The title is not representing what the post is about. “Use LLM to learn complex topics” here actually means that the author asks an agent to describe the problem area, and then implement a simple web-based simulation game, and by playing that game, the author actually learns about the topic and its constraints. They use chip making as an example.
> 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".
I’ve been using LLMs to create readable rewrites of RFCs and specs that interest me. It is not precise enough for implementation use, but it has increased my understanding of the underlying RFC.
Another useful approach has been asking Codex to implement complex things, like a Kademlia DHT or BitTorrent client in a literate style with the explicit purpose to increase understanding by reviewing the source code.
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
The little tool it outputted is nice, but click around the stages and the text is not high quality at all. The snippy titles, abbrievated explanations, I wish a few more iterations and thought was put into the actual main textual content. Especially for 'complex' stuff
i looked at the animations, they look cool, and i don't think i will enjoy learning things that way. as someone else said, there's a lot of content already produced on these topics. i also think the level at which these animations are playing, they are actually hiding the 'complexity' of these topics.
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.
What’s everyone’s opinion on learning new tech things in this day and age?
My opinion swings between positive and depressing vision of the future.
I still learn new stuff, but I’m afraid it won’t have any value in a year or so.
For example, I’m pretty good at optimizing low level stuff, but right now you can just ask LLMs to do so and they are pretty good at it. They will profile the code and suggest reasonable options like 90% of the time.
If people don't learn, and write, and converse, about new tech, the LLMs will not have raw material to learn their slop from. And I am quite worried that this is the direction we're going in, with the lake of insight being sipped dry and a future of shallow cliches as LLM responses.
I'm also trying out a lot of different approaches, and generally I like the sparring I can get from LLMs but with the acceptance that they make mistakes and some things still need some fact checking. But the models are improving fast, so I'm positive about this approach just becoming better going forward
I'm working on a side-project called tech-professor.com which is a platform for learning. The content is built directly from the source code in your pull request and repositories you follow. So you can quiz yourself and your team based on the code you ship.
It's in beta and a lot of changes are still on the way, but if you want to check it out and give feedback, feel free to sign up for free.
The biggest thing I've learned from doing stuff like this is that there are no shortcuts. At some point or another, to truly learn something deeply, you've got to dig in to the boring details and do things the hard way. LLMs can help with this...but I find it's usually tempting to try and just offload the boring stuff to them, which doesn't work.
The LLMs are a way to get quick feedback and getting it promotes quicker learning (if the feedback is good). Learning is difficult, sometimes I get blocked on something and before llms that could prevent me from learning some material, nowadays I have another tool to help me unblock and learn faster.
I think that could be called a shortcut, not in learning per se, but in the process of getting to learn.
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.
I'm just looking at the rocker engine piece. The belt is running backwards. That's the first thing I'd expect it to get right or flag if it doesn't. Human in the loop is also the quality control. If that fails the rest might have similar issues.
OP posted his rollercoaster tycoon inspired simulator that explained how chips are fabricated. Comments were full of people pointing out inaccuracies and hallucinations.
The problem with LLM explanations of unknown topics is that you literally cannot determine how right or wrong it is. I usually ask LLMs to bring references and they almost always admit they pulled random shit out of their ass and quickly appologize when evidence to the contrary surfaces.
Really neat idea, I think it is one of the best ways to exploit the combined building and explaining capabilities of LLMs.
I am currently building an app/game to explain friends and family concepts around wealth management and wealth building. Games are a great way to hide complexity while still including it in the « guide » you are making.
I use LLMs to learn deep technical concepts. I really like them because I can spend countless hours a day understanding things and building an investigation file with all my findings. I code examples and test the findings. It has helped me understand basically anything.
I'm using LLMs right now to build a terminal browser, a GUI browser, and a PyTorch/LibTorch replacement. It's really fun to be able to learn and make progress this way. It's like reading multiple interactive books, where every concept can be explained again and again until I understand it.
I’ve written a skill that I basically feed what I’m looking to do, some ideas I had for accomplishing it and any other details like tech stack, etc.
The skill then riffs with me, judging my ideas and suggesting alternatives. We go back and forth until something useful comes out of it. This process isn’t unlike how I do normal development.
However, once agreed it breaks the work into “steps”. It then creates a tutorial for me, for those steps, explaining each line, why each change happens etc. I can then ask questions, muse about an alternative idea etc. Then I do the steps, and I’ve learned and gotten what I wanted to get done.
This has been how I’ve been learning Godot and making a game for the past month or so. I didn’t go in blind, I started with a course from GDQuest so I could feel confident guiding the tutorials. I will say though, having a tutor to bounce ideas off of has been really useful.
I still try to figure it out myself, consult the docs, discord etc. But if I’m stumped I’ll run my tutor skill and have some fun.
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
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.
I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tried to use the LLM to fix this by having it generate a web page with diagrams and organized information flow. It's an improvement, but I still run into the issues I described in my first pint - LLM prose is annoyingly dense, and the useful information gets lost in a bunch of noise. You can direct it do something like "use plain English and avoid LLM prose - provide only as much information as necessary to demonstrate the point", but it is once again only a marginal improvement.
And then I begin to think to myself that I should just read a book on the topic written by a trusted source who put a lot of effort into teaching the topic properly and presenting the information in a thoughtful way. So, I am back to books and mostly try to use LLMs to clarify certain questions or ideas I have.
> Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions.
This is the issue with using ChatGPT as-is in the web app. I use ChatGPT/Claude/etc in the Notion web app now to organize my pages of knowledge and keep everything organized. That said, ChatGPT/Claude in Notion seems to produce inferior results than using them directly which is frustrating. I'm not sure why this is but perhaps LLMs in Notion have too much context and get bogged down.
165 comments
[ 3.7 ms ] story [ 175 ms ] threadThat's actually a fun way to learn processes!
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".
Another useful approach has been asking Codex to implement complex things, like a Kademlia DHT or BitTorrent client in a literate style with the explicit purpose to increase understanding by reviewing the source code.
Examples: https://rickcarlino.com/notes/note-dump-and-ai-summaries/ind...
https://github.com/RickCarlino/tiny-bt
Surprisingly effective.
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...
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.
I still learn new stuff, but I’m afraid it won’t have any value in a year or so.
For example, I’m pretty good at optimizing low level stuff, but right now you can just ask LLMs to do so and they are pretty good at it. They will profile the code and suggest reasonable options like 90% of the time.
Career-wise, this is terrible. But for me technology was polluted by the ever-growing greed.
For example I’d much rather actually learn assembly, than learn the nitty-gritty details of how LLMs work.
I'm working on a side-project called tech-professor.com which is a platform for learning. The content is built directly from the source code in your pull request and repositories you follow. So you can quiz yourself and your team based on the code you ship. It's in beta and a lot of changes are still on the way, but if you want to check it out and give feedback, feel free to sign up for free.
I think that could be called a shortcut, not in learning per se, but in the process of getting to learn.
I'm not sure I follow how this is actually guaranteed? The fact-checking process mentioned just seems to involve asking AI to review its own work.
The problem with LLM explanations of unknown topics is that you literally cannot determine how right or wrong it is. I usually ask LLMs to bring references and they almost always admit they pulled random shit out of their ass and quickly appologize when evidence to the contrary surfaces.
Also worth mentioning that Matt Pocock has a /teach skill that creates interactive, learning sites for learning a new skill.
https://github.com/mattpocock/skills/tree/main/skills/produc...
I'm using LLMs right now to build a terminal browser, a GUI browser, and a PyTorch/LibTorch replacement. It's really fun to be able to learn and make progress this way. It's like reading multiple interactive books, where every concept can be explained again and again until I understand it.
The skill then riffs with me, judging my ideas and suggesting alternatives. We go back and forth until something useful comes out of it. This process isn’t unlike how I do normal development.
However, once agreed it breaks the work into “steps”. It then creates a tutorial for me, for those steps, explaining each line, why each change happens etc. I can then ask questions, muse about an alternative idea etc. Then I do the steps, and I’ve learned and gotten what I wanted to get done.
This has been how I’ve been learning Godot and making a game for the past month or so. I didn’t go in blind, I started with a course from GDQuest so I could feel confident guiding the tutorials. I will say though, having a tutor to bounce ideas off of has been really useful.
I still try to figure it out myself, consult the docs, discord etc. But if I’m stumped I’ll run my tutor skill and have some fun.
It reduces friction a ton, but at the end of the day I’m not skipping anything.
And then I begin to think to myself that I should just read a book on the topic written by a trusted source who put a lot of effort into teaching the topic properly and presenting the information in a thoughtful way. So, I am back to books and mostly try to use LLMs to clarify certain questions or ideas I have.
Sounds like you'd be just as well off link-surfing Wikipedia?
This is the issue with using ChatGPT as-is in the web app. I use ChatGPT/Claude/etc in the Notion web app now to organize my pages of knowledge and keep everything organized. That said, ChatGPT/Claude in Notion seems to produce inferior results than using them directly which is frustrating. I'm not sure why this is but perhaps LLMs in Notion have too much context and get bogged down.