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

“Next-token predictor” is the wrong mental model for LLMs

gmcgoldr.github.io

Post reply on HN
Print view View original

91–100 of 331 posts

Re: “Next-token predictor” is the wrong mental model for LLMs

#91

Post by grebc »

danielmarkbruce wrote: post #47
jameshart wrote: post #40

Earlier quoted context omitted.

I think it’s a disagreement about what ‘predict’ means. The OP is arguing against people who think that an LLM is ‘predicting’ what token would likely follow if the text preceding were found among the corpus it was originally trained on . Instead it is ‘predicting’ what token would follow if the text were found among really good examples of the text it has being reinforced to produce - be that ‘chats with a helpful a…

yes, it's exactly this. And it's not a trivial distinction.

It’s deterministically trivial.

Re: “Next-token predictor” is the wrong mental model for LLMs

#92

Post by 27183 »

mort96 wrote: post #60
junofan wrote: post #45

Earlier quoted context omitted.

Vacuous, like calling a V8 a “next piston firing predictor” because engines are designed so that one piston sets up the next in the firing order and technically there’s some nonzero probability any piston can (mis)fire next. It’s missing two pieces: 1. Useful work that has been done (the previously generated token sequence :: the mechanical work already accomplished) 2. The role of structure in relation to the applic…

A V8 does not "predict" the firing of the next piston, it triggers the firing of the next piston at a precisely controlled time with a spark plug (or a fuel injection nozzle in the case of a diesel engine). The output of the LLM is literally a probability distribution of what the most likely next token is.

> A V8 does not "predict" the firing of the next piston

It kind of does, though. In a gasoline engine you need to spark the combustion in advance of the piston reaching top dead-center to ignite the fuel early enough that it is able to provide downward pressure on the piston as it rolls over top dead-center. The amount of advance required changes with RPM, fuel octane, etc.

Start of delivery timing in a diesel is similar. You have to do it sufficiently far in advance to account for compressibility of the injection lines, fuel burn rate, etc as a function of RPM. A mechanical governor on an injection pump has a timing advance device built in. Electronically governed injection pumps, or modern common rail systems, do that in software.

So mechanically, engines kind of "predict" the next combustion event. Even moreso when you consider a modern ECU, which may be working at nanosecond resolution to time multiple injection events per cycle. To do this at such a resolution it will have to send signals to components based on a predictive model derived from "past" sensor data. E.g. it needs to act ahead of time to account for electrical and mechanical delays in the system.

Re: “Next-token predictor” is the wrong mental model for LLMs

#93

Post by danielmarkbruce »

grebc wrote: post #91
danielmarkbruce wrote: post #47

Earlier quoted context omitted.

yes, it's exactly this. And it's not a trivial distinction.

It’s deterministically trivial.

Post train a model, you'll be able to determine it is not.

Re: “Next-token predictor” is the wrong mental model for LLMs

#94

Post by grebc »

jmull wrote: post #35

It's a weird article. Despite the title and some of the text, much of the article makes the point that LLMs are next-token predictors, where the predictions are based on both training data and various reinforcement learning techniques.

Obfuscation is the goal of the hype cycle in VC. Certain firms & individuals are minting money and that’s all that matters to them.

That there’s a legion of LLM nerds arguing deterministic this, pretraining & rewards that all the better for the con job they’re pulling off.

The technology will be relegated to the trash bin of history, just like crypto.

Re: “Next-token predictor” is the wrong mental model for LLMs

#95

Post by whateveracct »

jvanderbot wrote: post #2

A better statement might be: Current agentic systems may be *built* from next-token predictors which are conceptually simple, but because of agentic frameworks, recursive invocation, tool use, and *heavy* investment in reinforcement learning in these contexts and for specific applications, they can no longer be thought of as "Merely" next token predictors. Modern agentic work is probably more of a "emergent system fr…

the next token part is like the "clock" that drives it

Re: “Next-token predictor” is the wrong mental model for LLMs

#96

Post by grebc »

danielmarkbruce wrote: post #93
grebc wrote: post #91

Earlier quoted context omitted.

It’s deterministically trivial.

Post train a model, you'll be able to determine it is not.

The blog post itself says one thing, but then demonstrates the exact thing they’re arguing against.

If you can’t grasp that logic gap then there’s no point discussing further.

Re: “Next-token predictor” is the wrong mental model for LLMs

#97

Post by jameshart »

saghm wrote: post #48
jameshart wrote: post #40

Earlier quoted context omitted.

I think it’s a disagreement about what ‘predict’ means. The OP is arguing against people who think that an LLM is ‘predicting’ what token would likely follow if the text preceding were found among the corpus it was originally trained on . Instead it is ‘predicting’ what token would follow if the text were found among really good examples of the text it has being reinforced to produce - be that ‘chats with a helpful a…

That seems overly pedantic to me. If I asked you "What's your prediction for the Super Bowl?", I'm pretty confident you would infer that I mean predicting the outcome , not the event itself.

But if you are an NFL coach and I ask you to decide your next action in order to maximize your odds of winning the superbowl, while yes that does involve you having some predictive ability to think about what impact your actions would have on your odds of winning the Super Bowl… I don’t think you would call the process that you use to decide that next action ‘prediction’.

Re: “Next-token predictor” is the wrong mental model for LLMs

#99

Post by tracerbulletx »

Systemerror7A69 wrote: post #21

To be honest, I believe I get the point the article is trying to make, and to an extent I agree, but I also think the point is not really made very well. The core of the argument as I understood it is that LLMs aren't just using existing data is training but also new ones. That's fine and good, and you can't simply assume an LLM is simply mashing together all it's data to give you an average of all that got fed into…

I just think its a meaningless dismissive term. It literally does predict the next token. But it ignores that it coherently predicts long continuous sequences of those tokens, that tokens can be anything, and you can do almost literally anything with that capability if it does it well enough.

Re: “Next-token predictor” is the wrong mental model for LLMs

#100

Post by Planktonne »

I'm not going to stop describing things accurately because someone generated an article that continually undermines its own main point. Limiting the way we talk and think about LLMs to a very narrow set of terms doesn't help us.

EDIT: gentler phrasing

Post reply on HN