Show HN: Academa – Long-form STEM lecture videos generated by LLMs (academa.ai)

2 points by sinaatalay ↗ HN
Hi HN, we are Sina Atalay and Abdullah Geduk, co-founders of Academa. We are both PhD students.

We thought: what if lecture videos were written as code and compiled into video using computer graphics and TTS?

Then LLMs could write them, and lectures could be fixed with code edits instead of video production.

On correctness: LLMs may make mistakes. But these videos are code sitting in our repository, and we can maintain them. Every report and review becomes a fix in the source, and everyone who watches after that gets the corrected lecture. Every recorded lecture on the internet is stuck with its mistakes. Ours will continuously improve.

Each video also comes with an AI chat that understands everything said and shown in the lecture.

There is a longer write-up at the bottom of the page.

Happy to answer any questions.

24 comments

[ 0.28 ms ] story [ 33.4 ms ] thread
There are misplaced verbal emphasis and non-emphasis. And unfortunately these happen at the crucial moments. Makes it very hard to follow.
Thanks for the feedback. Emphasis is definitely important in these videos where there is no human hand to point with. We will improve this more and more in the upcoming days.
> On correctness: LLMs may make mistakes. But these videos are code sitting in our repository, and we can maintain them. Every report and review becomes a fix in the source, and everyone who watches after that gets the corrected lecture. Every recorded lecture on the internet is stuck with its mistakes. Ours will continuously improve.

Models change. Models are unpredictable. The assumption that we can constrain them between prompt bumpers has not been proven and seems unlikely to be provable given how these model works.

Beyond that, how do you know if the reports and reviews are even correct? Are you just gonna rely on the kindness of others to provide that value? Of all things that LLM’s have killed, I’m pretty sure the open sharing of knowledge and understanding are the first on the chopping block. I don’t care whether or not you’re pro or anti LLM, publishing knowledge for reputation is now a dead end for anyone wanting to make a living.

Wrapping others’ knowledge in a black box that may or may not accurately represent that knowledge is basically enshitification on steroids. The reason we hold folks like Lovelace, Sagan, or Feynman in high regard is because they weren’t wrong when they shared their understanding and knowledge.

But the best of luck to everyone involved! I’m sure everything will work out!

> Wrapping others’ knowledge in a black box that may or may not accurately represent that knowledge...

You wrote it well. This aspect irks me, too.

>Humans change. Humans are unpredictable. Especilly ones like Lovelace, Sagan, or Feynman. The assumption that we can constrain them between teaching classes has not been proven and seems unlikely to be provable given how these humans work.

That's such an excellent argument against letting humans teach other humans! You should start a petition.

Love the 'videos as code' idea! Imagine quickly iterating on explanations or generating variations for different learning styles.
This is a great idea. I find LLMs to be a good teacher, though I've primarily interacted with them through text.

I'm curious, what are the economics of producing this longer form content?

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.

Why do I need to use this? Why can't I just use the LLMs directly to generate lectures if I want?
That's right, just give me the prompt, not the LLM output, and I will prompt my own model! I would rather read the billions of tokens that went into the prompt, than watch a video, and I am sure all other students would too.

Just assign years worth of reading homework every week, and I am sure all the students will fullfill their assignments of reading every token that went into each video, no matter how many, rather than watch an LLM generated video.

Students simply need to learn how to read text as fast as an LLM can, and have an enormous token budget to use the LLMs directly themselves.

And while you're at it, increase their tuition by the amount those tokens cost, so each student can pay for feeding the same tokens in to their own LLM instead the school doing it once and paying out of their own pocket immediately. Because the idea of schools producing reusable courseware is unprecidented! That way they can fold the token cost into their student loans.

To me, the main advantage of the lecture format is the possibility to have me or others grill the lecturer for questions, benefiting the whole group. I'm not sure listening to a robot reading me a transcript and chatting with it really gives me that same advantage. What's the upside to this versus just getting slides and/or transcript w/ sources and feeding it to my own LLM?
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.

> To me, the main advantage of the lecture format is the possibility to have me or others grill the lecturer for questions, benefiting the whole group.

I've rarely, if ever, seen this. And if I had, I think most of the class would have just been annoyed, which you probably didn't notice.

I briefly worked as a Uni lecturer, and I completely agree.

Universities have made the mistake of competing with YouTube (video lectures), whereas what they can actually offer is direct access to domain experts.

I am skeptical that any other solution has much of a moat. So if the creators of this are after any feedback, I would offer that their best bet is to be competitive on User Experience, rather than underlying technology.

Fellow PhD student here, always wished for easier ways to update lecture content. This "code to video" idea could be huge for reproducibility.
What's the point? You don't want humans to talk to each other any more, to teach each other, to learn from each other? Everything has to be mediated through some sort of bot?

The future of humanity is dire if this is what's round the corner.

Thanks for making everything worse, you soulless bastards.

Great idea, but buggy. My lecture started mid-sentence and ended abruptly (Kalman filter). Looking forward to when you guys get it working well. Also, I'm curious if the lecture description language is public.
i find the writing style a bit peculiar at times. Take this lecture on bloom filters for example: https://academa.ai/lectures/bloom-filters

It suddenly starts talking about URLs, but it never really sets up the idea that we're using some kind of URL lookup service as an example. The way it introduces the memory limit feels similarly strange. At some point, it just says that we have 8GB of memory, but it does that halfway through the explanation, not as part of the setup of the problem we're actually solving.

I watched the linear regression video. I can see the value behind the idea, but there's a number of flaws that make the videos difficult to watch compared to something like a 3blue1brown video. The flat voice and even word spacing lull you into zoning out, right until a mispronunciation jolts you back.

The idea of using LLMs to write out a script and storyboard for the video is interesting, but I think it needs intermediary work to better instruct the speech and graphics on how to perform.