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

541–550 of 562 posts

Re: How I use LLMs to learn complex topics

#541

Post by kurthr »

kingkawn wrote: post #195
kurthr wrote: post #194

I am greatly disturbed by the idea that any of the demonstrations involve "complex topics". Whether it was the silicon workflow, LLMs, or EUV, I saw nothing complex. Are these supposed to be freshman undergrad or even high school level explainers? I suppose I didn't see any glaring errors on a quick glance, but definitely lots of details were glossed over. Perhaps basic special relativity could be done this way, or s…

Rejoice for your chance to brag

What do you consider complex? This might do basic anatomy, or maybe the ~200 bones in the skeletal system, but would you even cover the circulatory system this way? I sure wouldn't try to do liver function with all the feedback systems (bile, pancreas, pituitary) involved.

This might work to explain how a string is stored in different languages, or different sorting mechanisms (bubble vs heap vs insertion vs quick vs merge vs Tim)? That is something covered in 15 minutes of a CS class, but what it misses is why you would choose those mechanisms, and where they are optimal! It's not going to cover a complex topic, like even basic encryption that takes a few classes. In finance it might cover interest or a mortgage payment calculation, but it's not ever going to cover option calculations like Black-Scholes.

The issue is that if all you want to learn are some sequences of words that make is sound like you understand something, but not the processes and models that actually drive the performance and limit the design of that thing, then this "works". But it is classic LLM slop! It's a not good enough to win as a high school science fair entry.

There are things like language learning that I think different techniques could greatly benefit from LLMs. I would love for them to be popularized! I'm sure there are other LLM learning tools that are less gamified, but more effective for actual understanding and depth.

Re: How I use LLMs to learn complex topics

#542

Post by 8bitsout »

aswegs8 wrote: post #382
gavmor wrote: post #68

Earlier quoted context omitted.

Or is it just an unproven attempt? Seems like a pretty straightforward value proposition. Caveat emptor.

If you know anything about investing, you know it is highly likely to be either A a grift or B an innocent, but naive attempt.

From the website:

"Quant Competitions Achievement

In 2024, I achieved 7th place at Quantiacs, a global quantitative trading competition. With a background in financial software, I built AIvestor to democratize AI-powered investing tools that were previously only available to institutions."

I have no idea of the legitimacy of Quantiacs, but for someone with these claims what they are selling is extremely unfaithful. Anyone with a sufficient knowledge of markets would understand the issues with what is being presented on the "portfolio" page, and the approach is bunk.

It appears that the product is based on some vibe-coded slop (https://github.com/LaurentiuGabriel/gpt-trading-agent). I personally would feel bad even thinking about trying to sell something like this to people.

Re: How I use LLMs to learn complex topics

#543

Post by hackrmn »

bryzaguy wrote: post #514
hackrmn wrote: post #509

Earlier quoted context omitted.

There's been research done (I know, big words -- don't have any links readily available), where it was pointing to the fact that what goes easily in (into the brain) also goes easily out, and conversely, what the brain requires effort and literal calories and energy to understand, stays there longer (investment must be rewarded / recouped somehow). So while there's no doubt that facilitating learning is a net-positiv…

Spaced repetition could address this, no? Also, the right example or metaphor can make a difficult concept both easier to understand and stickier in my mind which I think is different than something easy to learn.

I agree regarding metaphors, I myself aggressively utilise analogies with both myself and others, as a "digestive", but I feel like with LLMs we're treading on thin ice as it's not straightforward to classify a particular use case as one scaffolding learning with a metaphor, or just having the opposite effect where your brain "sails" in a faulty sea of "learning" while in reality there's no real work being done, not of the kind the brain needs to do in order to re-order all the synapses and own networks that ends being "knowledge" eventually.

Re: How I use LLMs to learn complex topics

#544

Post by furyofantares »

TooSmugToFail wrote: post #356
furyofantares wrote: post #115

Earlier quoted context omitted.

"Turtles all the way down" is a phrase of, I think, unknown origin ( https://en.wikipedia.org/wiki/Turtles_all_the_way_down ) about infinite regress or trying to patch up some bad theory by appealing to itself. Someone claims that what holds the Earth in place is that it sits atop a giant turtle, and a skeptic asks what holds the turtle up, and the response is that it's turtles all the way down. Personally I think th…

I would have bet it’s a Terry Pratchett quote, and it kinda is: “"The turtle moves," said Didactylos. "The turtle is a giant reptile that swims through space. It doesn't have to stand on anything. Swimming is what turtles do. The idea that it has to stand on another turtle, and that turtle has to stand on another turtle, is just silly. It's turtles all the way down, and that's a logical absurdity." Small Gods, 1992

He's using it but if you CTRL+F the linked wikipedia page for 1967 you get someone using that exact phrase, or for 1882 above you get a pretty close version.

Re: How I use LLMs to learn complex topics

#545

Post by fluoridation »

AgentMatt wrote: post #489
TeMPOraL wrote: post #421

Earlier quoted context omitted.

> Also, parts of reality may appear to be contradictory with each other when some pieces are not known. Exactly. This tells you where something is off. The problem may be your lack of understanding or wrong understanding, or it may be with the source, or the framing, or you may have hit a genuine lack of data - still, the puzzles don't fit in some area. And yes, not all self-consistent understanding is correct. But a…

> But all inconsistent understanding is incorrect. Why do you believe that? Even if we assume that reality itself is self-consistent (what does that even mean?), why would that imply that we humans are able to find a self-consistent representation of it? Maybe reality is self-consistent in some sense but cannot even be represented by the tools we use for theory building. My point being, the ultimate target of our und…

You don't seem to be disagreeing with GP, you're just saying that correctness may be practically impossible.

Re: How I use LLMs to learn complex topics

#546

Post by brcmthrowaway »

8bitsout wrote: post #542
aswegs8 wrote: post #382

Earlier quoted context omitted.

If you know anything about investing, you know it is highly likely to be either A a grift or B an innocent, but naive attempt.

From the website: "Quant Competitions Achievement In 2024, I achieved 7th place at Quantiacs, a global quantitative trading competition. With a background in financial software, I built AIvestor to democratize AI-powered investing tools that were previously only available to institutions." I have no idea of the legitimacy of Quantiacs, but for someone with these claims what they are selling is extremely unfaithful. A…

"Democratize" in 2026 means "sell".

Re: How I use LLMs to learn complex topics

#547

Post by adityazero »

I just ask LLM to to give me a short tutorial on the thing i want to learn but i dont want to start from chapter-1, that is boring. so i upload my resume and say that make this tutorial based on the skillsets i already have.

btw, this is a much better experience than watching Youtube videos for learning.

Re: How I use LLMs to learn complex topics

#548

Post by laurentiurad »

phailhaus wrote: post #505
atroche wrote: post #488

Earlier quoted context omitted.

From the article: > I proceed asking it to build a simulation of that topic in a low-poly, Rollercoaster Tycoon-like animation Sounds like the Rollercoaster Tycoon part is just referring to the aesthetics/graphics, and the author is just suggesting building a top-down isometric 2D animated simulation (which I agree is a bit limiting, there are definitely some things where you'd want to be able to fly around a 3D spac…

Yeah that's the problem. Imagine trying to learn calculus as a top-down isometric 2D animated simulation. It doesn't make sense for the topic.

Calculus probably not, but you can find other types of animations for it. Learning how web requests work definitely fits this animation type.

Re: How I use LLMs to learn complex topics

#549

Post by batshit_beaver »

fl4regun wrote: post #537
batshit_beaver wrote: post #513

Earlier quoted context omitted.

They score 99% but then can’t explain _why_ their solution works with any accuracy. Not as useful for learning as one might think.

are you referring to this section? > Verification is different from generation: Models scoring 98 can solve problems but can't always explain why their approach works at the level a human mathematician would. It doesn't say it can't explain why with any accuracy, it just says it can't *always* explain at the level of a mathematician, but most of us don't have such a mathematician at our beck and call to answer our qu…

It’s not just math. Anecdotally, LLMs struggle the same way with software engineering where the code they write is correct (compiles and passes tests), but reasoning is wrong often enough to eliminate most trust in these models’ ability to explain codebases or even features they themselves produce. It’s not about the _level_ of the supposed intelligence where a model struggles to summarize things succinctly or simply enough (responding to the “pocket mathematician” comment) or can’t grasp certain concepts at all (if so, how tf is it able to apply them?). It’s that by their design LLMs have no concept of truth and no concept of causality. They guess with every single inference and it’s very hard as a user to understand which guesses are more or less certain, since, you know, confidence ratings aren’t part of these models’ design either.

Re: How I use LLMs to learn complex topics

#550

Post by MetroWind »

I mean it's a complex topic alright, but what you can learn with this is just a watered down pop-science level overview, which is not what I would call "learning".

A reasonable test is what I call the enhanced Feynman test: teach what you learnt to others, and be able to defend against reasonable questions.

A stretch goal I sometime use is to be able to read recent papers on the topic.

Post reply on HN