How I use LLMs to learn complex topics

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

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

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

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

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

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.

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.

I love this idea!

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").

> 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.

"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.

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

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

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

Gell-Mann Amnesia: the blog post

[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.