Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How I use LLMs to learn complex topics

laurentiugabriel.github.io

Post reply on HN
Print view View original

331–340 of 574 posts

Re: How I use LLMs to learn complex topics

#331

Post by djaro »

yoyohello13 wrote: post #58
royal__ wrote: post #24

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.

This is also why apps like Duolingo don't work for most users. They want to turn language learning into a fun, effortless game but effortless is fundamentally incompatible with learning.

Learning is uncomfortable. Reading a difficult (for you) text in a language you don't understand is exhausting and confusing. But that is where improvement happens.

Its even worse since Duolingo added a life system (not sure if they still use it), where you were only allowed to make 3 mistakes before having to recharge your energy. If you get everything right, you are not learning, you SHOULD be making mistakes constantly. That shows you're actually being challenged.

Re: How I use LLMs to learn complex topics

#332

Post by abustamam »

bilbo-b-baggins wrote: post #329
fy20 wrote: post #322

Earlier quoted context omitted.

I think it depends on what you want to learn and what your definition of "learnt" is. The other day I realised I had no idea how DNA and life works. I guess I studied it at high school (25 years ago), but maybe it didn't go into much detail or it just didn't click. So I asked ChatGPT to explain it to me, I came up with my own mental model from it's explanation, told it that, then it corrected me where I misunderstood…

Or do you? Cause if you went back and forth with ChatGPT for an hour it definitely hallucinated and lied to you at some point. Maybe consider using something else like Brilliant.org if you want to learn a topic, yanno, so you don’t propagate whatever hallucination from ChatGPT to your kids.

These days online courses like Brilliant and such are likely largely LLM generated. Are they actually vetted by experts before publication? Who knows. My money is on no, or at least, not until someone complains.

Its easy enough to prompt ChatGPT for primary sources when doing research to validate any claims its making.

Re: How I use LLMs to learn complex topics

#333

Post by fluoridation »

fy20 wrote: post #322
matherial wrote: post #306

This is, without exaggeration, probably the fiftieth blog post or long-form comment about how someone is using an LLM for "complex learning", and I'd just really like to see at least one of these to be accompanied by a statement saying what are the kinds of problems the author can now confidently solve that they couldn't before. In my experience, LLMs are really good for taking up your time and making you feel like y…

I think it depends on what you want to learn and what your definition of "learnt" is. The other day I realised I had no idea how DNA and life works. I guess I studied it at high school (25 years ago), but maybe it didn't go into much detail or it just didn't click. So I asked ChatGPT to explain it to me, I came up with my own mental model from it's explanation, told it that, then it corrected me where I misunderstood…

>So I asked ChatGPT to explain it to me, I came up with my own mental model from it's explanation, told it that, then it corrected me where I misunderstood things. We went backwards and forwards for an hour, me asking questions, it correcting me, until I felt like I understood the whole picture.

If you're only checking your understanding against the one source you used to obtain it, how can you tell whether your understanding coincides with reality (or rather, with general scientific understanding), and not just with the source you read? And I'm not asking just about ChatGPT; the same question could apply to any source. Books are not exempt from containing errors.

Re: How I use LLMs to learn complex topics

#334

Post by fluoridation »

matheusmoreira wrote: post #307
matherial wrote: post #306

This is, without exaggeration, probably the fiftieth blog post or long-form comment about how someone is using an LLM for "complex learning", and I'd just really like to see at least one of these to be accompanied by a statement saying what are the kinds of problems the author can now confidently solve that they couldn't before. In my experience, LLMs are really good for taking up your time and making you feel like y…

> don't really teach you anything Dunno, I've been learning a lot of Rust in the past few days. Just dove right into a project and asked AI to teach me stuff on a need to know basis. I'm actually getting used to Rust by now.

A programming language is a skill with an accessible source of irrefutable feedback. If the program doesn't work, then you did something wrong. What happens if you try to learn something less concrete or less testable, like quantum mechanics, as the GP suggested?

Re: How I use LLMs to learn complex topics

#335

Post by hasley »

One of the most exciting things about LLMs for me is to have someone with which I can discuss about technical/scientific/engineering things. Since usually I do not have a human at hand (or do not want to annoy people around me). Especially conversations that involve formulae can get really interesting and insightful.

Of course, you have to be careful with the answers. Especially when the discussions get longer. But usually I see that it is time to stop or to start a new session when the formulae do not make so much sense anymore or when the LLM repeats itself.

But with enough caution, LLMs are really a not-so-bad intellectual sparring partner for discussing ideas and insights.

Re: How I use LLMs to learn complex topics

#336

Post by freefaler »

Yes, there are many misconceptions on "learning", but LLM can be useful.

The approach that works for me is using Justin's skycak methods he mentions in his books:

https://www.justinmath.com/books/

Check the shorter "Advice on upskilling" or "The Math Academy way" for well researched approach.

So what works for me

- open a project in ChatGPT/Notebook LM - dump all the relevant and highly cited materials (textbooks, papers) - dump the advice on upskilling text or a short summary I've written for the LLM

- create "Learning Goals", that contain what I want to learn, and how to estimate is my level good enough

1) Ask it to create a learning path from the materials, following the approach. Give that to an adversarial LLM for cross check. (just for sanity check)

2) Ask it to create an "entry test" to check what I do know and what I don't

3) Iterate step by step on each module/submodule from the learning path that intermingles the approach of: small theory step + small practical task + small test. Log what's missing/wrong in my dept log. Give the dept log at the end of the session to the LLM to incorporate/create another test/task.

What I have found useful in this approach is that it will generate a lot of practical tests/tasks for me and it will explain a concept in many ways until I understand it. Also it finds some prerequisites I might miss, but based on my tests and debt log unexpected things I thought I understood surface.

So with the limits of LLM and while building a mental map of the relevant parts it's usually enough to spot the hallucinations, but if you apply structured approaches these are minimal. And it's super good, because the number of practice tests and explanations is endless.

The interfaces are a bit clunky, but current multimodal LLMs are ok with images or even hand writing.

I will recommend that structured approach.

Re: How I use LLMs to learn complex topics

#337

Post by copperx »

gb2d_hn wrote: post #80
copperx wrote: post #53

Earlier quoted context omitted.

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 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 came across the socratic method recently

This statement would out you as someone who didn't attend an elite school.

Re: How I use LLMs to learn complex topics

#338

Post by abustamam »

matherial wrote: post #306

This is, without exaggeration, probably the fiftieth blog post or long-form comment about how someone is using an LLM for "complex learning", and I'd just really like to see at least one of these to be accompanied by a statement saying what are the kinds of problems the author can now confidently solve that they couldn't before. In my experience, LLMs are really good for taking up your time and making you feel like y…

> many of the popular educational videos on YouTube are fun to watch and don't really teach you anything.

As a tangent, I think the concept of pop science has wasted so much time of what could be considered brilliant minds. I can't believe how much YouTube people I consider really smart consume under the guise of "learning stuff." And the videos are always designed to be addicting and to entice you to watch other of their stuff, which makes sense, because theyre a business, not a school.

I'm guilty of wasting time on YouTube as much as anyone else (I like watching stand-up routines and Red Bull extreme sports) but I am never under the guise that I'm doing anything productive with my time. Its okay to have fun learning, but I always felt that entertainment and education should be kept separate. You gotta learn something intentionally, not just get it served to you via algorithm.

Note im talking about the educational "shorts" not the 60+ minute deep dives that are basically a college level lecture.

Re: How I use LLMs to learn complex topics

#339

Post by 2muchcoffeeman »

matheusmoreira wrote: post #307
matherial wrote: post #306

This is, without exaggeration, probably the fiftieth blog post or long-form comment about how someone is using an LLM for "complex learning", and I'd just really like to see at least one of these to be accompanied by a statement saying what are the kinds of problems the author can now confidently solve that they couldn't before. In my experience, LLMs are really good for taking up your time and making you feel like y…

> don't really teach you anything Dunno, I've been learning a lot of Rust in the past few days. Just dove right into a project and asked AI to teach me stuff on a need to know basis. I'm actually getting used to Rust by now.

AI is a super polarising topic. Even now there are people who are like “it’s all AI slop so it’s all useless” along with the “OMG AI!!! OMG we will have AGI soon!!!” people.

The truth, as always, is in between. There’s loads of people using it for useful things, learning, automation and getting good results. But it’s also wrong enough that you need to deploy it carefully sometimes.

Don’t worry about either group. Keep objective and use AI where it helps and do it yourself where you are better. That’s all.

Re: How I use LLMs to learn complex topics

#340

Post by matheusmoreira »

fluoridation wrote: post #334
matheusmoreira wrote: post #307

Earlier quoted context omitted.

> don't really teach you anything Dunno, I've been learning a lot of Rust in the past few days. Just dove right into a project and asked AI to teach me stuff on a need to know basis. I'm actually getting used to Rust by now.

A programming language is a skill with an accessible source of irrefutable feedback. If the program doesn't work, then you did something wrong. What happens if you try to learn something less concrete or less testable, like quantum mechanics, as the GP suggested?

I agree with you. I'm also using AI to help me learn electronics so I can finally make some real stuff I can hold in my hands. Lots of hard engineering involved so I'm a lot less confident in my ability to spot the AI's own mistakes.

However, saying you can't learn "anything" is just too strong. I'm definitely managing to distill the AI's weights into my own brain.

Post reply on HN