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

141–150 of 574 posts

Re: How I use LLMs to learn complex topics

#141

Post by PaulStatezny »

rl3 wrote: post #73
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 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 you even saying anything whether you get what they're going through. This unspoken-yet-communicated information guides the conversation. Or as another example: humans can read the room -- you walk into a room and immediately adjust your demeanor based on what you see and sense.

LLMs are totally blind to things like this, and this adds an inescapable awkwardness to interacting with them. I don't believe they'll ever grow out of this. Which thankfully implies more long term demand for humans instead of robots. :)

Re: How I use LLMs to learn complex topics

#142

Post by tunesmith »

Calazon wrote: post #135
tunesmith wrote: post #60

Earlier quoted context omitted.

Generally speaking, the pattern is that people are overestimating how much "work replacement" will happen, and underestimating how much "work shifting" will happen. What is fascinating is how you can witness it at so many levels of organization. One example: Employer executive get enamored with moving from labor to capital. They believe that by using LLMs, they can replace a lot of workers. At my place of employment,…

I agree with you in the broad strokes, but replacement by LLMs isn't the only way the level of employment can be reduced. If LLMs can make it so that two programmers can do the work that used to require five, that can result in a very large reduction in employment, even while having (some) programmers is still essential.

On the bet that layoffs will result in programmers ending up at 40% of the staffing level they are now, I will take the over.

Re: How I use LLMs to learn complex topics

#143

Post by seabass »

> In plan mode (using CC, or OpenCode) I ask a model to build the foundational knowledge for X topic. I ask it to review the accuracy of the knowledge base it built in the previous step.

> What you get is a beautiful animation that is 100% accurate and free of hallucinations.

How do you make that leap?

Re: How I use LLMs to learn complex topics

#144

Post by arbitrary_name »

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.

dumb question, but what is the best way to feed the book to the llm?

i run into context window limits, or practical limitations of digitizing the book

Re: How I use LLMs to learn complex topics

#145

Post by dozerly »

furyofantares wrote: post #115
enraged_camel wrote: post #100

Earlier quoted context omitted.

What do you mean by this?

"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…

There are certainly uses where it’s good enough, but you can never be 100% certain of correctness in the way that people claim you can by stacking N layers of these models.

What triggered my response was the “just review the output with another LLM and it’s perfectly correct”

Re: How I use LLMs to learn complex topics

#147

Post by nightwalkerkg »

j45 wrote: post #129
nightwalkerkg wrote: post #118

My main issue with using AI as a learning platform is that unlike documentation, books, Youtube videos, there is not really a process of having someone "review the learning material". For example, I can always read the review of some book or ciriculum, the comments under a video, or if it's some for of open source documentation you can check the PRs and verify to some extent it's claim. With AI I can't really say wha…

You can ask the LLM to connect the dots to the sources before displaying it to you so you can see the proof in line. You can ask the LLM how to do this. Start with a topic you know well to get the mechanism working and trust it well.

Of course, and that is what I do, but it becomes and additional mental and time consuming effort. As an dumb example, if I am learning a new programming language and trying to grasp some concept, I'll check the docs, find the section and read it. I trust that the source in the docs has been already vetted by other devs and the authors. But if I ask the AI the same thing, I then need to verify it's claims usually by asking it to check if the info is true, and then possibly opening the source link (lucky for me Claude provides the links in the desktop app as footnotes). It's not a question about AI, it's about the trust I have of this tool, it builds over time, but as soon as the AI makes an assumption or a hallucination we are back down to square one.

I assume this will become less of an issue in the future as there is more trust between the AI tools and me.

Re: How I use LLMs to learn complex topics

#148

Post by gofreddygo »

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 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 better than having the LLM summarize the books or the topic (or even relying on second hand information). Another one is having the LLM quiz you on your topics of interest. With questions tailored to attack specific areas that you struggle with. Its wonderful at this, nothing I've used comes close to what an LLM can do here.

You define for yourself what your goals are, slowly refining them as you learn more, and use LLM as a tool. This ,I find works best for learning.

Re: How I use LLMs to learn complex topics

#149

Post by afro88 »

I'm all for this and I'm keen to try it. I certainly don't want to take away from sharing another neat use case for learning.

But

> What you get is a beautiful animation that is 100% accurate and free of hallucinations

100% free of hallucinations when you're not an expert that can check it is impossible. LLM hallucinations are an unsolved problem.

Re: How I use LLMs to learn complex topics

#150

Post by KronisLV »

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.

I’ve found the tone of Kimi K3 to be less obnoxious. Unfortunately it doesn’t wholly solve the issue, I don’t think any LLMs out there have a truly pleasant writing style, but at least not every assumption is “load bearing”.

Post reply on HN