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

491–500 of 572 posts

Re: How I use LLMs to learn complex topics

#491

Post by vonneumannstan »

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…

Idk about other people but the way I usefully use llms to help with study is to treat them as a good tutor. If you are stuck on a problem or need an explanation of a concept it helps greatly. Much of the actual process of studying Math, Physics, CS, etc in University is sitting in a room working on problem sets and now you can do that with the equivalent of a highly competent Grad Student to bug with any issue you run in to. However yes trying to get an LLM to draft a 1000 ft view of an entire field and calling that learning is a poor use case.

Re: How I use LLMs to learn complex topics

#492

Post by endymion-light »

dns_snek wrote: post #468
endymion-light wrote: post #410

Earlier quoted context omitted.

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

Your comment is phrased as if it somehow refutes their point but it doesn't. > Cause if you went back and forth with ChatGPT for an hour it definitely hallucinated and lied to you at some point. If you're asserting that this is not the case today then that's going to be require pretty extraordinary evidence. "Chatbots use Google now" is not evidence that the information they provide is in fact correct. They don't hal…

Firstly, I can't refute a point that's little more than an opinion - my doubt is that a modern frontier model is significantly hallucinating within a relatively short conversation that can easily be verified. There is no way to refute or accept the point without a complete conversation log. I am criticizing the hyperbolic nature of the comment.

I doubt you are getting to the context level of model degredation where it reaches context limits within a verbal hour conversation.

I've just tried to recreate your example on sonnet 5, and as someone who has done DIY projects it reads completely appropriate, but I'm happy for criticism from a shed builder. It never once tells me about paper machie or creates a silly example.

This is via a prompt requesting tools and materials, and could be further improved, unfortunately, I can't paste the markdown formatting provided.

""" Reference size used below: 8x10 ft shed. Scale material quantities to your dimensions.

Step 1: Check Regulations & Plan Materials: None yet — just your design/plan (graph paper or free shed-plan software)

Tools: None

Skills to find: None required, but if your shed is large or near a boundary, a quick chat with your local planning/building department saves headaches later

What to do: Confirm permit requirements, setback distances from boundaries, and max height/size allowed without permission. Sketch your design and finalize dimensions.

Step 2: Prepare the Site Materials: Landscape fabric (weed barrier) Gravel/crushed stone (for drainage base, ~4-6 in depth) Marking spray paint or stakes + string

Tools: Shovel & spade Wheelbarrow Rake Hand tamper or plate compactor Spirit level (4 ft) or laser level Tape measure Builder's square (for squaring corners)

Skills to find: Basic site leveling — not hard, but a laser level rental helps a lot if the ground has any slope If you have poor drainage/heavy clay soil, worth asking a landscaper for advice What to do: Clear vegetation, mark the footprint, excavate and level, add compacted gravel base for drainage.

... """

I won't include the whole document, can share it further but anyone can replicate just by asking sonnet

I just don't understand the need for such hyperbole, and pretending that models are still gpt3, when you can get counter evidence in seconds.

It reminds me of the craze teachers had against trusting Wikipedia - yes, you shouldn't take all claims at face value, but arguing that nothing from Wikipedia could be useful just makes the argument silly.

Re: How I use LLMs to learn complex topics

#493

Post by vonneumannstan »

tcp_handshaker wrote: post #473
Jtarii wrote: post #430

Earlier quoted context omitted.

If you have an actual mathematics professor to ask questions to then sure do that, but most people don't have that luxury. Also the error rate of frontier LLMs on textbook highschool/college level mathematics is going to be extremely low. It is also significantly more engaging and fun.

>> the error rate of frontier LLMs on textbook highschool/college level mathematics is going to be extremely low. The scientific basis for this statement is unclear.

>The scientific basis for this statement is unclear.

Is it? Actually this seems like one of the MOST clear aspects of LLM performance we can measure.

Re: How I use LLMs to learn complex topics

#494

Post by nicf »

defmacr0 wrote: post #444
sublinear wrote: post #423

Earlier quoted context omitted.

Is that meaningfully different from the study methods of the past? That doesn't require an LLM, and using one risks correctness in exchange for speed. You might not even get that speed if you're stuck in the weeds often enough. A decade ago, a google search for study guides written by another professor would have been slightly slower. A decade before that, you'd be even slower fumbling through several books. Every si…

I certainly would only trust my textbook as the authoritative source, but i can see that in the absence of an expert teacher it's nice to have something that can critique a proof. Imo the fact that it's hard to verify that your own proof is correct is one of the main barriers in self-studying math, especially if one is at a level where one is not completely fluent in applying the various techniques. This also applies…

I'm a private math tutor specializing in exactly this sort of material, and I agree with this very strongly. Knowing what "counts" as a proof is one of the most common gaps I see in students who come to me after self-studying, and most students do need some back-and-forth with an expert to really get that skill down. I imagine that LLM's could be very helpful for this if they were used judiciously!

Re: How I use LLMs to learn complex topics

#495

Post by atroche »

Even better (for some topics) would be to play a Factorio-style game (or a Factorio mod).

Leaving aside the whole can-we-trust-LLMs aspect, the ChipTycoon page is not really a simulation, and the animation doesn't actually add anything. I like the author's intent, but there's a lot of work to do still before he makes this useful.

Surprised no one's dropped a link to Bret Victor's https://worrydream.com/LadderOfAbstraction/ ("A Systematic Approach to Interactive Visualization") yet.

Re: How I use LLMs to learn complex topics

#497

Post by lelanthran »

knollimar wrote: post #234
calf wrote: post #120

Earlier quoted context omitted.

LLM is still too verbose, a real person Socratic conversation can interact a couple sentences at a time, not spew 1-3 windowfuls of low density bullet points. I even wonder if this behavior is due to next-token prediction architectures, somehow.

I don't understand some previous complaints. It's dense and verbose seem at ends to me. I know you probably don't consider it dense but wondering if someone can shed insight. I find them like empty calories, like programming youtube tutorials. They maximize for feeling learnt instead of steady progress

> I don't understand some previous complaints. It's dense and verbose seem at ends to me

It's dense along the wrong axis and verbose Along the wrong axis.

Like having acres of cardboard for dinner: you have too much dinner with not enough nutrition. Your dinner is plentiful and still not enough.

Re: How I use LLMs to learn complex topics

#499

Post by dns_snek »

endymion-light wrote: post #492
dns_snek wrote: post #468

Earlier quoted context omitted.

Your comment is phrased as if it somehow refutes their point but it doesn't. > Cause if you went back and forth with ChatGPT for an hour it definitely hallucinated and lied to you at some point. If you're asserting that this is not the case today then that's going to be require pretty extraordinary evidence. "Chatbots use Google now" is not evidence that the information they provide is in fact correct. They don't hal…

Firstly, I can't refute a point that's little more than an opinion - my doubt is that a modern frontier model is significantly hallucinating within a relatively short conversation that can easily be verified. There is no way to refute or accept the point without a complete conversation log. I am criticizing the hyperbolic nature of the comment. I doubt you are getting to the context level of model degredation where i…

Err, that wasn't meant as literal example because real conversations obviously have more than 1 turn. The only thing you could prove by getting a different result is that they don't _always_ do that, even if I shared the full conversation log.

You "don't understand the need for such hyperboles" because they're not hyperboles, I don't know how you can not pick up on these errors in your own conversations.

> and pretending that models are still gpt3

I explicitly said that the new ones are better. How's that for hyperbole?

Re: How I use LLMs to learn complex topics

#500

Post by cyrialize »

I've just been using LLMs (specifically DuckDuckGo's chat) to help find research and articles to dive into.

I don't really see the point of asking LLMs to summarize something for me when I can just read about it myself.

I will do chats back and forth about specific topics, but then always ask for follow up resources I could dive into.

This isn't fool proof - I'll sometimes get resources that aren't really what I'm looking for - but it feels better than searching the web.

Especially when I don't have a clear idea of what search terms to look for.

I haven't tried things like the Socratic method though or having LLMs teach me something! I've really just been focused on reading lately.

Post reply on HN