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.
It's much better to feed the book to the LLM and ask questions as you read along, instead of asking the LLM to basically write a custom book for you from scratch.
I can create a github issue with the information of the books I want to be created, the theme and the persona, and claude routine does the research to create these books. This is for my personal use, so I have the books based on my interests, and created few books based on projects in my Repo as well.
I came across the socratic method recently, and have used it to learn a couple of topics that I was having trouble getting to stick. There are some SKILL.md's available for it. It works for concepts as opposed to facts, and causes the model to guide you to answers through your own reasoning, which is both much more engaging than reading a wall of LLM text and helps the information stick.
i threw the entire sanderson cosmere into a RAG graph sorta deal just to see how it would do if i questioned an mcp server for it about a universe i know decently well. it was actually astoundingly good. was able to find easter eggs acrossed different books and answer dumb questions like "why is kaladin emo"
I've decided that the main thing I'm building is my own mental model. You can take notes, create docs, put graphs and websites together, but unless I'm just trying to generate some reference material the only real objective is to develop the understanding and intuitions inside my own brain.
So I have the LLM offer a very short explanation of something, and from there's it's just me asking questions. Anything that feels fuzzy or not fully internalized is something I poke at until I'm satisfied.
It really has helped me develop a sensitivity to what I understand vs what I don't, and the ability to drill into any part of it is amazing.
>I really don't want to read anything generated by something like Opus 5 at this point.
Personally, I find that its generated prose tends to have an undue weight to it, almost as if every topic I ask about is somehow bears a heavy burden, or is otherwise load-bearing, to use its parlance. Quite puzzling, really.
It has a sort of metronomic quality. It never slows down or speeds up or modulates its tone. It plods forward at a relentless pace and never has a light touch with anything.
I think this is one reason why LLM text is pretty exhausting to read for long stretches.
I have been using LLMs to help me turn my journals into interconnected notes and sometimes it is so confusing to read the notes that it doesn't resemble any human would write. Its like the models are getting stronger while also losing its touch to write human sounding sentences on complex topics.
The sycophancy is also a concern, it’s not really an impartial teacher, all its training is to suck up and maximize engagement rather than learning. The incentives are wrong.
Yeah, I am currently trying to work with Opus 5 to refresh myself on deep learning fundamentals, and... it's a mixed bag. I'm glad I already am familiar with the subject matter, as I can prompt for refinement and improvement. It is kinda following the Karpathy videos so far (a couple lessons in) but adding more math/derivations, which was what I asked for. It has trouble staying on topic, presenting information in a coherent/meaningful order, and providing all the context necessary to move through steps in its "course notes".
Like I said, I'm essentially continually prompting to refine the material. LLMs certainly continue to append, and never cut back. It just keeps spitting out additional content at me. So that's a bit annoying too. But I can basically get figure out what's going on with a few extra promps.
If youre curious what i've got so far... just be warned it is quite literally AI slop plus me continually prompting for clarification/cleanup etc. : https://github.com/cmoscardi/ai-for-ai
opus 5 doesn't follow instructions that great. probably needed that extra "creativity" to benchmax. if you are stuck on anthropic, try Opus 4.8 or Fable5 a try with the same prompts. very different results.
It's just long. It just doesn't shut up. It's overly verbose. And you can't tell it to be concise or you degrade its quality.
If I ask what an integral is, the correct answer is that it is the continuos analog of a sum, generally used to calculate areas and volumes.
It should really be a single sentence, and then let me ask more about the terms I don't understand, and here's the beauty, in the previous one there can be only 5 terms I cannot know.
An LLM will vomit an entire page or more of explanation which isn't bad per se, but is an answer to something different: "give me a short introductory explanation to integrals". And that's not what I asked.
The new Google Translate. They've made it slightly better at translating paragraphs of text but in many cases it's lost the basic function for translation: dictionary.
Try it out, fairly sure that if you out in 100 random words for 30 of them it will just refuse to translate them (it will copy paste the original word into the target language) or it will do silly things like use the target 4th dictionary definition instead of the primary one).
I think AI is surprisingly good at this. I use voice mode while working out to learn complex topics, follow up with reading, and then go back to ask the LLM more questions. They excel at simplifying complex ideas and have endless patience. One hack I found is telling the LLM to test my knowledge by asking me questions—that gives me a clear idea of what to read next. Overall, they’re a great tool to use alongside traditional learning methods like reading books and working through practice problems.
This is on top of the issue of LLMs being a moron. like, I'm sure dumb people can learn stuff from them, but I'm sticking to books written by people who know what they're talking ahout and not vibed slop.
If the output can't be trusted, and you use another llm whose output can't be trusted to check the untrusted output of the first llm, then you're back where you started.
I read it as “if your LLM is being checked by another LLM, well then you need another LLM to check the checker. And can you really trust _that_ LLM? Probably should have an LLM to check the third one, and…”
Agreed. Given how many significant errors LLMs make in my topic of expertise, despite my taking multiple error checking steps, the idea of catching 100% of hallucinations because you told the LLM to check itself is hilarious. It’s just a wild lack of insight: “I’m using the LLM to teach me something I don’t know about, I definitely have the knowledge base to spot any errors that might remain!”
Completely agree. While I didn't set things up to have AI review its output in a loop, my experience trying to build a specific acoustic testing rig with Opus 5 also aligns with the other "it's turtles all the way down" comment.
Opus 5 first built me a detailed plan, but a couple important details were either obviously wrong or felt unnecessary. I went back and forth asking for sources and more information probably like 4 times and every time it did the "in looking at things in more detail it appears my previous advice was incorrect" spiel. It just became exhausting at some point because it feels like it really lays bare how LLMs are just minimizing that loss function but don't actually "understand" anything. It was really useful as a search engine (it correlated some highly relevant source docs), but I just couldn't trust it to believe it was actually done at any step.
I could certainly envision a scenario whereby review would increase reliability but not how it would every guarantee 100%, there is a pretty big logical gap there.
In my experience it depends on how much in detail you want to go. Chip manufacturing is a really opaque industry, so in this particular case LLMs might not even have the training data. However, using it for a high-level introduction into something is usually pretty safe from hallucinations.
I thought after reading the title that the text was about learning something, yet the actual text seems to be about having a system do something for me.
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.
They're amazing at it, provided you keep asking the right questions.
Trust me when I say that in the hands of someone who doesn't have your experience, the LLMs would not be getting the results you get.
You might think what you're doing is trivial, it may be sessions that flow roughly, "Instrument this, okay this part is slow, profile this part, OK read the profile output and suggest a better approach".
But your experience will be steering it in the right direction, and you're probably unaware of just how much your experience is doing that guiding, as the LLM shoots off at 100mph, you feel like it's taking you with it, but you will be guiding it a lot more than you realise, and that's where learning and experience comes in, even if you're no longer operating at the lowest depth, your knowledge of that layer will be helping.
If nothing else, the experience to know when something is actually slow is a skill in itself. If a function takes 200ms, sometimes that's as quick as it can realistically go, and sometimes that's literally a million times slower than it could be, and there's actual skill and experience wrapped up in knowing what "slow" looks like.
I can only speak for myself, so I hope this resonates with you.
I wasn’t even really concerned with optimizing low level code before LLMs and that wasn’t why I was hired either.
However following that low level thread: We can look at the reasonable options and immediately know if they’re reasonable or nonsense. Why? We know the code. Now zoom a level out, where I think our expertise really lies.
Building a complex system isn’t easy. There are customers with requirements, there are budgets, SLAs etc. Sometimes one customer needs X and one needs Y. Our expertise is taking all of this in, and producing something that balances all the different variables. It’s knowing that we’ll expect X events a second so we’ll need Y to ensure we can tolerate failure.
Is it possible LLMs will be able to do all of that too? Maybe. But then why would our customers need the enterprises they pay for?
Generally speaking, the pattern is that people are overestimating how much "work replacement" will happen, and underestimating how much "work shifting" will happen.
What is fascinating is how you can witness it at so many levels of organization. One example: Employer executive get enamored with moving from labor to capital. They believe that by using LLMs, they can replace a lot of workers. At my place of employment, we have people that are surprised they can't file a Jira ticket describing a product ask, and have it kick off an implementation. You can build the skill to attempt that, but invariably you'll get back questions like "what do you mean by <x>" and "what do you want to do in this case, a, b, or c?"; questions that a product person or an exec are not well suited to answer.
In the past, programmers did that kind of interpretation and judgment call. So then you're in a quandary; who should do that work? Work that previously, you never imagined was an inherent part of what the replaceable code monkeys do at your beck and call?
And then, how do you hire for that? How do you find the training for the people that are experienced enough with... something... to know what a cohesive error response is, or what kind of telemetry strategy is best for that particular product and organization, what collection of product asks are incredibly complicated for what they're asking and can deliver 95% of the benefits at 5% of the work if we just do this instead, and whether you want to aim more towards thick or thin clients?
Who are those people? Wait, those are programmers? Wait, there's this whole collection of inherently human skills that we devalued, by not appreciating they were always quietly doing that for us in the past?
That's just one example. There's a repeating pattern of discovering where the work truly is, work that was embedded in manual patterns we might not have to involve ourselves with anymore, but is yet still essential. So the nature of our jobs changes massively, but the overall level of employment does not.
At least, not in the medium to long term. There is a lot of painful churn we have to suffer through first.
I sometimes get vague ideas for solving maths/science problems. They never pan out but i can talk in detail on group theory and advanced maths and science topics due to investigating such vague ideas over the years. These days the LLM shoots the ideas down instantly and honestly correctly, i know enough to know "yeah that's right, oh well" and move on. Which actually takes away a huge avenue of learning. I'm pretty torn on the outcome of this honestly.
I'm not 'wasting time' but I'm also not really learning.
There’s still an immense value in training the brain to learn and be able to approach new problems with the sort of procedural thinking that LLMs enable. We can explore topics that we are curious about and develop that sort of “muscle” to continue asking questions when we have them. I have no fear that when those bigger (and existential) problems arise we’ll be well equipped to keep asking questions and figuring out ways to solve them.
There's a big gap between being able to ask questions about something and understanding something.
The more things you understand, the higher the chance you'll spot a situation to use them in the future.
I think the best innovations come from times when someone is uniquely able to combine two of their previous experiences together. The more experiences you have in your back pocket the more combinations you have access to and the more likely you'll have a unique combination when the right problem comes along.
So you think building a warp drive is pointless because 99% of work, per your judgement, will be done by AI? Is your contribution meaningless and artifact useless? I wouldn't think so.
> I still learn new stuff, but I’m afraid it won’t have any value in a year or so.
This is silly. This would be like arguing that encyclopedias made knowing things pointless. I learn new stuff for me.
Professionally, it's important to know enough to know if you're going in the correct direction. Practically, tokens are going to continue to cost money and knowledge can save you tokens.
I mean, part of the reason the LLM can do that is because you know enough to direct the LLM to do so and verify the results to some degree, right? It's good to learn new things because:
1. It satisfies you curiosity (and curiosity is always valuable)
2. You can better utilize the LLM to expedite something you now have knowledge about
3. You still improve as an engineer/programmer/prompter/whatever
I still think it's very important not to outsource everything to AI because there is a lot of value in learning and doing things yourself which is an important part of life.
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.
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.
I’ve found that if I’m not struggling I’m not learning. If stuff is coming fast and easy that’s a sign that what I’m doing is not stretching existing skills enough.
It’s true of most things. Running, dieting, weightlifting being uncomfortable is a sign of progress.
Having an initial higher level understanding across the domain is extremely useful to contextualize the deeper stuff. I think boring details is a very leaky characterization, but I'll continue with it.
In my experience it's infinitely easier and faster to learn deep, "boring" things when you understand how they relate to your shallow and wide understanding of all of the related components.
The LLM is merely a tool. And you can use it for domain discovery that enables efficient deep learning at an unprecedented rate or you can develop a cursory understanding of a topic and think yourself an expert.
Quite - you still have to do the work yourself. I think LLMs are best placed to act as an eager tutor that doesn't mind discussing a topic ad nauseam until you're certain you understand it.
yes i've found that there are a few topics that i've really been able probably 10x my understanding of using LLMs, in particular in getting me over hoops that are hard to navigate when solo, BUT I have to be really careful for it to not just show me the answer all the time.
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.
Its fun but is it really effective ? I mean I checked the LLM one and I came out more confused about a topic I already know about, I find the best way to to learn using LLMs is to just generate an example try to somewhat get a mental model of how it works and then ground my understanding with traditional documentation and resources, its an iteration of a technique I used to do in college where I would read the textbook questions first to understand what is important and then read the chapter
I assume different ways of learning work for different people. For me personally, it's taking a piece of paper and drawing the diagram of how things work together; of if it's some math, then, again, using the pen and paper to follow the text. I can very much accept that for some people playing the simulation is a good way to touch the new problem space. I can easily imagine that for some topics, let's say, traffic signal automation, a careful simulation game will probably give more information than reading papers or manuals.
Game-based learning, described by Comenius, works if someone else prepares “a game” for you. E.g. like a dungeon master. :)
Otherwise you probably get more confused as you have mentioned.
On the other side, Peter Diamandis describes a situation where a bunch of kids were given a internet-connected computer and they had no teacher. Instead of it there was a “grandma” that checked kids from time to time.
After that there was a knowledge test that revealed “no teacher” approach was more efficient.
Thanks! The original title was "How I use LLMs to learn...", but somehow HN removed the "How" part. I even removed the initial post thinking it was a typo on my end and tried to post again, but I stumbled upon the same behavior.
Imo the podcast and the video are better served as background material for some other task. The low bandwidth becomes an advantage because it's often ok if you miss out on some parts due to lack of attention.
Indeed it's often a waste of time to just focus on talking people fully if you want to learn fast, reading and especially deliberate practice are better for that. But if you don't have the time, energy or focus, then listening to interviews in the background can be useful supplementally
I wish there was a LLM tool to explore a topic recursively, as a tree or a mindmap. You would start with some high level concept (say "cryptography") then dig further and further to more specific topics.
I think that would be a way more natural way to explore than being stuck on the classic linear output of a LLM.
I've been using them by reading some docs/wiki/tutorial, then when I think I understand something trying to do a rough explanation to the LLM and ask if I'm right. I'm usually making some analogy to something I already understand a little. I'm usually partially right but missing some key bits at the first pass. I go back and forward asking for explanations of various bits or asking for resources around the area I'm not understanding. Often times just discovering the relevant name for the area of study opens lots of doors. I basically use it like I would talk to a knowledgeable and patient teacher.
As for how useful it is to understand thins, I believe it's still useful and hope it will continue to be.
Gamifying the presentation could make topics more accessible to others. For me the overhead wouldn't help with my own learning. Also I've been burned by just learning things mechanistically (e.g., coding, applying algebraic rules), so I'm leery of learning just by making flashcards or models of the topic.
I find LLM's do great for learning when I ask what are the principles, how the main applications work, what are the key drawbacks, where are the growth plates in the field, etc. - the kind of thing a good advisor points to. Sometimes I have to ask it explicitly to use topological order of topics and show relations, which often highlights the gradient changes in the learning curve. For pruning, it's surprisingly good applying philosophical heuristics - Occam's razor, or Derrida's differance (the difference that makes a difference), etc.
And finally, no learning is effective without problem sets, and for those LLM's at times get me over blocking issues.
The degenerate case is memorizing the glib phrases regurgitated back to me; they're helpful and functional enough to get me into real trouble!
This guy is severely milking it now. If learning means building an inaccurate and incomplete understanding of the topic then go hog wild. Otherwise https://news.ycombinator.com/item?id=49209049 sums up my feelings about the author's attitude.
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.
I’ve started doing a similar thing after reading a post on hn about manually applying the code so that you actually understand it.
I have done this for all my work this week and it works quite well.
For one it lets you actually query the LLM as to why, their plans give a high level not every single change and it allows you to correct it as you go and the plan will change.
Something that I have realized recently is that it has become so easy to get an answer to almost any question with the help of chatbots that its almost unnecessary to spend any effort thinking about the problem or the solution. I feel like before when I had to spend time researching a problem to find an answer I learned so many things around the topic itself which helped me understand the problem itself better and gained a deeper understanding. Today it feels like you can have an answer to the most complex questions you might have, yet you gain a superficial understanding of the topic and might forget about it quickly.
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.
If you're using LLMs to learn or for research, and at some point you don't end up engaging with an actual resource (books, papers, lectures, web pages, etc) then you're playing yourself.
Personally I'm excited about these sorts of experiments. We all learn in different ways, and these sorts of techniques allow us to create "on-demand" syllabuses and lessons that fit our learning style and learning level.
It's not perfect, but I'm optimistic this will be a useful way to teach/learn in the future.
And, to be clear, I think this will be best utilized within a group/community setting. I don't think it will replace teachers or classrooms.
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.
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
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 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.
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
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.
> 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 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.
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!
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'm also not sure you can really learn chip production from widely available public information. It's a hugely complex industry where the details tend to shape larger strategies. For example, you can't really understand the relationship between Micron and TSMC without some awareness of the trade-offs of memory processes for peripheral transistors.
YouTube is just a big dump of information. Having a structured way to learning along with interacting helps you learn. Otherwise you're just binging information
> 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 an internal company assessment I needed to pass before end of our fiscal year. The study material consisted of 10 ppt decks about 80 slides each (so around 800 total). I had an AI read all the decks and compose a study guide with quizzes along the way. It came up with a 100page word doc that I used in place of the decks to prepare. It worked very well for this including, like you said, quizzing me over various sections.
(Yes I confirmed it was ok to use AI with the material)
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.
It's much better to feed the book to the LLM and ask questions as you read along, instead of asking the LLM to basically write a custom book for you from scratch.
I have this as a side project to create LLM generated books when my usage credit is left on my CC subscription.
https://sunprema.github.io/books/
I can create a github issue with the information of the books I want to be created, the theme and the persona, and claude routine does the research to create these books. This is for my personal use, so I have the books based on my interests, and created few books based on projects in my Repo as well.
If you are interested, here are the skills https://github.com/sunprema/kit
This is the repo where books are stored. https://github.com/sunprema/books
I came across the socratic method recently, and have used it to learn a couple of topics that I was having trouble getting to stick. There are some SKILL.md's available for it. It works for concepts as opposed to facts, and causes the model to guide you to answers through your own reasoning, which is both much more engaging than reading a wall of LLM text and helps the information stick.
Can you link the Skills.md?
I was so annoyed I made a Socratic wrapper based on predefined curriculum:
https://adaptive.bounded.cc
Trying to diagrams/animations didn't yield good results even with frontier models. But pure text, any model does a decent job.
i threw the entire sanderson cosmere into a RAG graph sorta deal just to see how it would do if i questioned an mcp server for it about a universe i know decently well. it was actually astoundingly good. was able to find easter eggs acrossed different books and answer dumb questions like "why is kaladin emo"
I've decided that the main thing I'm building is my own mental model. You can take notes, create docs, put graphs and websites together, but unless I'm just trying to generate some reference material the only real objective is to develop the understanding and intuitions inside my own brain.
So I have the LLM offer a very short explanation of something, and from there's it's just me asking questions. Anything that feels fuzzy or not fully internalized is something I poke at until I'm satisfied.
It really has helped me develop a sensitivity to what I understand vs what I don't, and the ability to drill into any part of it is amazing.
>I really don't want to read anything generated by something like Opus 5 at this point.
Personally, I find that its generated prose tends to have an undue weight to it, almost as if every topic I ask about is somehow bears a heavy burden, or is otherwise load-bearing, to use its parlance. Quite puzzling, really.
It has a sort of metronomic quality. It never slows down or speeds up or modulates its tone. It plods forward at a relentless pace and never has a light touch with anything.
I think this is one reason why LLM text is pretty exhausting to read for long stretches.
I have been using LLMs to help me turn my journals into interconnected notes and sometimes it is so confusing to read the notes that it doesn't resemble any human would write. Its like the models are getting stronger while also losing its touch to write human sounding sentences on complex topics.
The sycophancy is also a concern, it’s not really an impartial teacher, all its training is to suck up and maximize engagement rather than learning. The incentives are wrong.
Have you tried using the caveman skill ? :D Might be worth a try if you dont like long prose https://github.com/JuliusBrussee/caveman
Yeah, I am currently trying to work with Opus 5 to refresh myself on deep learning fundamentals, and... it's a mixed bag. I'm glad I already am familiar with the subject matter, as I can prompt for refinement and improvement. It is kinda following the Karpathy videos so far (a couple lessons in) but adding more math/derivations, which was what I asked for. It has trouble staying on topic, presenting information in a coherent/meaningful order, and providing all the context necessary to move through steps in its "course notes".
Like I said, I'm essentially continually prompting to refine the material. LLMs certainly continue to append, and never cut back. It just keeps spitting out additional content at me. So that's a bit annoying too. But I can basically get figure out what's going on with a few extra promps.
If youre curious what i've got so far... just be warned it is quite literally AI slop plus me continually prompting for clarification/cleanup etc. : https://github.com/cmoscardi/ai-for-ai
opus 5 doesn't follow instructions that great. probably needed that extra "creativity" to benchmax. if you are stuck on anthropic, try Opus 4.8 or Fable5 a try with the same prompts. very different results.
It annoys me that the default AI mode is so tedious and longwinded. I read a lot of nonfiction - the house style of AI is basically marketing copy.
LLMs help me refine my search. If I want to dive deeper into any topic, I can yield a strong list of primary sources relatively quickly.
> First, I get exhausted reading LLM prose.
Often "be concise, to the point." is enough, but you can also paste it some stuff you like as an example text and ask to do style transfer.
> LLM prose is annoyingly dense
It's just long. It just doesn't shut up. It's overly verbose. And you can't tell it to be concise or you degrade its quality.
If I ask what an integral is, the correct answer is that it is the continuos analog of a sum, generally used to calculate areas and volumes.
It should really be a single sentence, and then let me ask more about the terms I don't understand, and here's the beauty, in the previous one there can be only 5 terms I cannot know.
An LLM will vomit an entire page or more of explanation which isn't bad per se, but is an answer to something different: "give me a short introductory explanation to integrals". And that's not what I asked.
The new Google Translate. They've made it slightly better at translating paragraphs of text but in many cases it's lost the basic function for translation: dictionary.
Try it out, fairly sure that if you out in 100 random words for 30 of them it will just refuse to translate them (it will copy paste the original word into the target language) or it will do silly things like use the target 4th dictionary definition instead of the primary one).
I think AI is surprisingly good at this. I use voice mode while working out to learn complex topics, follow up with reading, and then go back to ask the LLM more questions. They excel at simplifying complex ideas and have endless patience. One hack I found is telling the LLM to test my knowledge by asking me questions—that gives me a clear idea of what to read next. Overall, they’re a great tool to use alongside traditional learning methods like reading books and working through practice problems.
This is on top of the issue of LLMs being a moron. like, I'm sure dumb people can learn stuff from them, but I'm sticking to books written by people who know what they're talking ahout and not vibed slop.
I have been using this tool for the past few months that was posted on here: https://github.com/devenjarvis/lathe
It generates tutorials for you, and serves a webpage that lets you complete them. It does a remarkable job.
It still has a bit of the LLM prose problem, but it does help you fine tune the ‘voice’ it uses.
> What you get is a beautiful animation that is 100% accurate and free of hallucinations.
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.
All these LLM-as-review hype pieces don’t acknowledge that it’s turtles all the way down
What do you mean by this?
If the output can't be trusted, and you use another llm whose output can't be trusted to check the untrusted output of the first llm, then you're back where you started.
I read it as “if your LLM is being checked by another LLM, well then you need another LLM to check the checker. And can you really trust _that_ LLM? Probably should have an LLM to check the third one, and…”
Agreed. Given how many significant errors LLMs make in my topic of expertise, despite my taking multiple error checking steps, the idea of catching 100% of hallucinations because you told the LLM to check itself is hilarious. It’s just a wild lack of insight: “I’m using the LLM to teach me something I don’t know about, I definitely have the knowledge base to spot any errors that might remain!”
Completely agree. While I didn't set things up to have AI review its output in a loop, my experience trying to build a specific acoustic testing rig with Opus 5 also aligns with the other "it's turtles all the way down" comment.
Opus 5 first built me a detailed plan, but a couple important details were either obviously wrong or felt unnecessary. I went back and forth asking for sources and more information probably like 4 times and every time it did the "in looking at things in more detail it appears my previous advice was incorrect" spiel. It just became exhausting at some point because it feels like it really lays bare how LLMs are just minimizing that loss function but don't actually "understand" anything. It was really useful as a search engine (it correlated some highly relevant source docs), but I just couldn't trust it to believe it was actually done at any step.
I could certainly envision a scenario whereby review would increase reliability but not how it would every guarantee 100%, there is a pretty big logical gap there.
In my experience it depends on how much in detail you want to go. Chip manufacturing is a really opaque industry, so in this particular case LLMs might not even have the training data. However, using it for a high-level introduction into something is usually pretty safe from hallucinations.
I thought after reading the title that the text was about learning something, yet the actual text seems to be about having a system do something for me.
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.
They're amazing at it, provided you keep asking the right questions.
Trust me when I say that in the hands of someone who doesn't have your experience, the LLMs would not be getting the results you get.
You might think what you're doing is trivial, it may be sessions that flow roughly, "Instrument this, okay this part is slow, profile this part, OK read the profile output and suggest a better approach".
But your experience will be steering it in the right direction, and you're probably unaware of just how much your experience is doing that guiding, as the LLM shoots off at 100mph, you feel like it's taking you with it, but you will be guiding it a lot more than you realise, and that's where learning and experience comes in, even if you're no longer operating at the lowest depth, your knowledge of that layer will be helping.
If nothing else, the experience to know when something is actually slow is a skill in itself. If a function takes 200ms, sometimes that's as quick as it can realistically go, and sometimes that's literally a million times slower than it could be, and there's actual skill and experience wrapped up in knowing what "slow" looks like.
“asking the right questions” is built on years of experience doing the things now being offloaded to AI
“asking the right questions” is also a moving target with each model release
People simply underestimate the value of doing the work and think that the end result is all that matters
I can only speak for myself, so I hope this resonates with you.
I wasn’t even really concerned with optimizing low level code before LLMs and that wasn’t why I was hired either.
However following that low level thread: We can look at the reasonable options and immediately know if they’re reasonable or nonsense. Why? We know the code. Now zoom a level out, where I think our expertise really lies.
Building a complex system isn’t easy. There are customers with requirements, there are budgets, SLAs etc. Sometimes one customer needs X and one needs Y. Our expertise is taking all of this in, and producing something that balances all the different variables. It’s knowing that we’ll expect X events a second so we’ll need Y to ensure we can tolerate failure.
Is it possible LLMs will be able to do all of that too? Maybe. But then why would our customers need the enterprises they pay for?
Generally speaking, the pattern is that people are overestimating how much "work replacement" will happen, and underestimating how much "work shifting" will happen.
What is fascinating is how you can witness it at so many levels of organization. One example: Employer executive get enamored with moving from labor to capital. They believe that by using LLMs, they can replace a lot of workers. At my place of employment, we have people that are surprised they can't file a Jira ticket describing a product ask, and have it kick off an implementation. You can build the skill to attempt that, but invariably you'll get back questions like "what do you mean by <x>" and "what do you want to do in this case, a, b, or c?"; questions that a product person or an exec are not well suited to answer.
In the past, programmers did that kind of interpretation and judgment call. So then you're in a quandary; who should do that work? Work that previously, you never imagined was an inherent part of what the replaceable code monkeys do at your beck and call?
And then, how do you hire for that? How do you find the training for the people that are experienced enough with... something... to know what a cohesive error response is, or what kind of telemetry strategy is best for that particular product and organization, what collection of product asks are incredibly complicated for what they're asking and can deliver 95% of the benefits at 5% of the work if we just do this instead, and whether you want to aim more towards thick or thin clients?
Who are those people? Wait, those are programmers? Wait, there's this whole collection of inherently human skills that we devalued, by not appreciating they were always quietly doing that for us in the past?
That's just one example. There's a repeating pattern of discovering where the work truly is, work that was embedded in manual patterns we might not have to involve ourselves with anymore, but is yet still essential. So the nature of our jobs changes massively, but the overall level of employment does not.
At least, not in the medium to long term. There is a lot of painful churn we have to suffer through first.
> I still learn new stuff, but I’m afraid it won’t have any value in a year or so.
I have stuff to do now, the value of the knowledge in a year or two isn't important if it solves the issues I have today.
I sometimes get vague ideas for solving maths/science problems. They never pan out but i can talk in detail on group theory and advanced maths and science topics due to investigating such vague ideas over the years. These days the LLM shoots the ideas down instantly and honestly correctly, i know enough to know "yeah that's right, oh well" and move on. Which actually takes away a huge avenue of learning. I'm pretty torn on the outcome of this honestly.
I'm not 'wasting time' but I'm also not really learning.
There’s still an immense value in training the brain to learn and be able to approach new problems with the sort of procedural thinking that LLMs enable. We can explore topics that we are curious about and develop that sort of “muscle” to continue asking questions when we have them. I have no fear that when those bigger (and existential) problems arise we’ll be well equipped to keep asking questions and figuring out ways to solve them.
There's a big gap between being able to ask questions about something and understanding something.
The more things you understand, the higher the chance you'll spot a situation to use them in the future.
I think the best innovations come from times when someone is uniquely able to combine two of their previous experiences together. The more experiences you have in your back pocket the more combinations you have access to and the more likely you'll have a unique combination when the right problem comes along.
One possible value in learning new things is developing a habit of learning.
In particular it might be valuable to be in the habit of learning things that one is bad at doing.
Or not.
So you think building a warp drive is pointless because 99% of work, per your judgement, will be done by AI? Is your contribution meaningless and artifact useless? I wouldn't think so.
The way learning new stuff rewires your brain cannot really be predicted, but the effects are positive.
I don’t agree with the implication that there has to be a practical reason to learn new things. I enjoy learning new technologies because it’s fun.
> I still learn new stuff, but I’m afraid it won’t have any value in a year or so.
This is silly. This would be like arguing that encyclopedias made knowing things pointless. I learn new stuff for me.
Professionally, it's important to know enough to know if you're going in the correct direction. Practically, tokens are going to continue to cost money and knowledge can save you tokens.
I mean, part of the reason the LLM can do that is because you know enough to direct the LLM to do so and verify the results to some degree, right? It's good to learn new things because:
1. It satisfies you curiosity (and curiosity is always valuable)
2. You can better utilize the LLM to expedite something you now have knowledge about
3. You still improve as an engineer/programmer/prompter/whatever
I still think it's very important not to outsource everything to AI because there is a lot of value in learning and doing things yourself which is an important part of life.
I decided to learn watchmaking instead
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.
Examples: https://rickcarlino.com/notes/note-dump-and-ai-summaries/ind...
https://github.com/RickCarlino/tiny-bt
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.
I’ve found that if I’m not struggling I’m not learning. If stuff is coming fast and easy that’s a sign that what I’m doing is not stretching existing skills enough.
It’s true of most things. Running, dieting, weightlifting being uncomfortable is a sign of progress.
Having an initial higher level understanding across the domain is extremely useful to contextualize the deeper stuff. I think boring details is a very leaky characterization, but I'll continue with it.
In my experience it's infinitely easier and faster to learn deep, "boring" things when you understand how they relate to your shallow and wide understanding of all of the related components.
The LLM is merely a tool. And you can use it for domain discovery that enables efficient deep learning at an unprecedented rate or you can develop a cursory understanding of a topic and think yourself an expert.
Quite - you still have to do the work yourself. I think LLMs are best placed to act as an eager tutor that doesn't mind discussing a topic ad nauseam until you're certain you understand it.
yes i've found that there are a few topics that i've really been able probably 10x my understanding of using LLMs, in particular in getting me over hoops that are hard to navigate when solo, BUT I have to be really careful for it to not just show me the answer all the time.
I’ve been doing something similar (browser only interactive courses served from GitHub pages) to teach me topics from beginner to advanced
LLMs and systems intersection - https://kernelspace.naigap.com
Distributed systems - https://byzantine.play.naigap.com
These are high quality at first glance. the visualizations and exercises are helpful.
What is your process for creating these resources?
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.
That's actually a fun way to learn processes!
Its fun but is it really effective ? I mean I checked the LLM one and I came out more confused about a topic I already know about, I find the best way to to learn using LLMs is to just generate an example try to somewhat get a mental model of how it works and then ground my understanding with traditional documentation and resources, its an iteration of a technique I used to do in college where I would read the textbook questions first to understand what is important and then read the chapter
I assume different ways of learning work for different people. For me personally, it's taking a piece of paper and drawing the diagram of how things work together; of if it's some math, then, again, using the pen and paper to follow the text. I can very much accept that for some people playing the simulation is a good way to touch the new problem space. I can easily imagine that for some topics, let's say, traffic signal automation, a careful simulation game will probably give more information than reading papers or manuals.
> a careful simulation game
Totally agree, unfortunately careful simulation games are very rare
Game-based learning, described by Comenius, works if someone else prepares “a game” for you. E.g. like a dungeon master. :)
Otherwise you probably get more confused as you have mentioned.
On the other side, Peter Diamandis describes a situation where a bunch of kids were given a internet-connected computer and they had no teacher. Instead of it there was a “grandma” that checked kids from time to time.
After that there was a knowledge test that revealed “no teacher” approach was more efficient.
But it was a group, not an individual activity…
Thanks! The original title was "How I use LLMs to learn...", but somehow HN removed the "How" part. I even removed the initial post thinking it was a typo on my end and tried to post again, but I stumbled upon the same behavior.
HN likes to remove “How” and “Why” from titles. You need to edit them back right after you post it
I guess we all learn in different ways. I prefer reading, and can fairly fast find the articles that make sense to me.
Colleagues often suggest podcasts and videos - I very, very rarely listen to them or see them.
The bandwidth is too low. It's not efficient and ultimately I'm bored.
This is a nice project, it looks cute. I watched some of the pages But I want more than that, more information, and faster - still a Wiki fan.
Also, step number 2 in the flow: have the LLM check itself... Naah, I don't believe that.
But you're not the only using gen ai like that. Take care.
Imo the podcast and the video are better served as background material for some other task. The low bandwidth becomes an advantage because it's often ok if you miss out on some parts due to lack of attention.
Indeed it's often a waste of time to just focus on talking people fully if you want to learn fast, reading and especially deliberate practice are better for that. But if you don't have the time, energy or focus, then listening to interviews in the background can be useful supplementally
I wish there was a LLM tool to explore a topic recursively, as a tree or a mindmap. You would start with some high level concept (say "cryptography") then dig further and further to more specific topics.
I think that would be a way more natural way to explore than being stuck on the classic linear output of a LLM.
I've been using them by reading some docs/wiki/tutorial, then when I think I understand something trying to do a rough explanation to the LLM and ask if I'm right. I'm usually making some analogy to something I already understand a little. I'm usually partially right but missing some key bits at the first pass. I go back and forward asking for explanations of various bits or asking for resources around the area I'm not understanding. Often times just discovering the relevant name for the area of study opens lots of doors. I basically use it like I would talk to a knowledgeable and patient teacher.
As for how useful it is to understand thins, I believe it's still useful and hope it will continue to be.
Gamifying the presentation could make topics more accessible to others. For me the overhead wouldn't help with my own learning. Also I've been burned by just learning things mechanistically (e.g., coding, applying algebraic rules), so I'm leery of learning just by making flashcards or models of the topic.
I find LLM's do great for learning when I ask what are the principles, how the main applications work, what are the key drawbacks, where are the growth plates in the field, etc. - the kind of thing a good advisor points to. Sometimes I have to ask it explicitly to use topological order of topics and show relations, which often highlights the gradient changes in the learning curve. For pruning, it's surprisingly good applying philosophical heuristics - Occam's razor, or Derrida's differance (the difference that makes a difference), etc.
And finally, no learning is effective without problem sets, and for those LLM's at times get me over blocking issues.
The degenerate case is memorizing the glib phrases regurgitated back to me; they're helpful and functional enough to get me into real trouble!
This guy is severely milking it now. If learning means building an inaccurate and incomplete understanding of the topic then go hog wild. Otherwise https://news.ycombinator.com/item?id=49209049 sums up my feelings about the author's attitude.
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.
I’ve started doing a similar thing after reading a post on hn about manually applying the code so that you actually understand it.
I have done this for all my work this week and it works quite well.
For one it lets you actually query the LLM as to why, their plans give a high level not every single change and it allows you to correct it as you go and the plan will change.
Something that I have realized recently is that it has become so easy to get an answer to almost any question with the help of chatbots that its almost unnecessary to spend any effort thinking about the problem or the solution. I feel like before when I had to spend time researching a problem to find an answer I learned so many things around the topic itself which helped me understand the problem itself better and gained a deeper understanding. Today it feels like you can have an answer to the most complex questions you might have, yet you gain a superficial understanding of the topic and might forget about it quickly.
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.
My high hopes were quickly dashed at the step that involved turning a complex topic into rollercoaster tycoon.
If you're using LLMs to learn or for research, and at some point you don't end up engaging with an actual resource (books, papers, lectures, web pages, etc) then you're playing yourself.
Personally I'm excited about these sorts of experiments. We all learn in different ways, and these sorts of techniques allow us to create "on-demand" syllabuses and lessons that fit our learning style and learning level.
It's not perfect, but I'm optimistic this will be a useful way to teach/learn in the future.
And, to be clear, I think this will be best utilized within a group/community setting. I don't think it will replace teachers or classrooms.
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.
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
This is a great share, gonna come back to it.
Also worth mentioning that Matt Pocock has a /teach skill that creates interactive, learning sites for learning a new skill.
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 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.
https://model-systems-labs.github.io/latent/llm-systems/less...
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
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.
anyone using LLM to learn a new language? got any useful prompts for this?
AKA - How I skim read a lot and learn nothing of value.
> 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".
Too over engineered, few text paragraphs would suffice to understand the topic.
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.
not all knowledge can easily be translated into a pipeline alike game imho
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!
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'm also not sure you can really learn chip production from widely available public information. It's a hugely complex industry where the details tend to shape larger strategies. For example, you can't really understand the relationship between Micron and TSMC without some awareness of the trade-offs of memory processes for peripheral transistors.
YouTube is just a big dump of information. Having a structured way to learning along with interacting helps you learn. Otherwise you're just binging information
Is there a way we could turn this into a reusable skill?
> 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.
Gell-Mann Amnesia: the blog post
"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.
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 had an internal company assessment I needed to pass before end of our fiscal year. The study material consisted of 10 ppt decks about 80 slides each (so around 800 total). I had an AI read all the decks and compose a study guide with quizzes along the way. It came up with a 100page word doc that I used in place of the decks to prepare. It worked very well for this including, like you said, quizzing me over various sections.
(Yes I confirmed it was ok to use AI with the material)
I love this idea!
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.
Or is it just an unproven attempt? Seems like a pretty straightforward value proposition. Caveat emptor.
What does this have to do with the topic?