How LLMs work • Hacker News Board

Re: How LLMs work

#101

Post by Ampersander » Sat, Jun 06, 2026, 9:09 AM UTC

lionkor wrote: post #65

It sucks that this article is clearly LLM edited, with common phrases like "same shape as", "the intuition: ", and the "tiny explainer" which clearly generalized from a prompt accidentally. Good article, but when sharing it I will have to preface "yes it's slop, but it's a good explanation". Absolutely embarrassing that the author didn't catch that these LLM-isms are a (and here I'll use one) bad signal. In fact, I w…

You're not supposed to read it, just like you're not supposed to write anything anymore. Claude can read and write more than any human. We just lean back and relax now.

Re: How LLMs work

#102

Post by Ampersander » Sat, Jun 06, 2026, 9:17 AM UTC

vocram wrote: post #68

Saying an article is of inferior quality just because editing was AI-assisted is like saying a book is lower quality just because it was printed rather than written by hand

You are exactly right! People do not find the writing obnoxious, they are backwards technophobes getting brought down by their superstitions.

Re: How LLMs work

#103

Post by adammarples » Sat, Jun 06, 2026, 9:19 AM UTC

otabdeveloper4 wrote: post #40

10GBps wrote: post #15

Earlier quoted context omitted.

Yep. It's nearly identical to the neural nets we were using in the 90s. Back then even a supercomputer wasn't big enough or fast enough to do what we do today. I have to wonder though. Is this all a human brain is? A similar thing to an LLM just scaled exponentially larger. I mean a brain is not just neurons with simple connections to each other. The neurons, axons, dendrites, , etc in a brain are all holding and pro…

> I mean a brain is not just neurons with simple connections to each other. No, it's not. There are many animals that have extremely complex and even learned behaviour that have literally zero neurons. Clearly "neurons" is an oversimplification just-so story, not a scientific theory.

Apparently even single-celled protozoa can show learned trial and error behaviour.

Re: How LLMs work

#104

Post by Ampersander » Sat, Jun 06, 2026, 9:19 AM UTC

AltruisticGapHN wrote: post #88

I don't like how most LLM explainer articles and videos say that essentially a LLM " predicts the next word". I'm a developer but not very good at maths and I still don't understand any of it. A LLM clearly has some "visual" capacity. You ask Gemini to build something with Canvas and it's able to reason about the shape of things. Like recently I waanted a checkbox that has like a gradient flowing around the edge. It…

I do agree bigly. Calling what is basically a superhuman brain inside a computer just a "token predictor" is peak thinkslop.

Re: How LLMs work

#105

Post by inkysigma » Sat, Jun 06, 2026, 9:20 AM UTC

yukIttEft wrote: post #98

> so the model figures out during training what each token should look for and what it should offer But how does it learn this token-relationship? All it has is many text samples, but still, nowhere it says how the tokens relate to each other, so where does this information come from?

At a high level, the text samples are how the relationships are derived. If we treat text samples as sequences of tokens, then the sequences of tokens describe the joint distributions they occur together which confers the relationship between them. Iirc, this is related to the idea of the distributional hypothesis in NLP: the idea the semantics of words should be similar if they occur in similar situations.

Re: How LLMs work

#106

Post by inkysigma » Sat, Jun 06, 2026, 9:22 AM UTC

singpolyma3 wrote: post #2

Next do "why LLMs work"

This is essentially an open research question. ML theory is unfortunately very weak relative to where the empirics are. I think there's a relatively optimistic paper that was posted a while back here but I would also take it with a grain of salt.

https://arxiv.org/abs/2604.21691

There's of course empirical results and relatively weak theoretical results like the UAT but I also don't think that answers your question fully, especially since it seems impossible to definitively answer questions that the industry seems to betting on like whether or not there is a lower bound to their error rate or whether hallucination as a problem can be solved. We have much stronger ideas of what linear regression is doing relative to what LLMs are doing.

Re: How LLMs work

#107

Post by golergka » Sat, Jun 06, 2026, 9:33 AM UTC

malwrar wrote: post #10

Back when ChatGPT came out, I was so shocked by how _good_ it was for an “AI” product that I simply had to know how it worked. Over the next month I ended up drawing out a block diagram on a whiteboard I have in my office, with the math involved next to each step in the blackboard. I’d puzzle about each step along the way, and the triumph of completing the drawing was also that of this sense of deep understanding. I…

After building some toy LLMs on my own I came to realise that architecture is not the hard part. Train is.

Re: How LLMs work

#108

Post by helloplanets » Sat, Jun 06, 2026, 9:49 AM UTC

10GBps wrote: post #6

I learned TCP/IP by watching and reading raw packets over packet radio at 1200 baud. I've noticed the same thing is possible if you watch the output of a slow LLM. Eventually you start to see the machinery. input tokens = output tokens, it's math. I can't exactly predict the tokens generated but I can see how they are formed. It's a lot like chess. You can't see every possible move but the mechanism is understandable…

It's basically possible build an LLM using just routers+packets, and then hook them up to Wireshark to see it compute!

Re: How LLMs work

#109

Post by 360MustangScope » Sat, Jun 06, 2026, 10:01 AM UTC

antran22 wrote: post #91

AltruisticGapHN wrote: post #88

I don't like how most LLM explainer articles and videos say that essentially a LLM " predicts the next word". I'm a developer but not very good at maths and I still don't understand any of it. A LLM clearly has some "visual" capacity. You ask Gemini to build something with Canvas and it's able to reason about the shape of things. Like recently I waanted a checkbox that has like a gradient flowing around the edge. It…

It's still predicting the next word. Somewhere in the gigantic dataset that the LLM was trained on, there is a phrase that says "gradient border" being in the vicinity of a CSS code that render the stuff. Therefore when you run it on an inference loop there's a good chance it output that CSS code when you tell it to render a "gradient border" Multi-modal models that can understand visual input do exists, but no such…

What about things it wasn’t trained on?

For instance I’ve written a few custom languages to learn how to write a VM and the lexer/parser/compiler/etc. that it had never seen before and then just gave it the syntax which is different than what it had ever seen before. Simply due to the fact I made it and it had never been trained on it.

After giving it my documentation, it was able to write the language just like a language that it had been trained on. I’ve also seen this behavior at work where there are weird quirks to do things and definitely not standard and it can handle it.

Re: How LLMs work

#110

Post by 2muchcoffeeman » Sat, Jun 06, 2026, 10:01 AM UTC

crossroadsguy wrote: post #86

malwrar wrote: post #10

Back when ChatGPT came out, I was so shocked by how _good_ it was for an “AI” product that I simply had to know how it worked. Over the next month I ended up drawing out a block diagram on a whiteboard I have in my office, with the math involved next to each step in the blackboard. I’d puzzle about each step along the way, and the triumph of completing the drawing was also that of this sense of deep understanding. I…

What hopes/paths does a mere CS bachelor (not deep into stats/maths), and mid level dev (native mobile only; 10-15 years exp.), have about not only understanding it (maybe not fully) but getting possibly into this as a career? Not expecting churning out models and AI systems from the first weeks/months but entry/employment into this field? (If I can be honest, and I am not being disparaging about anything lest it mig…

I think you need to ask what you actually want to do with the AI.

If you want to be a researcher and come out with the next breakthrough, get ready to go back to school and learn some math.

If you just need to learn how to use it well and build things with it, then you probably just need to have a high level understanding.

Same as programming. I’d bet most programmers have no idea about the physics that makes computers work.