about it won't work?

We ask Claude Opus 5 to write a specific kind of source code that only our proprietary software understands and can render into a lecture video with computer graphics and TTS.

Without our system, there isn’t really an equivalent target language you can ask the LLM to write. Manim exists, but you won’t get videos like these by simply asking an LLM to generate Manim code.

Claude Opus 5, with high thinking, generates the video in a single shot.

The one that asks questions at the beginning is Gemini Flash 3.7.

Coding, graphics, all seem to have very defined background data for an LLM to base their decisions on, test, and even when I correct it we're all on the same page. Seems like there's lots of room for AI productivity there.

What I find funny is that approximate to computer graphics are video games. When I ask AI about a decision available to me in a video game AI completely fails, OFTEN. I assume all the forums and changes made to a game over time might be quite confusing for AI. But I've also seen it completely make up characters and decisions and weapons and so on about some very clearly defined games and paths. It's an interesting dynamic.

Thank you :)

> We never intended to use 3Blue1Brown's name in a negative or misleading way

You submitted this with the title “Manim (3Blue1Brown's animation engine) in the browser via WebGPU”

Being misleading is exactly what you intended to do.

You can use the editor however you like without signing up. The examples are simply sample prompts for the AI, but you can paste in any Manim code to editor from ChatGPT or anywhere else, and the preview will render it instantly.

Downloading videos is completely free. Only the AI-powered features are behind the paywall, and there's a 7-day free trial.

We'll put more pre-written examples, thank you!

That was also unclear to me, so +1 for more code examples. Also, it seems like maybe this doesn't work in Safari but there's not error message or anything. I was looking for a Run or Render button or something to get things to happen, until I gave up and tried Firefox.

Thank you!