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

251–260 of 574 posts

Re: How I use LLMs to learn complex topics

#251

Post by PsylentKnight »

intrasight wrote: post #170
gofreddygo wrote: post #148

Earlier quoted context omitted.

I have to agree with this. Completely relying on LLM for all your learning needs is a disaster. But being absolutely against use of LLMs isn't doing you any favors. This is where you don't have a formula but rely on you judgement and evidence of your having learnt something. For example having an LLM summarize a dense topic and to find books so that you can filter faster and spend time reading those books works way b…

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's can do it in a fraction of the time and it's "good enough"

Re: How I use LLMs to learn complex topics

#252

Post by giancarlostoro »

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.

Whats funny about LLMs is they are trained from books, but they are also trained to not output books, so how much of an LLM skews its output because a perfectly normal sentence could be a quote in like 300 different books?

Re: How I use LLMs to learn complex topics

#253

Post by intrasight »

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…

I got started as a software engineer working in the nuclear industry in the 80s. We measured our documentation in inches not pages, and it was all written by hand. And I'll bet you the documentation in the nuclear industry is still written by hand and not by LLMs.

Re: How I use LLMs to learn complex topics

#254

Post by eru »

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…

> First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point.

Agreed.

I find Opus 5, and even Fable, to be overly wordy in eg PR descriptions and code comments.

However, I suspect that's more to do with what they are trained to do by default than LLMs in general. I have a little setup where I tell Claude to work together with Codex to tighten up prose and comments, and for me that produces much more palatable text that needs less human editing afterwards.

Re: How I use LLMs to learn complex topics

#255

Post by maplethorpe »

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…

I'm choosing to (mostly) switch off the news and continue learning things I find interesting anyway. Maybe the world will punish me for it at some point, but I guess I'll have to deal with that when it happens. The alternative is too depressing otherwise.

Re: How I use LLMs to learn complex topics

#256

Post by Revanche1367 »

I only use LLMs for explaining things if the subject is one I’m deeply familiar with and can independently and easily verify the facts. Doing so with new knowledge areas is very risky for obvious reasons.

For example, “explain how the code in this file works,” I am familiar with the overall codebase, I know the purpose of the file, and I can read it or write tests to verify if I suspect what it’s telling me isn’t correct. Or, if it’s really important, I can overcome my introvertedness and ask the team member who wrote it…but that’s a last resort nowadays, which I am very thankful for. In 99% of cases since at least Claude 4.2 days, Claude and Codex have been very accurate. Gemini on the other hand messes up more frequently and sometimes does weird things like try to delete files it’s not familiar with, at least the 3.6 flash model I’ve been using lately does this. But, code explanations are still good for the most part.

Re: How I use LLMs to learn complex topics

#257

Post by controlbird »

Revanche1367 wrote: post #256

I only use LLMs for explaining things if the subject is one I’m deeply familiar with and can independently and easily verify the facts. Doing so with new knowledge areas is very risky for obvious reasons. For example, “explain how the code in this file works,” I am familiar with the overall codebase, I know the purpose of the file, and I can read it or write tests to verify if I suspect what it’s telling me isn’t cor…

100% agreed.

Re: How I use LLMs to learn complex topics

#258

Post by coderatlarge »

avilay wrote: post #227
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…

I have had very similar experience! I wanted to learn Probablistic ML, checked out a couple of MOOCs, but didn't find any that were at my level - some were too advanced, some too beginner level. Claude was unable to one-shot a course, so I am now asking it to generate it module by module. But even here, it is not doing a very good job. I muddle through the concepts that it has written, do a whole bunch of back-and-fo…

i’m personally deriving a huge amount of value from the custom materials fable is assembling for me. for example i asked it to write a focused expository math paper on reed solomon to accompany an implementation module that it wrote for me. it’s remarkably useful to steer it to create graphs and diagrams of exactly how you like the material presented. or the bibliography researched and cross-linked with the body or the order you want your questions addressed.

it also researched vision correcting displays for me and i can finally put that idea to bed - i was never really going to pick up an optometry textbook tbh. plus it was able to pull together a bunch of geometric and physical context about light and the eye plugging exactly my personal knowledge gaps.

in general i suspect these materials might not be that interesting to others because they are so custom to my learning style and personal needs and preferences.

these are usually not one shot documents but rather many prompts deep before i get something I’m willing to sit down and read or study. but dramatically quicker than assembling it myself from primary sources. i wouldn’t say it matches master expositors but then they’re not available to write on any topic i happen to need right now.

plus I’ll just have a live voice discussion with the system when i go for a walk and there are still things bothering me on a topic. it takes a little patience but if i’m in the mood it’s amazing.

i generally find that it can help track down specific references if i suspect hallucinations. but especially on factual topics my experience so far has been extremely encouraging.

Re: How I use LLMs to learn complex topics

#259

Post by tclancy »

eyepea2007 wrote: post #151
tclancy wrote: post #134

Earlier quoted context omitted.

It’s a reference to Bernard Shaw, who once said that if we ever created a truly artificial mind it would be inside a turtle’s shell. Sturgill Simpson covered the track on his seminal work, Xeno’s Paradox.

an LLM tells me there is no evidence that Bernard Shaw ever said any such thing :)

Well sure, it was George Bernard Shaw, not the old CNN anchor. Also, turtles are tight lipped by nature.

Re: How I use LLMs to learn complex topics

#260

Post by supriyo-biswas »

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…

> I get exhausted reading LLM prose.

While my advice is specific to learning about codebases, the way I do it is to have it generate mock data and put it in the local development environment, and give me some exploratory commands, and then ask away. It's a machine after all, so I don't have to read its preceding prose to understand whether it did tell me something, it can just repeat it however many times I ask it, and the hands on commands etc. give me something to actually try and implement.

Post reply on HN