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

131–140 of 275 posts

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

#131

Post by dnautics »

qsera wrote: post #98
basch wrote: post #95

Earlier quoted context omitted.

It's honestly disheartening and a bit shocking how everyone has started repeating the predict the next syllable criticism. The language model predicts the next syllable by FIRST arriving in a point in space that represents UNDERSTANDING of the input language. This was true all the way back in 2017 at the time of Attention Is All You Need. Google had a beautiful explainer page of how transformers worked, which I am st…

>represents UNDERSTANDING of the input language. It does not have an understanding, it pattern matches the "idea shape" of words in the "idea space" of training data and calculates the "idea shape" that is likely to follow considering all the "idea shape" patterns in its training data. It mimics understanding. It feels mysterious to us because we cannot imagine the mapping of a corpus of text to this "idea space". It…

> pattern matches the "idea shape" of words in the "idea space

it does much more than this. first layer has an attention mechanism on all previous tokens and spits out an activation representing some sum of all relations between the tokens. then the next layer spits out an activation representing relations of relations, and the next layer and so forth. the llm is capable of deducing a hierarchy of structural information embedded in the text.

not clear to me how this isn't "understanding".

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

#132

Post by qsera »

echelon wrote: post #110
qsera wrote: post #63

Earlier quoted context omitted.

>Now the machines are getting better than we are Then AI companies should stop looking for investors and instead play stock markets with all that predictive powers!

The real money is in using the models to build utility and money-making companies. You're removed from orders of magnitude in upside potential if you have to wait for the public markets.

> money-making companies

You mean, money sucking companies, right?

>You're removed from orders of magnitude in upside potential if you have to wait for the public markets.

because that won't work. That is why!

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

#133

Post by nairboon »

basch wrote: post #113
steve1977 wrote: post #108

Earlier quoted context omitted.

From what I understand, it's more like "input is 1, 3, 5, 7" so "output is likely to be 9". Understanding would be a bit generous of a term for that I guess, but that also depends on the definition of understanding.

Id really invite people to read the google blog post. https://research.google/blog/transformer-a-novel-neural-netw... Google chose the word understanding.

Google chose "understanding" in that context, because the relevant AI/ML task is called "Natural language understanding". But that term is an aspiration. It's the problem of trying to reveal the "meaning" of text data (language) as in making sense of the symbols with computers.

Just because Transformers work well on the "Natural language understanding" task in AI, doesn't mean that a Transformer actually "understands" language in the human sense.

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

#134

Post by throw310822 »

ChaitanyaSai wrote: post #43

The whole next word thing is interesting isn't it. I like to see it with Dennett's "Competence and comprehension" lens. You can predict the next word competently with shallow understanding. But you could also do it well with understanding or comprehension of the full picture. A mental model that allows you to predict better. Are the AIs stumbling into these mental models? Seems like it. However, because these are suc…

> You can predict the next word competently with shallow understanding.

I don't get this. When you say "predict the next word" what you mean is "predict the word that someone who understands would write next". This cannot be done without an understanding that is as complete as that of the human whose behaviour you are trying to predict. Otherwise you'd have the paradox that understanding doesn't influence behaviour.

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

#135

Post by Kim_Bruning »

GodelNumbering wrote: post #84

It is probably the first-time aha moment the author is talking about. But under the hood, it is probably not as magical as it appears to be. Suppose you prompted the underlying LLM with "You are an expert reviewer in..." and a bunch of instructions followed by the paper. LLM knows from the training that 'expert reviewer' is an important term (skipping over and oversimplifying here) and my response should be framed as…

In your model, explain the old trick "think step by step"

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

#136

Post by karamanolev »

grey-area wrote: post #122
steve1977 wrote: post #103

Earlier quoted context omitted.

> Predict the next word is a terrible summary of what these machines do though, they certainly do more than that What would that be?

They generate text based on quite a large context, including hidden prompts we don’t see and their weights are distorted heavily by training. So I think there’s a lot more than a simple probability of word x coming next. That makes ‘predict next word’ a reductive summary IMO. I do not personally feel it resembles thinking or reasoning though and really object to that framing because it is misleading many people.

> their weights are distorted heavily by training

What does that even mean? Their weights are essentially created by training. There aren't some magic golden weights that are then distorted.

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

#137

Post by heavyset_go »

c22 wrote: post #76
wavemode wrote: post #74

Earlier quoted context omitted.

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?

You can write an f(x) and record the input and output and that can be your training data. Or just download some time-series data or something.

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

#138

Post by basch »

steve1977 wrote: post #125
basch wrote: post #117

Earlier quoted context omitted.

A the time, it was a free language translation tool. You weren't paying for transformers in 2017.

True, but that doesn't mean that Google did not already have intentions to monetize it if possible.

You would think, wouldn’t you?

And yet they waited until ChatGPT was a thing and threw Bard together overnight in response.

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

#139

Post by justinator »

317070 wrote: post #119
sasjaws wrote: post #93

A while ago i did the nanogpt tutorial, i went through some math with pen and paper and noticed the loss function for 'predict the next token' and 'predict the next 2 tokens' (or n tokens) is identical. That was a bit of a shock to me so wanted to share this thought. Basically i think its not unreasonable to say llms are trained to predict the next book instead of single token. Hope this is usefull to someone.

As an expert in the field: this is exactly right. LLMs are trained to do whole book prediction, at training time we throw in whole books at the time. It's only when sampling we do one or a few tokens at the time.

where do you get these books?

honking intensifies

WHERE DO YOU GET THESE BOOKS?!

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

#140

Post by interloxia »

basch wrote: post #113
steve1977 wrote: post #108

Earlier quoted context omitted.

From what I understand, it's more like "input is 1, 3, 5, 7" so "output is likely to be 9". Understanding would be a bit generous of a term for that I guess, but that also depends on the definition of understanding.

Id really invite people to read the google blog post. https://research.google/blog/transformer-a-novel-neural-netw... Google chose the word understanding.

The task is language understanding. The tool is amazing. Pianos are amazing. The task is to create music. The process is to transform movement to sound. They don't understand music.
Post reply on HN