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

551–560 of 563 posts

Re: How I use LLMs to learn complex topics

#551

Post by tito »

tito wrote: post #315

I ran this on ship tracks to see the global warming result. It built a toy climate model for cloud forcing: https://ship-tracks-tycoon.netlify.app For background, in 2020 the International Maritime Organization changed fuel standards globally. The intent was to reduce pollution, which is great for human health. But, it turns out some of that pollution was supporting cloud formation and creating a cooling layer global…

I wanted to understand how well this process works for a topic I already know.

I made for carbon dioxide removal, which I work on. First shot had most of the visualizations well made. And it was nice to see what I work on in a visual way that I hadn't seen before. I added labels to the warming graph and a removal build out graph too: https://removal-valley.netlify.app (while I saw familiar inputs as the sources, I didn't go through to make sure the numbers are all tied in properly, so that's where I would recommend someone proceed with this draft. But the things that are visualized, and how they're visualized, that's good to go)

I also had it animate the history of focused research organizations (a topic I was looking to learn about). That one is more a history of the space, and after that ends it's a simulation: https://fro-park.netlify.app

All three of these started with the prompts given in the OP and put into Claude. I haven't reviewed the actual numbers underpinning the models yet (nothing jumped out at me though as terribly wrong) so I included a "Draft" tag at the top of the page.

Code for both is on my GitHub: https://github.com/titojankowski/removal-valley https://github.com/titojankowski/fro-park

Re: How I use LLMs to learn complex topics

#553

Post by ethbr1 »

engineer_22 wrote: post #535
ethbr1 wrote: post #477

Earlier quoted context omitted.

ChatGPT also offered this: "For the correct analogy for the mind is not a vessel that needs filling, but wood that needs igniting - no more - and then it motivates one towards originality and instils the desire for truth. Suppose someone were to go and ask his neighbours for fire and find a substantial blaze there, and just stay there continually warming himself: that is no different from someone who goes to someone…

You didn’t read it but I should? Hey @turzmo I found your 21 year old and I agree with you!

woosh

Re: How I use LLMs to learn complex topics

#554

Post by moffkalast »

TeMPOraL wrote: post #426
moffkalast wrote: post #383

Earlier quoted context omitted.

> consistency with your lived experience Aka confirmation bias. We like explanations that fit what we expect, even if they're completely wrong.

I said consistent with your experience, not with your expectations. Lived experience is empirical data.

That would be the case if our memory wouldn't be completely fluid and built on subjective perceptions. The two sort of merge together over time, you come to see what you expect. It's only when something really out there breaches the belief model when that actually happens.

Re: How I use LLMs to learn complex topics

#555

Post by agumonkey »

esalman wrote: post #185
agumonkey wrote: post #123

Earlier quoted context omitted.

anybody adds some prologue about what style of answers are prefered ? i know i often try to change the linguistic patterns because i too (unsurprisingly) am tired of llm prose.

I've heard people promoting LLM to use ASD-STE100 Simplified Technical English with some improvement.

ha, nice, i'm gonna try that for a while

Re: How I use LLMs to learn complex topics

#556

Post by TeMPOraL »

fluoridation wrote: post #536
TeMPOraL wrote: post #419

Earlier quoted context omitted.

The very first thing I mention: self-consistency . It's the only thing you have if you don't have any empirical data. It's the only thing anyone has, really. QM scientists reading QM papers and experiment reports of other people, and talking with each other, are still relying on self-consistency to sniff their own (or other people's) mistakes.

>The very first thing I mention: self-consistency. So if I consistently tell you that that lithium atoms are heavier than carbon atoms, that would make it more likely to be true? >QM scientists reading QM papers and experiment reports of other people, and talking with each other, are still relying on self-consistency to sniff their own (or other people's) mistakes. Physicists don't need self-consistency. They can tes…

> So if I consistently tell you that that lithium atoms are heavier than carbon atoms, that would make it more likely to be true?

Nope. But if you said that, and used it as part of an explanation of some process, and every step logically checked out, and the outcome checked out too, and agreed with other things you said, and other things others said, then yes, I'd be likely to believe you.

Alas, a quick look at the periodic table raises a red flag - your explanation is inconsistent with the periodic table and what I know about its structure.

That doesn't necessarily say you are wrong - could be me. But judging by the tone of your comment vs. heaps of other things I know that are consistent with my understanding of chemistry and inconsistent with your statement...

> Physicists don't need self-consistency. They can test consistency against reality itself. That's not self-consistency, that's just plain old empiricism.

No they can't. No one has that much time or money. Physicists aren't routinely replicating every core result empirically for themselves. They rely on the descriptions of experiments and data that they read, and the self-consistency and extreme interconnectedness of reality, which means that wrong information will not add up with someone's experiment, expectations, or lived experience somewhere, and will be quickly flagged as wrong.

Empiricism is only useful because reality is self-consistent. If it weren't, you couldn't really infer anything from empirical evidence because things would just be whatever they wanted to be.

(Or more precisely: we can't prove reality is self-consistent, but if it isn't, nothing can ever make any sense, and we may just as well pack up our technological civilization and go back to the caves we crawled out of. Fortunately, empirical evidence supports the notion of reality being self-consistent to the extent we can observe it :).)

Re: How I use LLMs to learn complex topics

#557

Post by TeMPOraL »

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…

> 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.

Yes. Fortunately, we also usually don't need the error to be zero. In practice, we usually have narrow scope at any given time, and can get away with a lot of error.

E.g. people in the past found alternatives to modern germ theory, involving evil spirits and other such shenanigans, but to the extend they covered the high-level mechanisms (curse transfers through contact, hygiene and boiling water removes the harmful effects, etc.), it doesn't really matter the theories were wrong. The beliefs were consistent with each other and empirical evidence to some degree, and to that degree were useful.

> 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.

That's fair. Our brains and attentions are finite, you always have to limit the scope. If you imagine you'd have practically forever, you could sort it out and make it all consistent to arbitrary degree (subject to fundamental computational limits, which are physical limits). In practice, the heuristic of consistency works like this:

- For things within your domain of interest, inconsistent information flags an error.

- For things at the interface between your domain of interest and another domain(s), inconsistent information flags an abstraction boundary. It's where you can observe simplifications both domains make because they don't add up (and if you adjust them to make them mutually consistent, you just allowed two domains to work together).

Re: How I use LLMs to learn complex topics

#558

Post by fluoridation »

TeMPOraL wrote: post #556
fluoridation wrote: post #536

Earlier quoted context omitted.

>The very first thing I mention: self-consistency. So if I consistently tell you that that lithium atoms are heavier than carbon atoms, that would make it more likely to be true? >QM scientists reading QM papers and experiment reports of other people, and talking with each other, are still relying on self-consistency to sniff their own (or other people's) mistakes. Physicists don't need self-consistency. They can tes…

> So if I consistently tell you that that lithium atoms are heavier than carbon atoms, that would make it more likely to be true? Nope. But if you said that, and used it as part of an explanation of some process, and every step logically checked out, and the outcome checked out too, and agreed with other things you said, and other things others said, then yes, I'd be likely to believe you. Alas, a quick look at the p…

>But if you said that, and [...] I'd be likely to believe you.

That wasn't what I asked. I was very deliberate, I asked if it would be more likely to be true. What's under discussion is not your standard of evidence, but whether non-contradiction by itself is sufficient to conclude that a claim is true.

>Alas, a quick look at the periodic table raises a red flag

That's not self-consistency anymore, that's cross-corroboration. Which, yeah, good on you if you do that, but it's not the process being proposed either by the OP or by fy20.

>Physicists aren't routinely replicating every core result empirically for themselves.

OK, but that wasn't what I said. A physicist can't test every result, sure, but he can test those that are most relevant to his work. I'm not going to get into the philosophy of empiricism because it's not relevant here. My point was that an expert reading a peer's paper is not the least bit comparable to a layman reading an LLM's summary of a field of study. They're just not similar situations. One has the context and the capability to detect bullshit, while the other does not.

Re: How I use LLMs to learn complex topics

#559

Post by ethin »

bonoboTP wrote: post #474
ethin wrote: post #137

Earlier quoted context omitted.

This is (exactly) why I very strongly tell people not to teach themselves with an LLM. Particularly from the ground up. If you do not understand the domain, you cannot learn from the model because you won't know what questions to ask and it certainly isn't going to answer all of them for you.

The LLM doesn't have to be the sole single only exclusive source you learn from. It's an addition to a mix. Nothing is a single definitive answer. Same way as many other things, like Anki flashcards or Duolingo or some YouTube channel, or some tutorial website or indeed a coursebook or an audio course or whatnot. Use multiple sources and use the strengths of each.

What you describe is indeed the ideal method of learning. However, I think we both know that if LLMs are pushed as a learning device, people will substitute everything else for them (or companies will very strongly encourage that substitution).

Re: How I use LLMs to learn complex topics

#560

Post by kingkawn »

kurthr wrote: post #541
kingkawn wrote: post #195

Earlier quoted context omitted.

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…

Hallelujah!
Post reply on HN