Simply explained: How does GPT work? • Hacker News Board

Re: Simply explained: How does GPT work?

#131

Post by IshKebab » Thu, Apr 06, 2023, 4:50 PM UTC

ZeroGravitas wrote: post #104

> It is able to link ideas logically, defend them, adapt to the context, roleplay, and (especially the latest GPT-4) avoid contradicting itself. Isn't this just responding to the context provided? Like if I say "Write a Limerick about cats eating rats" isn't it just generating words that will come after that context, and correctly guessing that they'll rhyme in a certain way? It's really cool that it can generate coh…

> Like if I say "Write a Limerick about cats eating rats" isn't it just generating words that will come after that context, and correctly guessing that they'll rhyme in a certain way?

Aren't you just doing that?

Re: Simply explained: How does GPT work?

#132

Post by JieJie » Thu, Apr 06, 2023, 4:52 PM UTC

i-use-nixos-btw wrote: post #130

I’d be interested in hearing from anyone who takes the Chinese Room scenario seriously, or at least can see how it applies to any of this. I cannot see that it matters if a computer understands something. If it quacks like a duck and walks like a duck, and your only need is for it to quack and walk like a duck, then it doesn’t matter if it’s actually a duck or not for all intents and purposes. It only matters if you…

I literally lost a friend of thirty years yesterday because she is wedded to the Chinese Room analogy so fiercely, she refuses to engage on the subject at all.

For all the terrible things people worry about ChatGPT doing, this was not one that I thought I was going to have to deal with.

(edit: ChatGPT was not involved at all, but when I suggested she give it a try to see for herself, that was the end of it.)

Re: Simply explained: How does GPT work?

#133

Post by swframe2 » Thu, Apr 06, 2023, 4:55 PM UTC

sirwhinesalot wrote: post #46

It predicts the next word/token based on the previous pile of words/tokens. Given a large enough model (as in GPT3+) it can actually output some rather useful text because the probabilities it learned on what the next token should be are rather accurate.

(my opinion) It is not predicting based on 'words/tokens'. It is transforming the general words/tokens embeddings into a context specific embedding which encodes "meaning". It is not an n-gram model of words. It is more like an n-gram model of "meaning". It doesn't encode all the "meanings" that humans are able to but with addition labelled data it should get closer. I think gpt is a component which can be combined to create AGI. Adding the API so it can use tools and allowing it to self-reflect seem like it will get closer to AGI quickly. I think allowing to read/write state will make it conscious. Creating the additional labels it needs will take time but it can do that on its own (similar to alpha-go self-play).

Re: Simply explained: How does GPT work?

#134

Post by rwmj » Thu, Apr 06, 2023, 4:56 PM UTC

i-use-nixos-btw wrote: post #130

I’d be interested in hearing from anyone who takes the Chinese Room scenario seriously, or at least can see how it applies to any of this. I cannot see that it matters if a computer understands something. If it quacks like a duck and walks like a duck, and your only need is for it to quack and walk like a duck, then it doesn’t matter if it’s actually a duck or not for all intents and purposes. It only matters if you…

Isn't the whole point of Searle raising the Chinese Rooom argument exactly so that these kinds of things can be debated?

Re: Simply explained: How does GPT work?

#135

Post by mhink » Thu, Apr 06, 2023, 5:01 PM UTC

i-use-nixos-btw wrote: post #130

I’d be interested in hearing from anyone who takes the Chinese Room scenario seriously, or at least can see how it applies to any of this. I cannot see that it matters if a computer understands something. If it quacks like a duck and walks like a duck, and your only need is for it to quack and walk like a duck, then it doesn’t matter if it’s actually a duck or not for all intents and purposes. It only matters if you…

In my understanding of the Chinese Room example, the resolution to the argument is that the *human* may not understand Chinese, but the *system as a whole* can be said to understand it.

With this in mind, I think asking whether ChatGPT *in and of itself* is "conscious" or has "agency" is sort of like asking if the speech center of a particular human's brain is "conscious" or has "agency": it's not really a question that makes sense, because the speech center of a brain is just one part of a densely interconnected system that we only interpret as a "mind" when considered in its totality.

Re: Simply explained: How does GPT work?

#136

Post by iliane5 » Thu, Apr 06, 2023, 5:02 PM UTC

i-use-nixos-btw wrote: post #130

I’d be interested in hearing from anyone who takes the Chinese Room scenario seriously, or at least can see how it applies to any of this. I cannot see that it matters if a computer understands something. If it quacks like a duck and walks like a duck, and your only need is for it to quack and walk like a duck, then it doesn’t matter if it’s actually a duck or not for all intents and purposes. It only matters if you…

What I find really entertaining is the "just predicting the next token" argument.

If just predicting the next token can produce similar or better results than the almighty human intelligence on some tasks, then maybe there's a bit of hubris in how smart we think we actually are.

Re: Simply explained: How does GPT work?

#137

Post by rfmoz » Thu, Apr 06, 2023, 5:04 PM UTC

I’ve been looking an article like this, great job. Thanks

Re: Simply explained: How does GPT work?

#138

Post by lanstin » Thu, Apr 06, 2023, 5:04 PM UTC

justrealist wrote: post #55

pen2l wrote: post #39

Earlier quoted context omitted.

The more constraints there are (e.g. like your example) the better it should perform. So it disappoints me when copilot, knowing what libraries are available in the IDE it's running in, hallucinates up a method call that doesn't exist. Separately (and apologies for going on a tangent), where do you think we are in the Gartner cycle? Around GPT3 time I was expecting for trough of disillusionment to come, particularly…

> hallucinates up a method call that doesn't exist I actually think it helps to reframe this. It hallucinates up a method call that predictively should exist. If you're working with boto3, maybe that's not actually practical. But if it's a method within your codebase, it's actually a helpful suggestion! And if you prompt it with the declaration and signature of the new method, very often it will write the new helper…

If you have a long iterative session by the end it will have forgotten the helpful hallucinations at the beginning, so then phantom methods evolve in their name and details.

I wonder if it is better at some languages than others. I have been using it for Go for a week or two and it’s ok but not awesome. I am also learning how to work with it, so probably will keep at it, but it is clearly a generative model not a thinking being I am working with.

Re: Simply explained: How does GPT work?

#139

Post by danenania » Thu, Apr 06, 2023, 5:05 PM UTC

Zetice wrote: post #127

Does anyone have a good recommendation for a book that would cover the underlying ideas behind LLMs? Google ends up giving me a lot of ads, and ChatGPT is vague about specifics as per usual.

Not a book, but here's a really good explanation in blog post form from Stephen Wolfram:

https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-...

Re: Simply explained: How does GPT work?

#140

Post by bnralt » Thu, Apr 06, 2023, 5:07 PM UTC

i-use-nixos-btw wrote: post #130

I’d be interested in hearing from anyone who takes the Chinese Room scenario seriously, or at least can see how it applies to any of this. I cannot see that it matters if a computer understands something. If it quacks like a duck and walks like a duck, and your only need is for it to quack and walk like a duck, then it doesn’t matter if it’s actually a duck or not for all intents and purposes. It only matters if you…

> I’m no philosopher, but if your argument hinges on moving goalposts until purity is reached, and your basic assumption is that the requirements for purity are infinite, then it’s not a very useful argument.

I imagine many definitions are initially rather broad and only get refined down over time. Laertius gives us a classic example:

> Plato defined man thus: “Man is a two-footed, featherless animal,” and was much praised for the definition; so Diogenes plucked a cock and brought it into his school, and said, “This is Plato’s man.” On which account this addition was made to the definition, “With broad flat nails.”

I don’t think it’s correct to think of that as infinitely moving goalposts, however. More that the weakness of definitions isn’t always immediately transparent.