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

361–370 of 574 posts

Re: How I use LLMs to learn complex topics

#361

Post by __alexs »

fluoridation wrote: post #333
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…

>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 unde…

How can you really say you you've learnt the alphabet if you haven't read the document in which the first use of the letter Y appeared?

Re: How I use LLMs to learn complex topics

#362

Post by navigate8310 »

fluoridation wrote: post #346
matheusmoreira wrote: post #340

Earlier quoted context omitted.

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.

It's true in a very real sense, though. Without calibration, how can you tell whether you're learning something real or something fictitious? Imagine trying to learn a language from a single teacher, without ever talking to or corresponding with a native speaker. How could you tell whether you're actually learning the language, or the teacher's unique dialect? Yes, you indeed "learned" something, it's just something…

This made me realize all those benchmarks which unlike loosely acts as a person being awarded with a certificate after his doctorate is rather worthless, for you never know when it bullshit-ted.

Re: How I use LLMs to learn complex topics

#364

Post by elAhmo »

fluoridation wrote: post #359
ChrisGreenHeur wrote: post #358

Earlier quoted context omitted.

Same question applies if you only check it against your children's biology books

Uh, yeah. That's what I said. Did you have a point or...?

For majority of people, especially children, book is an authoritative source. Virtually no one outside of research fields and very excited enthusiasts will check sources in depth to see whether what is shown in the book is true or not.

So, I think the point OP is making is that most people don't really check sources while learning things 'the conventional way'.

Re: How I use LLMs to learn complex topics

#365

Post by num42 »

There is something called tacit knowledge that cannot be easily learned through LLMs. LLMs are currently very good for research and theoretical knowledge. For example, learning how to make mechanical watches involves a lot of hands on, tacit knowledge. That skill would also be transferable to building other precision instruments. I don’t think we can currently learn these kinds of skills easily with the help of LLMs.

Even if you know everything about bicycles their mechanics, components, and how they work you still have to learn how to actually build, repair, or ride one through practice. Knowing, understanding, learning, and practicing are completely different things.

There are also niche areas of expertise that can take years to develop,not just to the point where you know the terminology and jargon, but where you understand the nuances of the field, can recognize the "unknown unknowns", and eventually have the ability to push the boundaries of existing knowledge. Maybe that is what we should really call learning: not simply acquiring information, but developing enough understanding and practical experience to contribute something new to the field.

Ironically, on the same front page of HN, there is a post about Andrew Wiles and this. I don’t think I would be able to comprehend Fermat’s Last Theorem, the Poincaré Conjecture, or Gödel’s Incompleteness Theorems, even with the availability of LLMs.

Re: How I use LLMs to learn complex topics

#366

Post by pasc1878 »

lambda wrote: post #276
voidhorse wrote: post #202

Earlier quoted context omitted.

The "Socratic Method" (aka maieutic) skills annoy me, precisely because when you read them they are the kind of low-effort, low-expertise crap someone who over relies on AI would naively come up with when tasked with the problem of coming up with skills for learning. "Hey the Platonic dialogues are pretty cool and smart, let's do that". The body of literature on learning theory, and beyond that on specific types of l…

Can you provide some references to the research you're referring to? Sounds interesting but you haven't really provided enough information to find it.

That is the point – you can't just provide the references in a short post here.

You need much more time and guidance.

Re: How I use LLMs to learn complex topics

#367

Post by qnleigh »

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…

100% agree. They are not good teachers. Nevertheless I've been using LLMs more and more to learn complex topics, but my learning is always anchored in something else:

- Getting through textbooks and lecture notes. LLMs have gotten very good at answering basic questions on quite advanced material (e.g. representation theory and quantum field theory). By asking a very specific question or even giving the LLM a screenshot, I can get unstuck a lot faster.

- Learning e.g. new python packages. Instead of hunting for examples on Stack Exchange, now I ask an LLM to write a minimal working example and then build off of that. By writing most of the remaining code myself and only using the LLM to answer questions, I've been able to learn new packages significantly faster.

In both cases, the LLM isn't providing the curriculum or guiding what I learn. The textbooks, papers and coding tasks are. But now I can pick these things up much more efficiently.

Re: How I use LLMs to learn complex topics

#368

Post by sciencejerk »

abustamam wrote: post #338
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…

I can't watch Mark Rober's content because of this. He dilutes his remarkable engineering stunts into ADHD internet memes.

Re: How I use LLMs to learn complex topics

#369

Post by fluoridation »

__alexs wrote: post #361
fluoridation wrote: post #333

Earlier quoted context omitted.

>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 unde…

How can you really say you you've learnt the alphabet if you haven't read the document in which the first use of the letter Y appeared?

Because you can successfully use it to communicate with other people. That's the grounding truth. If you'd only ever read about it and never actually employed it then yes, you would not be able to make that claim.

Re: How I use LLMs to learn complex topics

#370

Post by hlovdal »

ixsploit wrote: post #326
SwtCyber wrote: post #313

Earlier quoted context omitted.

I think the key difference here is that you're using the LLM to create exercises, not to replace the learning material

_Doing_ is probably one of the best ways to learn something.

"The best way is to learn"

From the hilarious "There are 3 ways to learn. (Knowledge Fight Animated)"

https://www.youtube.com/watch?v=NsqZZiWDHAQ

Post reply on HN