> here’s how LLMs actually work
But how is that useful in any way?
For all we know, LLMs are black boxes. We really have no idea how did ability to have a conversation emerge from predicting the next token.
But how is that useful in any way?
For all we know, LLMs are black boxes. We really have no idea how did ability to have a conversation emerge from predicting the next token.
Maybe you don't. To be clear, this is benefiting massively from hindsight, just as how if I didn't know that combustion engines worked, I probably wouldn't have dreamed up how to make one, but the emergent conversational capabilities from LLMs are pretty obvious. In a massive dataset of human writing, the answer to a question is by far the most common thing to follow a question. A normal conversational reply is the most common thing to follow a conversation opener. While impressive, these things aren't magic.
Obviously, that's the objective, but who's to say you'll reach a goal just because you set it ? And more importantly, who's the say you have any idea how the goal has actually been achieved ?
You don't need to think LLMs are magic to understand we have very little idea of what is going on inside the box.
Your comment about 'binary arithmetic' and 'billions of logic gates' is just nonsense.
You can define understanding to require such detail that nobody can claim it; you can define understanding to be so trivial that everyone can claim it.
"Why does the sun rise?" Is it enough to understand that the Earth revolves around the sun, or do you need to understand quantum gravity?
Somewhere along the way from one transistor to a few billion human understanding stops but we still know how it was all assembled together to perform boolean arithmetic operations.
With LLMs, The "knowing" you're describing is trivial and doesn't really constitute knowing at all. It's just the physics of the substrate. When people say LLMs are a black box, they aren't talking about the hardware or the fact that it's "math all the way down." They are talking about interpretability.
If I hand you a 175-billion parameter tensor, your 'knowledge' of logic gates doesn't help you explain why a specific circuit within that model represents "the concept of justice" or how it decided to pivot a sentence in a specific direction.
On the other hand, the very professions you cited rely on interpretability. A civil engineer doesn't look at a bridge and dismiss it as "a collection of atoms" unable to go further. They can point to a specific truss and explain exactly how it manages tension and compression, tell you why it could collapse in certain conditions. A software engineer can step through a debugger and tell you why a specific if statement triggered.
We don't even have that much for LLMs so why would you say we have an idea of what's going on ?
Again, we lack even this much with LLMs so why say we know how they work ?
So why ? Because even in 2026, nevermind 18 and 19, the only way to really know exactly how a neural network will perform trained with x data at y scale is to train it and see. No elaborate "laws", no neat equations. Modern Artificial Intelligence is an extremely empirical, trial and error field, with researchers often giving post-hoc rationalizations for architectural decisions. So no, we do not have any precise models that tell us how a LLM will respond to any query. If we did, we wouldn't need to spend months and millions of dollars training them.
And even for potential LLMs, there are some pretty good extrapolations for overall answer quality based on the amount of data and the amount of training.
We don't have a model for a LLM that does exist will respond to a specific query either.
>For an LLM that exists it's still hard to interpret but it's very clear what is actually happening.
No, it's not and I'm getting tired of explaining this. If you think it is, write your paper and get very rich.
>That's better than you often get with quantum physics when there's a bunch of particles and you can't even get a good answer for the math.
You clearly don't understand any of this.
>And even for potential LLMs, there are some pretty good extrapolations for overall answer quality based on the amount of data and the amount of training.
Oh really ? Lol
Yes we do... It's math, you can calculate it.
> No, it's not and I'm getting tired of explaining this. If you think it is, write your paper and get very rich.
Why would I get rich for explaining how to do math?
> You clearly don't understand any of this.
Could you be more specific?
Quantum physics is stupidly hard to calculate when you approach realistic situations.
A real LLM takes a GPU a fraction of a second.
They're both hard to interpret, please realize I'm agreeing that LLMs are hard to interpret. But they're easier than QM on some other fronts.
And mentioning copenhagen or many-worlds doesn't show that quantum mechanics are easy to interpret, that's about as useful as saying an LLM works like neuron activation.
> Oh really ? Lol
Here's one of many posts about it. https://cameronrwolfe.substack.com/p/llm-scaling-laws
This reminds me of Searle's insipid Chinese Room; the rebuttal (which he never had an answer for) is that "the room understands Chinese". It's just not satisfying to someone steeped in cultural traditions that see people as "souls". But the room understands Chinese; the LLM understands language. It is what it is.
[1] Since it's deterministic, it certainly can be debugged through, but you probably don't have the patience to step through trillions of operations. That's not the technology's fault.
Train a tiny transformer on addition pairs (i.e i.e '38393 + 79628 = 118021') and it will learn an algorithm for addition to minimize next token error. This is not immediately obvious. You won't be able to just look at the matrix multiplications and see what addition implementation it subscribes to but we know this from tedious interpretability research on the features of the model. See, this addition transformer is an example of a model we do understand.
So those inscrutable matrix multiplications do have underlying meaning and multiple interpretability papers have alluded as much, even if we don't understand it 99% of the time.
I'm very fine with simply saying 'LLMs understand Language' and calling it a day. I don't care for Searle's Chinese Room either. What I'm not going to tell you is that we understand how LLMs understand language.
Incidentally, your description of LLMs also describes all software, ever. It's just math, man! That doesn't make you an expert kernel hacker.
You may never get a scientific answer to "how should I prompt the model to achieve <x>", just like you may never get a capital-S scientific answer to "how should I convince people to do X". What would it even mean to "understand people" like this?
You demand too much.
No it isn't. Type a question into a base model, one that hasn't been finetuned into being a chatbot, and the predicted continuation will be all sorts of crap, but very often another question, or a framing that positions the original question as rhetorical in order to make a point. Untuned raw language models have an incredible flair for suddenly and unexpectedly shifting context - it might output an answer to your question, then suddenly decide that the entire thing is part of some internet flamewar and generate a completely contradictory answer, complete with insults to the first poster. It's less like talking with an AI and more like opening random pages in Borge's infinite library.
To get a base language model to behave reliably like a chatbot, you have to explicitly feed it "a transcript of a dialogue between a human and an AI chatbot", and allow the language model to imagine what a helpful chatbot would say (and take control during the human parts). The fact that this works - that a mere statistical predictive language model bootstraps into a whole persona merely because you declared that it should, in natural English - well, I still see that as a pretty "magic" trick.
To be fair, only if you pose this question singularly with no proceeding context. If you want the raw LLM to answer your question(s) reliably then you can have the context prepended with other question-answer pairs and it works fine. A raw LLM is already capable of being a chatbot or anything else with the right preceding context.
They're not simple though. You can understand, in a reductionist sense, the basic principles of how transformers perform function approximation; but that does not grant an intuitive sense of the nature of the specific function they have been trained to approximate, or how they have achieved this approximation. We have little insight into what abstract concepts each of the many billions of parameters map on to. Progress on introspecting these networks has been a lot slower than trial-and-error improvements. So there is a very real sense in which we have no idea how LLMs work, and they are literally "magic black boxes".
No matter how you slice it - if "magic" is a word which can ever be applied to software, LLM chatbots are sure as shit magic.
My best friend who has literally written a doctorate on artificial intelligence doesn't. If you do, please write a paper on it, and email it to me. My friend would be thrilled to read it.
The whole point of the area of work that as far as I know is called interpretability, is precisely to try and figure exactly how these things work
So I thought your comment was a good way of putting this
However reading some Standford study summaries (not the whole thing) and just generally where AI research is now, it's clear that researchers can't deterministically say exactly how the black box works.
So yet gain, HN armchair scientists are no better than any other topic. I love reading comments here, but so many people have opinions on things that aren't well founded.
I'm not saying this is bad or underwhelming, by the way. It's incredible how far people were able to push machine learning with just the knowledge we have now, and how they're still making process. I'm just saying it's not magic. It's not something like an unsolved problem in mathematics.
In general, every attempt at explanation of LLM's that appeal to "[just] predicting next token" is thought terminating and automatically invalid as explanation. Why? Because it is confusing the objective function with the result. It adds exactly zero over saying "I know how a chess engine works, it just predicts the next move and has been trained to predict the next move" or "A talking human just predicts the next word, as it was trained to do". It says zero about how this is done internally in the model. You could have a physical black box predicting the next token, and inside you could have simple frequentist tables or you could have a human brain or you could have an LLM. In all cases you could say the box is predicting the next token and if any training was involved you could say it was trained to predict the next token.
Uh yes, we do. It works in precisely the same way that you can walk from "here" to "there" by taking a step towards "there", and then repeating. The cognitive dissonance comes when we conflate this way of "having a conversation" (two people converse) and assume that the fact that they produce similar outputs means that they must be "doing the same thing" and it's hard to see how LLMs could be doing this.
Sometimes things seems unbelievable simply because they aren't true.
It's funny how, in order to explain one complex phenomenon, you took an even more complex phenomenon as if it somehow simplifies it.
I wasn't referring to the biomechanical process of walking, I was referring to the process of gradient descent, which is well understood and yes, quite simple.
Thing is, that would be a rebuttal if I'd said something about the underlying tensor fiddling code being understood, and you were claiming that next token prediction was a mysterious emergent phenomena.
Unfortunately that's not the argument I made. My claim is that there's nothing surprising or mysterious about the fact that a system designed to repeatedly generate a highly likely continuation of a sequence of tokens (considered as a member of pre-specified class of sequences) winds up producing something that looks like it could be a member of that class. That's kind of the whole point. These things were designed to predict plausible next tokens, and that's exactly what they do.