Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I don't know how you get here from “predict the next word”

grumpy-economist.com

Post reply on HN
Print view View original

71–80 of 275 posts

Re: I don't know how you get here from “predict the next word”

#71

Post by pushedx »

measurablefunc wrote: post #55
brookst wrote: post #44

Earlier quoted context omitted.

Not the person you asked, and “novel” is a minefield. What’s the last novel anything , in the sense you can’t trace a precursor or reference? But.. I recently had a LLM suggest an approach to negative mold-making that was novel to me. Long story, but basically isolating the gross geometry and using NURBS booleans for that, plus mesh addition/subtraction for details. I’m sure there’s prior art out there, but that’s tr…

I don't know, that's why I asked b/c I always see a lot of empty platitudes when it comes to LLM praise so I'm curious to see if people can actually back up their claims. I haven't done any 3D modeling so I'll take your word for it but I can tell you that I am working on a very simple interpreter & bytecode compiler for a subset of Erlang & I have yet to see anything novel or even useful from any of the coding assist…

Which agents are you using, and are you using them in an agent mode (Codex, Claude Code etc.)?

The difference in quality of output between Claude Sonnet and Claude Opus is around an order of magnitude.

The results that you can get from agent mode vs using a chat bot are around two orders of magnitude.

Re: I don't know how you get here from “predict the next word”

#72

Post by libraryofbabel »

dylan604 wrote: post #30
libraryofbabel wrote: post #17

I have come to think “predict the next token” is not a useful way to explain how LLMs work to people unfamiliar with LLM training and internals. It’s technically correct, but at this point saying that and not talking about things like RLVR training and mechanistic interpretability is about as useful as framing talking with a person as “engaging with a human brain generating tokens” and ignoring psychology. At least A…

I think talking to people unfamiliar with LLM training using words like "RLVR training and mechanistic interpretability" is about as useful as a grave robber in a crematorium.

Obviously you don’t just say those words and leave it at that. Both those things can be explained in understandable terms. And even having a superficial sense of what they are gives people a better picture of what modern LLMs are all about than tired tropes from three years ago like “they’re just trained to predict the next token in the training data, therefore…”

Re: I don't know how you get here from “predict the next word”

#73

Post by kristiandupont »

wavemode wrote: post #41
selridge wrote: post #34

Earlier quoted context omitted.

>You're implicitly assuming that what you asked the LLM to do is unrepresented in the training data. This is just as stuck in a moment in time as "they only do next word prediction" What does this even mean anymore? Are we supposed to believe that a review of this paper that wasn't written when that model (It's putatively not an "LLM", but IDK enough about it to be pushy there) was trained? Does that even make sense?…

Statistical models generalize. If you train a model that f(x) = 5 and f(x+1) = 6, the number 7 doesn't have to exist in the training data for the model to give you a correct answer for f(x+2) Similarly, if there are millions of academic papers and thousands of peer reviews in the training data, a review of this exact paper doesn't need to be in there for the LLM to write something convincing. (I say "convincing" rath…

I had Claude help me get a program written for Linux to compile on macOS. The program is written in a programming language the author invented for the project, a pretty unusual one (for example, it allows spaces in variable names).

Claude figured out how the language worked and debugged segfaults until the compiler compiled, and then until the program did. That might not be magic, but it shows a level of sophistication where referring to “statistics” is about as meaningful as describing a person as the statistics of electrical impulses between neurons.

Re: I don't know how you get here from “predict the next word”

#74

Post by wavemode »

c22 wrote: post #64
wavemode wrote: post #41

Earlier quoted context omitted.

Statistical models generalize. If you train a model that f(x) = 5 and f(x+1) = 6, the number 7 doesn't have to exist in the training data for the model to give you a correct answer for f(x+2) Similarly, if there are millions of academic papers and thousands of peer reviews in the training data, a review of this exact paper doesn't need to be in there for the LLM to write something convincing. (I say "convincing" rath…

> If you train a model that f(x) = 5 and f(x+1) = 6, the number 7 doesn't have to exist in the training data for the model to give you a correct answer for f(x+2) This is an interesting claim to me. Are there any models that exist that have been trained with a (single digit) number omitted from the training data? If such a model does exist, how does it represent the answer? (What symbol does it use for the '7'?)

When I say "model" here I'm referring to any statistical model (in this example, probably linear regression). Not specifically large language models / neural networks.

Re: I don't know how you get here from “predict the next word”

#75

Post by nekusar »

retrac wrote: post #42

I know this sounds insane but I've been dwelling on it. Language models are digital Ouija boards. I like the metaphor because it offers multiple conflicting interpretations. How does a Ouija board work? The words appear. Where do they come from? It can be explained in physical terms. Or in metaphysical terms. Collective summing of psychomotor activity. Conduits to a non-corporeal facet of existence. Many caution agai…

There's 2 completely different ways to understand how a Ouija board works. Occult, and Scientific.

Scientific: It's a combined response from everyone's collective unconscious blend of everyone participating. In other words, its a probabilistic result of an "answer" to the question everyone hears.

Occult: If an entity is present, it's basically the unshielded response of that entity by collectively moving everyone's body the same way, as a form of a mild channel. Since Ouija doesn't specific to make a circle and request presence of a specific entity, there's a good chance of some being hostile. Or, you all get nothing at all, and basically garbage as part of the divination/communication.

But comparing Ouija to LLMs? The LLM, with the same weights, with the same hyperparameters, and same questions will give the same answers. That is deterministic, at least in that narrow sense. An Ouija board is not deterministic, and cannot be tested in any meaningful scientific sense.

Re: I don't know how you get here from “predict the next word”

#76

Post by c22 »

wavemode wrote: post #74
c22 wrote: post #64

Earlier quoted context omitted.

> If you train a model that f(x) = 5 and f(x+1) = 6, the number 7 doesn't have to exist in the training data for the model to give you a correct answer for f(x+2) This is an interesting claim to me. Are there any models that exist that have been trained with a (single digit) number omitted from the training data? If such a model does exist, how does it represent the answer? (What symbol does it use for the '7'?)

When I say "model" here I'm referring to any statistical model (in this example, probably linear regression). Not specifically large language models / neural networks.

Gotcha, I don't think I know enough about it. What constitutes training data for a for a (non neural network) statistical model? Is this something I could play around with myself with pen and paper?

Re: I don't know how you get here from “predict the next word”

#77

Post by fc417fc802 »

jen729w wrote: post #40
spiralcoaster wrote: post #26

Earlier quoted context omitted.

Two very big revelations here that I would love to know more about: 1. Can you reveal "what's actually happening behind the scenes" beyond the hint you gave? I can't figure it out. 2. Can you explain how an ants sense of smell leads to anthills?

> 2. Can you explain how an ants sense of smell leads to anthills? Ant 0: doesn’t seem to be dangerous here. I’ll drop a scent. Ant 1: oh cool, a safe place. And I didn’t die either. I’ll reinforce that. Ant 142,857,098,277: cool anthill.

The dynamics of ant nest creation are way more complicated than that. The evolved biological parallel of a procedural generation algorithm. In addition, the completed structure has to be compatible with the various programmed behaviors of the workers.

Re: I don't know how you get here from “predict the next word”

#78

Post by bryanrasmussen »

floren wrote: post #61
bryanrasmussen wrote: post #38

Earlier quoted context omitted.

and this is somehow not related to the size and availability of corpora in English?

No, I'm quite sure that's why it's better.

OK but then that goes back to their other assertion that it gives a huge hint at what is going on behind the scenes, is that huge hint just "more data gives better results!" if so, that doesn't seem at all important since that is the absolutely central idea of an LLM. That is not behind the scenes at all, that is the introduction to the play as written by the author.

Not your fault obviously, but they have not yet described what that huge hint is, and I'm just at the edge of my seat with anticipation here.

Re: I don't know how you get here from “predict the next word”

#79

Post by compass_copium »

kristiandupont wrote: post #73
wavemode wrote: post #41

Earlier quoted context omitted.

Statistical models generalize. If you train a model that f(x) = 5 and f(x+1) = 6, the number 7 doesn't have to exist in the training data for the model to give you a correct answer for f(x+2) Similarly, if there are millions of academic papers and thousands of peer reviews in the training data, a review of this exact paper doesn't need to be in there for the LLM to write something convincing. (I say "convincing" rath…

I had Claude help me get a program written for Linux to compile on macOS. The program is written in a programming language the author invented for the project, a pretty unusual one (for example, it allows spaces in variable names). Claude figured out how the language worked and debugged segfaults until the compiler compiled, and then until the program did. That might not be magic , but it shows a level of sophisticat…

But the programming language has explicitly laid out rules. It was not trained on those sets of rules, but it was trained on many trillions of lines of code. It has a map of how programs work, and an explanation of this new language. It's using training data and data it's fed to generate that result.

Re: I don't know how you get here from “predict the next word”

#80

Post by gammalost »

It is really interesting how great and also how terrible LLMs can be at the same time. For example, I had a really annoying bug yesterday, I missed one character, "_". Asking ChatGPT for help led to a lot of feedback that was arguably okay but not currently relevant (because there was a fatal flaw in the code).

Remade the conversation with personal information stripped here https://chatgpt.com/share/699fef77-b530-8007-a4ed-c3dda9461d...

Post reply on HN