How I use LLMs to learn complex topics • Hacker News Board

Re: How I use LLMs to learn complex topics

#481

Post by ethbr1 » Mon, Aug 10, 2026, 1:30 PM UTC

cube00 wrote: post #479

tcp_handshaker wrote: post #472

Earlier quoted context omitted.

Plus they will take one hour to explain what could take 2 min, just to keep you on the platform....

The algorithm wanted these "educational" videos to be 10 minutes at first and now it seems to want them to be 20 minutes. Once I saw that I realised just how padded the content really was and started looking elsewhere. Other good tells the content is low quality or a bad fit for video are excessive amounts of talking head (should have been a podcast) or stock video clips (it's video, show me something).

Listening to YouTube on 2x makes it slightly bearable.

But this was also the joke about TED Talks: everyone came away smugly confident they were part of an amazing tide of progress, ignoring any engineering or scaling challenges.

Re: How I use LLMs to learn complex topics

#482

Post by phailhaus » Mon, Aug 10, 2026, 1:34 PM UTC

The fact the author thinks every topic can be fit onto a rollercoaster tycoon-style analogy leads me to think they do not actually understand these topics very well.

Re: How I use LLMs to learn complex topics

#483

Post by jmuguy » Mon, Aug 10, 2026, 1:34 PM UTC

dbreunig wrote: post #226

> What you get is a beautiful animation that is 100% accurate and free of hallucinations How does he know?

I think these same people believe everything they see on TV, unless the thing on TV is something they already knew about.

Re: How I use LLMs to learn complex topics

#484

Post by jupi2142 » Mon, Aug 10, 2026, 1:38 PM UTC

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 agree. If it's not followed by a test/exam, then it's entertainment, not learning.

Re: How I use LLMs to learn complex topics

#485

Post by embedding-shape » Mon, Aug 10, 2026, 1:43 PM UTC

KeplerBoy wrote: post #411

embedding-shape wrote: post #397

Earlier quoted context omitted.

> To be fair the entry barrier got a lot lower over the past ~5 years. Now you can write very good CUDA kernels with just a few lines of python DSL code. Zero cpp boilerplate and zero explicit compiler calls. Well, yeah, but what I've being doing is learning proper CUDA, not "Python-compiled-to-CUDA" (otherwise it'd take like a just a week to understand enough :P ) and that's looking more or less the same today (alth…

I wouldn't call one proper CUDA and the other one some dumbed down version. Nvidia really seems to be pushing for these DSLs to be first class within the ecosystem. In some cases probably even more cutting edge than the nvcc frontend, since it's easier to do some experimenting on a new niche package than on the tool everyone relies on. I believe more and more production code is running kernels which didn't originate…

> I wouldn't call one proper CUDA and the other one some dumbed down version. Nvidia really seems to be pushing for these DSLs to be first class within the ecosystem.

I wouldn't say one is dumbed down either, just different, at least the entrypoints and how you end up using the different solutions.

I'm currently experimenting with cuda-oxide for some new simulations, and managed to keep the entire simulation within just Rust essentially, while going the "traditional" (maybe better term than "proper"?) way I've ended up with a bunch of .cu files and then integrating them (via cudarc usually). Kernels themselves feel the same across both, but the integration clearly makes them different enough that I think it's worth distinguishing them, at least for clarity if nothing else.

If someone else already knew Rust but not C++, wanted to get into CUDA programming, going the cuda-oxide route would probably be easier and more familiar, than cudarc, I'd guess. Personally I'm not sure what route I prefer yet, both (as always?) have tradeoffs.

Re: How I use LLMs to learn complex topics

#486

Post by AgentMatt » Mon, Aug 10, 2026, 1:46 PM UTC

TeMPOraL wrote: post #374

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…

Self-consistency and consistency with your lived experience are good heuristics. Reality is self-consistent, so anything that doesn't add up indicated an error in the source or your understanding of it (or both). EDIT: I think it's a kind thing you need to tune yourself into. OTOH, I've observed many (most?) people seemingly being completely oblivious to self-consistency issues of their beliefs and mental models, or…

> I've observed many (most?) people seemingly being completely oblivious to self-consistency issues of their beliefs and mental models, or even texts they're reading or instructions they're following, and yet... somehow they're generally more successful at life because of it

What do you mean by "successful at life" here? Genuine happiness, fulfillment in life? Or in the sense of doing well by what society holds as it's current interpretion of what one should strive for, and otherwise just kinda drifting through life?

Because if it's the latter, I'd say that is to be expected. It's much simpler to put your energy into fulfilling the expectations of whoever is your superior in your current group, mostly get the expected reward, and then just coast. Reflection and experimentation, which is required to get to self-consistent views, takes effort and and the willingness to question existing beliefs, which will also be uncomfortable times.

Re: How I use LLMs to learn complex topics

#487

Post by Thanemate » Mon, Aug 10, 2026, 1:48 PM UTC

I once uploaded a 700 pages book and quizzed chatGPT strictly on its contents. It answered somewhere between 60-90% across 6 quizzes. This was 2 months ago. Those quizzes were fact checking statements, not even problem solving.

I'd be extremely cautious to ask it to have it explain any specialized concept even from a document.

Re: How I use LLMs to learn complex topics

#488

Post by atroche » Mon, Aug 10, 2026, 1:59 PM UTC

phailhaus wrote: post #482

The fact the author thinks every topic can be fit onto a rollercoaster tycoon-style analogy leads me to think they do not actually understand these topics very well.

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 space in first person, move time back and forth, manipulate parts of it).

Re: How I use LLMs to learn complex topics

#489

Post by AgentMatt » Mon, Aug 10, 2026, 1:59 PM UTC

TeMPOraL wrote: post #421

snmx999 wrote: post #388

Earlier quoted context omitted.

Reality is most likely self-consistent, but as we can only experience a tiny part of it it‘s impossible to tell. Also, parts of reality may appear to be contradictory with each other when some pieces are not known.

> 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 understanding may be self-consistent, but the way we _necessarily_ have to reduce it to lossy theories means that we can only ever approach it with a non-zero error. And a theory focusing on one aspect, minimizing representational error from one direction of approaching it, necessarily has to make assumptions that will contradict those made by another theory trying to minimize representational error coming from another direction / domain.

Re: How I use LLMs to learn complex topics

#490

Post by refactor_master » Mon, Aug 10, 2026, 2:02 PM UTC

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.

AIME and HMMT are high school math olympiad competitions now used to benchmark AI. Frontier models score 95-99%

https://benchlm.ai/blog/posts/aime-hmmt-competition-math