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

Simply explained: How does GPT work?

confusedbit.dev

Post reply on HN
Print view View original

31–40 of 392 posts

Re: Simply explained: How does GPT work?

#31

Post by vadansky »

habosa wrote: post #20

Is it possible that we don’t truly know how it works? That there is some emergent behavior inside these models that we’ve created but not yet properly described? I’ve read a few of these articles but I’m still not completely satisfied.

I hate being the bearish guy during the hype cycle, but I think a lot of that is just anthropomorphizing it. They fed it TBs of human text, it spits out human text, we think it's humanesque.

Of course maybe I'm wrong and it's AGI and it will find this comment and torture me for for insulting it's intelligence.

Re: Simply explained: How does GPT work?

#32

Post by EForEndeavour »

onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

The advanced capabilities of scaled up transformer models fed oodles of training data has burdened me with pseudo-philosophical questions about the nature of cognition that I am not well equipped to articulate, and make me wish I'd studied more neuroscience, philosophy, and comp sci earlier in life. A possibly off-topic thought dump:

- What is thinking, exactly?

- Does human (or superhuman) thinking require consciousness?

- What even is consciousness? Why is it that when you take a bunch of molecular physical laws and scale them up into a human brain, a signal pattern emerges that feels things like emotions, continuity between moments, desires, contemplation of itself and the surrounding universe, and so on?

- Why and how does a string predictor on steroids turn out to do things that seem so close to a practical definition of thinking? What are the best evidence-based arguments supporting and opposing the statement "GPT4 thinks"? How do people without OpenAI's level of model access try to answer this question?

(And yes, it's occurred to me that I could try asking GPT4 to help me make these questions more complete)

Re: Simply explained: How does GPT work?

#33

Post by z3c0 »

LeSaucy wrote: post #27
onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

I have only seen gpt generate imperative algorithms. Does it have the ability to work with concurrency and asynchrony?

I've attempted to pose a concurrency problem to GPT4. The output was invalid code, though likely would have looked correct to the untrained eye. It was only after I spelled out the limitations that it could account for them.

Re: Simply explained: How does GPT work?

#34

Post by twobitshifter »

simonw wrote: post #12
onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

I've started to suspect that generating code is actually one of the easier things for a predictive text completion model to achieve. Programming languages are a whole lot more structured and predictable than human language. In JavaScript the only token that ever comes after "if " is "(" for example.

I loved your example. I think that may be an obvious advantage to LLM, humans are poor at learning new languages after adolescence but a LLM can continue to learn and build new connections. Studies show that multilingual people have an easier time making connections and producing new ideas, In the case of programming, we may build something that knows all programming languages and all design patterns and can merge this knowledge to come up with better solutions than the ordinary programmer.

Re: Simply explained: How does GPT work?

#35

Post by senectus1 »

Analog24 wrote: post #24
winternett wrote: post #21

Where is IBM's Watson in all this? It seems as if it never existed? That is just one example of how companies keep making these grand presentations and under-delivering on results... Plain and simple the over-hyped GPT editions are NOT truly AI, it is scripting to assemble coherent looking sentences backed by scripts that parse content off of of stored data and the open web into presented responses.... There is no "a…

What would be the differentiating factor(s) for true AI/intelligence in your opinion?

any sufficiently advanced technology is AI...

Re: Simply explained: How does GPT work?

#36

Post by seydor »

Analog24 wrote: post #28
seydor wrote: post #17

This is confusing, using the semantic vectors arithmetic of embeddings is not very relevant to transformers and its completely missing the word 'attention'. I don't think transformers are that difficult to explain to people , but it is hard to explain "why" they work. But i think it's important for everyone to look under the hood and know that there are no demons underneath.

Embeddings and their relationship to each other are definitely relevant to transformers. Why do you think that's not the case?

gptX embeddings aren't even words. Even so, the embedding relationship is useful but not the core of what transformers do to find relationships between words in sequences.

Re: Simply explained: How does GPT work?

#37

Post by agentultra »

onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

It's not thinking, plain and simple.

Anything it generates means nothing to the algorithm. When you read it and interpret what was generated you're experiencing something like the Barnum-Forer effect. It's sort of like reading a horoscope and believing it predicted your future.

Re: Simply explained: How does GPT work?

#38

Post by kingkongjaffa »

EForEndeavour wrote: post #32
onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

The advanced capabilities of scaled up transformer models fed oodles of training data has burdened me with pseudo-philosophical questions about the nature of cognition that I am not well equipped to articulate, and make me wish I'd studied more neuroscience, philosophy, and comp sci earlier in life. A possibly off-topic thought dump: - What is thinking, exactly? - Does human (or superhuman) thinking require conscious…

I think since the mechanisms are different we should arrive at a distinction between:

organic thinking (I.e. the process our squishy human brains do)

and mechanical thinking ( the computational and stochastic processes that computers do ).

Re: Simply explained: How does GPT work?

#39

Post by pen2l »

simonw wrote: post #12
onetrickwolf wrote: post #7

I've been using GPT4 to code and these explanations are somewhat unsatisfactory. I have seen it seemingly come up with novel solutions in a way that I can't describe in any other way than it is thinking. It's really difficult for me to imagine how such a seemingly simple predictive algorithm could lead to such complex solutions. I'm not sure even the people building these models really grasp it either.

I've started to suspect that generating code is actually one of the easier things for a predictive text completion model to achieve. Programming languages are a whole lot more structured and predictable than human language. In JavaScript the only token that ever comes after "if " is "(" for example.

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 when we see the results of it being implemented everywhere but it hasn't really come yet. I'm seeing too many examples of good usage (young folks using it for learning, ESL speakers asking for help and revisions, high-level programmers using it to save themselves additional keystrokes, the list is long).

Re: Simply explained: How does GPT work?

#40

Post by matjet »

exitb wrote: post #30
simonw wrote: post #12

Earlier quoted context omitted.

I've started to suspect that generating code is actually one of the easier things for a predictive text completion model to achieve. Programming languages are a whole lot more structured and predictable than human language. In JavaScript the only token that ever comes after "if " is "(" for example.

On the other hand, if you want to use an external library on the line 80, you need to import it at the top. I once asked it for a short example code of something, no longer than 15 lines and it said "here's a code that's 12 lines long" and then added the code. Did it have the specific code "in mind" already? Or was it just a reasonably-sounding length and it then just came up with code that matched that self-imposed…

The latter option is closest, but neither is quite right. It would have ~known~ that the problem asked, combined with a phrase for a 15 line limit has associations with a length of 12 lines (perhaps most strongly 12, but depending on temp it could have given other answers). From there it is constrained to (complete) solutions that lead to 12 lines, from the several (partial) solutions that already exist in the weights.
Post reply on HN