How I use LLMs to learn complex topics

haha, I did the same to study new topic and then realized how personalized education will turn out in the near future. The only thing left is keeping a curious mind and ask a lot of questions !!

I tend to ask the LLM for a single HTML page explanation, with a pedagogical approach. Something about dropping the word pedagogical leads to a more structured outcome, but I haven't quite figured it out why yet.

Very cool, I like the visual learning nature of this and the auto play once starting. The game graphics are engaging which counts for a lot these days, I feel my attention span suffering after using agents for the past year.

I've been working on a similar process of pushing to github pages, but focused more on having "practice sessions" with coding blocks to test content. Using webassembly and mock servers to mock backend endpoints Here's one I built to build a full stack llm chat system in the browser.

https://model-systems-labs.github.io/latent/llm-systems/less...

> What you get is a beautiful animation that is 100% accurate and free of hallucinations.

How do you know if you're learning this for the first time? Very risky to learn from LLMs. I've done it, but you have to keep your wits about you. Lots of "oh of course you're right - what I just told you was completely wrong".

My favorite way to learn infra topics at work right now is asking for a humorous analogy involving monkeys and bananas. I tend to remember the result, and it gives me reference points for new topics.

Oh, I do similar, but using single page websites.

Last month, I read The Prince and had it make a text adventure campaign for me.

For a lot of other topics, I often just ask it to create a simple python example that I can run.

LLMs can help you understand a language, but they can't replace learning the vocabulary. Words and phrases still need to be learned the old-fashioned way: repetition

AKA - How I skim read a lot and learn nothing of value.

I don’t think I really agree with the author’s approach here, but I will say LLMs have been a huge help to me as I’ve been reviewing linear algebra and diving into signal processing. Anything in a textbook that I don’t fully grasp or am confused about, I just take a snapshot or copy paste then ask a model to derive it or explain it in different terms.

It reduces friction a ton, but at the end of the day I’m not skipping anything.

The selected topic (chip manufacturing) is being presented at a shallow level at best. Go read Wikipedia’s article [0] and see how deep and broad the topic is. It also skips quite a few steps, and utterly glosses over how insane of an accomplishment EUV is.

This is my biggest societal issue with LLMs: they allow you to think that you’ve “learned” a topic because you read a lot of technical terms. I don’t think it bodes well for the future.

0: https://en.wikipedia.org/wiki/Semiconductor_device_fabricati...

Building learning artefacts is under appreciated.

Inthink this was always the best way to learn. But it used to require immense work for a teacher.

My compiler course is a great example - program in plug in a stage of a compiler.

These exercises can be made on demand and incredibly easy now.

YouTube has so many truly wonderful videos on chip production. I admire your approach but it seems like a lot of people are in this ai maxxing phase where they reach for ai for everything despite their being ready, high quality things already available for free

i've asked llms to write a presentation for me on a given topic. for whatever reason, that finds the hidden layer responsible for explaining things well.

The biggest win for AI dev efficiency is cutting down what gets loaded into context. Semantically matching tasks to the top tools helps a lot.

Too over engineered, few text paragraphs would suffice to understand the topic.

Is there a way we could turn this into a reusable skill?

That seems like a terrible way to learn. It’s a neat animation but cmon, there’s like educational TV programs from the 80s that explain this so well, in Germany there’s “Sendung mit der Maus”, not sure if they have a segment on chip manufacturing. But in these clips you can at least see the real stuff instead of some half wrong animation, just let the LLM write a few paragraphs for you or better find an ACM article or book on the subject, probably still takes less time than coming up with that animation…

God does everything have to be productized and glorified as if you’ve invented a new way of learning. Read some books!

anyone using LLM to learn a new language? got any useful prompts for this?

not all knowledge can easily be translated into a pipeline alike game imho

Another, possibly easier, way is to ask an LLM to give you a quiz on a topic, and then discuss your answers with it.

Surprisingly effective.

Kids use agents for exam training, rather than cheating. Which is great as long as the LLM does not hallucinate

This animation is worse than useless. I've taught a lot of students. This is not learning, it's stamp collecting.

You're just memorizing a nonsensical recipe. What are the constraints? Why do we do X rather than Y? How does a particular thing scale? etc.

All you're doing is fooling yourself into thinking that you've acquired some knowledge. When in reality you haven't even learned the basic mental model to reason about this stuff.

You've learned something when you have a mental model that makes correct predictions. Until then you've memorized it at best, and as with most memorized things it will decay exponentially and will be gone from your memory soon enough.

I love this idea!

> I personally find the style used by LLMs to explain things difficult to follow. It's just too simplistic

I also struggle with LLMs explaining things, but for the opposite reason.

I consistently have problems to get short, precise but plain/simple answers.

Instead I'm overwhelmed with walls of texts, often filled with jargon that is a mixture of imprecise and unneeded.

The style at which I learn better is by asking about stuff interactively. I ask you what something is, you give me a 3-4 sentences top answer. Then I explore and dig into the topic from your answer on the things I want to know better.

i had Bolt create an interactive app teaching me Oberon language but despite several attempts to fix issues, there were still glitches in unexpected places. So the experience was... meh.

Then I went back to a book written by humans (Eric Nikitin's "Realm of Oberon").

"What you get is a beautiful animation that is 100% accurate and free of hallucinations."

Do you know it is free of hallucinations because you crossed checked it with the source material or because you told the LLM "don't hallucinate"

I recently used Opus to create a learning plan in ClickUp for every Tailscale feature and it worked very well.

I mean, yeah, fun project. But that whole game could be like 15 mins of prompting.

once again. state and persistence are the issue. not generic llm inference.

Gell-Mann Amnesia: the blog post

His other project, https://aivestor.tech/, seems like a huge grift.

[flagged]

[dead]

[dead]

[flagged]

[flagged]

I am greatly disturbed by the idea that any of the demonstrations involve "complex topics". Whether it was the silicon workflow, LLMs, or EUV, I saw nothing complex. Are these supposed to be freshman undergrad or even high school level explainers? I suppose I didn't see any glaring errors on a quick glance, but definitely lots of details were glossed over.

Perhaps basic special relativity could be done this way, or simple derivatives, but definitely not general relativity or integrals, much less PDEs. I guess I was hoping for a 3B1B type output. Oh well.