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

281–290 of 574 posts

Re: How I use LLMs to learn complex topics

#281

Post by rDr4g0n »

bumby wrote: post #280
rDr4g0n wrote: post #270

Earlier quoted context omitted.

LLMs can't "read the room" and infer how much context the audience already has, so they try include everything. human conceptual thinking is very much a multi-dimensional graph, which relies on light "approximate" concepts that are "good enough". LLM AR token generation is extremely one dimensional and doesnt care about the "weight" of the concept behind a token. LLMs hold billions of parameters in "mind" at once. hu…

I’m curious where you get the estimate that humans hold “like four” parameters in their mind at once?

updated the comment. i meant four "concepts". i dont reason about my own thinking in terms of parameters.

Re: How I use LLMs to learn complex topics

#282

Post by unethical_ban »

PsylentKnight wrote: post #251
intrasight wrote: post #170

Earlier quoted context omitted.

Make it your goal to teach a room full of other humans that topic. I guarantee you will know that material cold. I've done lots of technical training in my career and after teaching a class two or three times I find myself to be very competent in the topic. It's long been the case that the best way to learn something is to teach something.

> It's long been the case that the best way to learn something is to teach something Which is pretty unfortunate for those that want to learn. I used to enjoy writing documentation at work, it was my favorite part of the job. And it did feel like it benefited me more than it benefited all the people that were (or weren't) reading my documentation. Now I can't really justify spending much time on docmentation when LLM…

There is still value in experts distilling knowledge and crafting it to the audience. I'm a consultant in cybersecurity and someone asked me "give me a best practice framework for good policy hygiene". I'm sure an LLM could spit out some tips, but I've been on the industry 15 years and can write in 5 pages what an LLM wouldn't conceive of in that space.

Re: How I use LLMs to learn complex topics

#283

Post by wannabe44 »

PaulStatezny wrote: post #141
rl3 wrote: post #73

Earlier quoted context omitted.

> I really don't want to read anything generated by something like Opus 5 at this point. Personally, I find that its generated prose tends to have an undue weight to it, almost as if every topic I ask about somehow bears a heavy burden, or is otherwise load-bearing , to use its parlance. Quite puzzling, really.

Yes! I have a personal theory: LLMs are *fundamentally* handicapped at perceiving what's going on in the mind of the human (this can't be "innovated away") and that's at the root of what makes them suck at conversation. Next time you're chatting with someone, notice how much understanding is shared without anything being said. E.g. the other person might share something deeply disappointing, and they can tell without…

No, they're just trained to impress the C-suite motherfuggers with dense vocab.

Re: How I use LLMs to learn complex topics

#284

Post by peab »

copperx wrote: post #53
8bitsout wrote: post #48

I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tri…

It's much better to feed the book to the LLM and ask questions as you read along, instead of asking the LLM to basically write a custom book for you from scratch.

I also agree with this. LLMs are a great companion when reading a book to clarify things and dive into specific topics.

I'd imagine an application that uses LLMs will be created that better manages learning. It's just not clear what that UX is yet- it's obviously not just a chatbot

Re: How I use LLMs to learn complex topics

#285

Post by DrewADesign »

unclebucknasty wrote: post #245
DrewADesign wrote: post #219

Earlier quoted context omitted.

The fact that some people get genuine value from LLMs when learning doesn’t contradict the fact that they’re Dunning-Krueger “expertise” generators. The fact that the person learning from them is in charge of ensuring they aren’t full of shit, which they frequently are, is an inescapable flaw in this process. I honestly think that reduces the value of these things to just above what you can find out with a search eng…

Sounds about right. Tangentially, but related: I'm old enough to remember when the spirit of your comment was pervasive on HN.

It wasn’t even all that long ago. I noticed around the time ChatGPT 3.5 was released I saw a significant change in tone regarding LLMs and diffusion models. I think that’s when some serious astroturfing started.

I’m old enough that I worked my first IT summer job the same year slashdot was founded. I’ve seen a lot of tech tribalism form and dissipate, and this one didn’t feel organic. My gut says a lot of the us-vs-them tension originated in a deliberate campaign to cast AI boosters as the tech industry in-crowd, and ‘other’ the people not on-board. Who knows.

Re: How I use LLMs to learn complex topics

#286

Post by DrewADesign »

champagnepapi wrote: post #277
unclebucknasty wrote: post #197

Earlier quoted context omitted.

I've (elsewhere) written about this diminishing return effect on LLM utility in relation to increasing expertise. The question: what's the net positive gain of turning people who know nothing in a given field into sub-novices, while weighing actual experts down with work slop and marginal returns? And I wonder what the true cost is of arming so many novices with that level of dangerous knowledge.

I think the true cost will be some catastrophic failures. Just hoping folks don’t get hurt due to people not understanding what they’re doing with these things but believing they’re competent.

If that is the case, I seriously doubt the blame would ever touch the people that oversold this shit.

Re: How I use LLMs to learn complex topics

#287

Post by btown »

bumby wrote: post #280
rDr4g0n wrote: post #270

Earlier quoted context omitted.

LLMs can't "read the room" and infer how much context the audience already has, so they try include everything. human conceptual thinking is very much a multi-dimensional graph, which relies on light "approximate" concepts that are "good enough". LLM AR token generation is extremely one dimensional and doesnt care about the "weight" of the concept behind a token. LLMs hold billions of parameters in "mind" at once. hu…

I’m curious where you get the estimate that humans hold “like four” parameters in their mind at once?

Cowan (2001) is an oft-cited paper proposing three to five "chunks" of capacity in human attention: https://www.cambridge.org/core/journals/behavioral-and-brain...

The full PDF is worth a read (Figure 1 may be of interest to many here): https://www.cambridge.org/core/services/aop-cambridge-core/c...

If "attention is all you need" then it's something we do indeed lack, in comparison to LLMs! But it's an interesting question: might machine cognition benefit from similar bottlenecks in an attention algorithm? Advancements like Kimi Linear seem to indicate that we're far from the finish line: https://arxiv.org/abs/2510.26692

Re: How I use LLMs to learn complex topics

#289

Post by tarkin2 »

f311a wrote: post #21

What’s everyone’s opinion on learning new tech things in this day and age? My opinion swings between positive and depressing vision of the future. I still learn new stuff, but I’m afraid it won’t have any value in a year or so. For example, I’m pretty good at optimizing low level stuff, but right now you can just ask LLMs to do so and they are pretty good at it. They will profile the code and suggest reasonable optio…

Not good at subjects you have no previously learnt knowledge.

They tell you have "hit the nail on the head" when you really haven't.

They tell you have had a "great insight" when you are really haven't.

They give you the illusion of learning and progress but essentially give you faulty preconceptions will trip you up further down the road.

You can ask the LLM to be more critical and less sycophantic but that only gets you so far:

They want you to continue using, being dependent on and feeding data into the LLM--your independence isn't a priority.

Post reply on HN