Live data from Hacker News

LLM-Integrated Multivariable Calculus Course

calculus.academa.ai

41–50 of 50 posts

Re: LLM-Integrated Multivariable Calculus Course

#41

Earlier quoted context omitted.

These are 14 hours of video, so it's easy to find mistakes. We've probably made plenty of them. But this isn't AI slop. We created the technology so that the content can be updated and improved over time. If we make mistakes, we'll fix them and continue maintaining the material. These aren't static MP4 files recorded once with a camcorder.

To give a more precise indication, I watched maybe the first 5 minutes of lecture 1 and 5 for this. I highly encourage you to take "didicatically useful" as a bar to aim for, rather than "not making mistakes". I think it's a cool tech demo, but if you're positioning this as a course that's ready to be consumed by students, I think doing the quality control is not optional.

Thank you for the feedback! We'll make it better. We take quality very seriously.

Re: LLM-Integrated Multivariable Calculus Course

#42
post #28

Earlier quoted context omitted.

> All we want to do is innovate. That's very clear. That's why we have spyware, ad tech, WWII-era German chemical weapons, the East India Company, Oracle's business model, fintech, ... Ask anyone 40 years older. Regrets focus on time with family and meaningful work. Few people think: "Did I innovate enough?" > We simply can't open source this because we're rewriting and rebuilding it every day. I don't quite see the…

First, I need to make my startup successful so I can continue innovating over the next 15 years. Open-sourcing our work could be a distraction at this stage. Maintaining an open-source project requires significant time and effort. It would also make it easier for competitors to build products that compete directly with us, such as https://studio.academa.ai . That would make it harder for my startup to succeed. I'm no…

Don't pay too much attention to the naysayers if they don't have constructive advice to offer (but do try to collect what signal you can from the noise). There are a lot of people who viscerally hate AI for a ton of different reasons, or maybe are perfectionists about the subject matter. Even if these AI technologies are currently imperfect, they solve Bloom's Two Sigma problem - students tutored to mastery one-on-one perform two standard deviations better than students taught in traditional classroom settings. Imagine a world where everyone is 30 IQ points smarter just from better education technology!

Personally, I just used chatgpt the other day to _finally_ understand why a dot product of vectors is equivalent to cosine similarity. Mathacademy's lesson is very good but the explanation wasn't enlightening for me, it took chatgpt breaking it down into tiny bite-sized chunks, patiently re-explaining what a cosine actually is and where it disappears to in the dot product, making little animations of vectors with sliders that I could move myself to try stuff with differently shaped and rotated triangles, for me to _actually and viscerally understand it_ and after spending probably 2 hours on this simple concept, now I _actually_ feel like I understand it rather than having just memorized it. So I feel much more confident that I can build deeper understanding on top of that.

Re: LLM-Integrated Multivariable Calculus Course

#43

Earlier quoted context omitted.

First, I need to make my startup successful so I can continue innovating over the next 15 years. Open-sourcing our work could be a distraction at this stage. Maintaining an open-source project requires significant time and effort. It would also make it easier for competitors to build products that compete directly with us, such as https://studio.academa.ai . That would make it harder for my startup to succeed. I'm no…

Don't pay too much attention to the naysayers if they don't have constructive advice to offer (but do try to collect what signal you can from the noise). There are a lot of people who viscerally hate AI for a ton of different reasons, or maybe are perfectionists about the subject matter. Even if these AI technologies are currently imperfect, they solve Bloom's Two Sigma problem - students tutored to mastery one-on-on…

Thank you!

Re: LLM-Integrated Multivariable Calculus Course

#44

Earlier quoted context omitted.

Is cloning Manim "innovation" now? Plenty of open source is updated every day. You had no problem taking advantage of Manim to profit, but when it comes to returning the great favor done to you by Manim being open source, you don't care? Okay.

Everything I do is driven by a single goal: to make my startup successful so I can innovate in edtech. Nothing else. You may not believe me, and you may think I have ulterior motives, but I don't. My only goal is to build technology that meaningfully advances education.

> Everything I do is driven by a single goal: to make my startup successful so I can innovate in edtech. Nothing else.

I believe you entirely. That comes across in everything you say. Huge harm has been done in education precisely by people with similarly amoral motivation. History of education is filled with case after case of amoral motivations leading to immoral behavior.

Other industries have this more extreme. Fritz Haber is a biography worth reading.

The comments you're making aren't very honest -- I suspect with yourself more than with anyone else. For example:

> Maintaining an open-source project requires significant time and effort.

No. It doesn't. You need to flip the "public" bit on github and post a "caveat emptor" shingle. The effort you're cloning -- manim -- did exactly that. The result was a synergistic, friendly, manim-ce.

And the author has been able to work full-time in this space, his entire career, without doing anything evil, unethical, harmful, or unpleasant, and strictly advancing the world.

You're competing -- rather than cooperating -- with folks like him.

> I simply need enough protected space to innovate competitively and give the company the best chance to succeed.

You don't seem to understand how this works. A few points:

- Education is a highly-regulated industry for good reasons (student harm, societal harm, privacy risks, etc.), and education research goes through IRBs for similar reasons.

- Startups can work on IP, but usually -- and especially in education -- networks, connections, support, etc. are more important. It's hard to build an IP moat.

- Startups have a 95% failure rate. I'd give this one more than that.

A few corollaries:

a) With the current model, you'll have a hard time building partnerships with the people you need, and indeed, people (myself included!) will be rooting for you to fail. That weakens, not strengthens, your odds of success.

b) An example of another way to accomplish your stated goal is a five-year research grant, or a position which supports doing this kind of work (e.g. instructional staff at your university). Those have >> 5% success rates.

c) Open business models aren't less likely to be successful here than closed ones. Red Hat sold for $34B.

Otherwise, my best wish for you is to fail fast, and to learn a lot from the process.

Re: LLM-Integrated Multivariable Calculus Course

#46
post #16

I think a lot of this is the inevitable (and good) direction teaching must go. As someone who has self-taught most of my skills both before and after AI, some deep feedback: I don't want a fixed piece of content when learning with AI, like a video or blogpost or book—unless I'm completely new to the subject, and even then maybe not. The reason is that some parts of the topic will be naturally easier or harder for me.…

I agree. I really cringed when I viewed this platform. The potential in educational AI rests in its interactivity, quizzing and socratic dialogue. There are many great and engaging courses on Calculus taught by charismatic and interesting instructors (humans). And in this age of MOOC, all it takes is a handful of strong online accessible courses for there to be diminishing returns in trying to improve the quality of lecture content.

I want to see agents quiz me, understand my strengths and weaknesses, setup study plans, using spaced repetition to ensure I retain information, engage in dialogue such that I come to the answer through articulated reasoning. Not watch lecture content similar to what's already out there but with less soul.

Re: LLM-Integrated Multivariable Calculus Course

#48
post #8

Earlier quoted context omitted.

How are you guaranteeing accuracy?

By storing the content in a semantically meaningful way (not mp4s), making it easy to review, version control, and maintain.

This isn't really an answer.

How are you checking the accuracy of the content? Especially if you plan to scale this to hundreds of courses, it doesn't seem like you actually have humans checking.

Re: LLM-Integrated Multivariable Calculus Course

#49
post #48

Earlier quoted context omitted.

By storing the content in a semantically meaningful way (not mp4s), making it easy to review, version control, and maintain.

This isn't really an answer. How are you checking the accuracy of the content? Especially if you plan to scale this to hundreds of courses, it doesn't seem like you actually have humans checking.

Let me elaborate.

Our content is text, not MP4 files. So we review it with humans and AI, just like how software companies review their software. We may make mistakes, but that's okay because we maintain the content. We continuously improve it and fix issues as we find them.

It'll even become more accurate than cam-recorded lecture videos over time, because those aren't being updated.

Re: LLM-Integrated Multivariable Calculus Course

#50
post #16

I think a lot of this is the inevitable (and good) direction teaching must go. As someone who has self-taught most of my skills both before and after AI, some deep feedback: I don't want a fixed piece of content when learning with AI, like a video or blogpost or book—unless I'm completely new to the subject, and even then maybe not. The reason is that some parts of the topic will be naturally easier or harder for me.…

I couldn't agree more. But if you look at it from this perspective, you may understand why we use static videos for this demo. Definition: the AI tutor is some AI that can generate these videos. If that generation happens in real time, it's a complete reimagination of education. It's literally the AI private tutor. But before you can do that in real time, ask yourself: let alone real time, can you even generate a vid…

That's great. You certainly know more the ins-and-outs, and I wish you luck.
Post reply on HN