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

401–410 of 574 posts

Re: How I use LLMs to learn complex topics

#401

Post by elbear »

__alexs wrote: post #398
fluoridation wrote: post #393

Earlier quoted context omitted.

It's not the same thing. A language is a closed system, it just requires that the participants agree on the rules in order to be successful. Biology is not a language, it's a field of study of phenomena that exist independently of minds. If you read a biology textbook (or an LLM's output about biology) and then relate to someone else what you've read, you and the other person can discuss the topic, and be no closer t…

Biology is in some sense a language, how do we even agree on what the boundaries of biology vs other domains of science are without participants agreeing on the rules? In any case I think you have an overly narrow definition of learning that we're unlikely to come to terms over.

He's talking about learning that makes you operational. If you can speak with someone, then you've learned language. If you can get a computer to do something, then you've learned some programming.

The equivalent for biology would be to grow a plant or a few plants and animals successfully. That's operational at a certain level, you could also be operational at a lower or higher level.

Re: How I use LLMs to learn complex topics

#402

Post by fluoridation »

elbear wrote: post #401
__alexs wrote: post #398

Earlier quoted context omitted.

Biology is in some sense a language, how do we even agree on what the boundaries of biology vs other domains of science are without participants agreeing on the rules? In any case I think you have an overly narrow definition of learning that we're unlikely to come to terms over.

He's talking about learning that makes you operational. If you can speak with someone, then you've learned language. If you can get a computer to do something, then you've learned some programming. The equivalent for biology would be to grow a plant or a few plants and animals successfully. That's operational at a certain level, you could also be operational at a lower or higher level.

No, it doesn't necessarily need to be applicable, it just needs to be testable. The size of the Earth for example may not affect you directly in any way, but it's something you can verify to some degree of precision. But if you just read about it, can you really say that you know it? What if all you believe about the size and shape of the Earth is from what you've asked an LLM? Do you still know it?

EDIT: Perhaps not the best example, because the size and shape of the Earth are data that are repeated often enough that an LLM would be unlikely to quote it grossly incorrectly, but I think my point still comes across.

Re: How I use LLMs to learn complex topics

#403

Post by trueno »

etherlord wrote: post #124
trueno wrote: post #103

Earlier quoted context omitted.

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"

Sanderson is 100% in the training data

damn it good point

Re: How I use LLMs to learn complex topics

#404

Post by trueno »

malfist wrote: post #188
trueno wrote: post #103

Earlier quoted context omitted.

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"

If you don't know why kaladin is emo, did you truly read the books lol. Every character has to deal with the stresses of war and most don't come equipped with good mental health to begin with, they're just normal people

i was more or less testing to see how complete of an answer it could come up by scanning the whole semantic graph so i threw questions at it that spanned multiple books

Re: How I use LLMs to learn complex topics

#405

Post by 8-prime »

FailMore wrote: post #391

I would prefer to view code this way - a flow of data between things... a project I'd really like to work on. Has anyone done anything similar?

There have been numerous approaches doing things akin to that. I remember my university working on such a project. Or at least a similar one, representing a code base as a street network with traffic showing how data flows through the system.

I too, would like to have such a tool for viewing larger projects where the flow can be cumbersome to reason about. One issue I guess would be finding the right level of abstraction in the representation.

Re: How I use LLMs to learn complex topics

#406

Post by manfromchina1 »

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 personally don't get this attitude. For one thing, nobody on earth can give you a 500-word summary of quantum physics in a way that lets you internalize even a tiny bit of it. That's not how you learn anything.

Here's how I do it: I open Baby Rudin (3rd ed.), second chapter, and read the main text - absolute brutality. I unpack almost every sentence with Claude/GPT until I finally get what's going on. No ELI5 nonsense, just examples and counterexamples galore while absorbing the techniques and the way of thinking in analysis/topology. How do I know I've learned the material? By solving every single problem in that chapter. Here's the thing, though: the problems in Rudin can be brutal and decoupled from what's in the text, so if you can handle them, you've definitely mastered the material. No 500-word summary of analysis here.

Re: How I use LLMs to learn complex topics

#407

Post by 0x696C6961 »

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 like to rephrase things in my own words when I read new concepts. The LLM can tell me if my version is totally off.

Re: How I use LLMs to learn complex topics

#408

Post by latexr »

enraged_camel wrote: post #100
dozerly wrote: post #46

Earlier quoted context omitted.

All these LLM-as-review hype pieces don’t acknowledge that it’s turtles all the way down

What do you mean by this?

Other comments have answered in the concrete what was meant, but to answer in the abstract, in case you’re unfamiliar with the expression:

https://en.wikipedia.org/wiki/Turtles_all_the_way_down

Re: How I use LLMs to learn complex topics

#409

Post by sumitkumar »

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…

Agree. Just pay attention to the follow up questions a learner is asking to see the progress. If the follow up is just "continue", "go on", "next" or a non-sequitur then it is smell of a stall. If it is challenging or filling a gap in the answer then it is progress. So production from the learner is the only signal of worth here not the quality of LLM response, the time spent or the ability of the learner to reproduce the facts given by the LLM.

Re: How I use LLMs to learn complex topics

#410

Post by endymion-light »

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.

This would be a valid point maybe 3 years ago, but most chatbots will now query and verify direct sources, especially in research mode.

This is very simple to validate and verify. You could argue it may find false primary sources.

You can condemn models for a variety of other things, but acting as if this is still reality shows a lack of understanding as to modern model capabilities

Post reply on HN