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

What is ChatGPT doing and why does it work?

writings.stephenwolfram.com

Post reply on HN
Print view View original

231–240 of 518 posts

Re: What is ChatGPT doing and why does it work?

#231

Post by xeyownt »

If you don't have a Wolfram language intrepeter, you can use ChatGPT to act like one. It produces quite convincing results. ----------

Hi Chat! Do you know the Wolfram Language? I would like you to act as a Wolfram Language interpreter. I will type in command and you will reply with the expected response. If the response contains some output that you cannot reproduce (e.g. like an image), you will try to replace it by a description of that response. My first command is: model = NetModel[{"GPT2 Transformer Trained on WebText Data","Task" -> "LanguageModeling"}]

Re: What is ChatGPT doing and why does it work?

#232

Post by scarface74 »

jeremyjh wrote: post #222
scarface74 wrote: post #217

Earlier quoted context omitted.

This is a script I told ChatGPT to write. “Write a Python script that returns a comma separated list of arns of all AWS roles that contain policies I specify with the “-p” parameter using argparse” Then I noticed there was a bug, AWS API calls are paginated and it would only return the first 50 results. “that won’t work with more than 50 roles” Then it modified the code to use “paginators” Yes, you can find similar c…

Ok that actually sounds hugely useful. It makes sense for very well known APIs it will get them quite accurately.

I wonder how well it would work if you seeded it with the inputs and outputs of custom APIs and then tell it to write code based on your API.

Re: What is ChatGPT doing and why does it work?

#233

Post by xeyownt »

xeyownt wrote: post #231

If you don't have a Wolfram language intrepeter, you can use ChatGPT to act like one. It produces quite convincing results. ---------- Hi Chat! Do you know the Wolfram Language? I would like you to act as a Wolfram Language interpreter. I will type in command and you will reply with the expected response. If the response contains some output that you cannot reproduce (e.g. like an image), you will try to replace it b…

{ "The best thing about AI is its ability to be", "The best thing about AI is its ability to be able", "The best thing about AI is its ability to be able to", "The best thing about AI is its ability to be able to do", "The best thing about AI is its ability to be able to do so", "The best thing about AI is its ability to be able to do so much", "The best thing about AI is its ability to be able to do so much more", "The best thing about AI is its ability to be able to do so much more than humans" }

Re: What is ChatGPT doing and why does it work?

#234

Post by Baeocystin »

int_19h wrote: post #216
Baeocystin wrote: post #157

Earlier quoted context omitted.

ChatGPT has been blowing every single translation task I've thrown it out of the water, even compared to other modern systems. I have no idea why more people aren't talking about that aspect of it either, other than the Anglosphere in general is kind of oblivious to things that aren't English.

For Russian, at least, sticking the article (bit by bit) into ChatGPT produces results that are broadly comparable to Bing and Google translators. It is somewhat more likely to pick words that are not direct translations, but might convey the idea better given the likely cultural background of someone speaking the language - for example, it will sometimes (but not always) replace "voodoo" with "witchcraft". However,…

I'm sure you're on the right track, regarding the % of the training corpus in English vs. other languages. It has done very well with colloquial Spanish as spoken in California, for example, which probably isn't too surprising.

What amazes me (and that you hint at) is that it still manages to pick more appropriate word/phrase choices, most of the time, even compared to dedicated translation software. I get the feeling (and I fully admit, this is just a feeling) that it's not using English, or any other language, as a pivot, but that there's some higher-dimensionality translation going on that allows it to perform as well as it does.

Re: What is ChatGPT doing and why does it work?

#235

Post by Baeocystin »

tkgally wrote: post #202
britzkopf wrote: post #132

Earlier quoted context omitted.

The thing I'm sort of confused about, but maybe someone can explain why I shouldn't be, is, why does there seem to be no implication for language translation? Or is there but coverage is overwhelmed by the fascination with chatGPT? In short, is machine language translation now a fully solved problem? A couple years ago when I tested Google translate in a non-esoteric conversation with my Russian speaking girlfriend a…

I worked as a translator for many years and have been following developments in machine translation closely. In my opinion, ChatGPT does represent a significant advance for machine translation. If you have the time to watch it, I made a video about the topic last week: https://youtu.be/najKN2bXqCo

Thanks for sharing this.

Re: What is ChatGPT doing and why does it work?

#236

Post by michael-go »

robert-wallis wrote: post #94

I'd really like to see an LLM use Wolfram Alpha APIs like the new Toolformer paper does https://paperswithcode.com/paper/toolformer-language-models-...

checkout https://youtu.be/wYGbY811oMo and play with the demo at https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain

Re: What is ChatGPT doing and why does it work?

#237

Post by zhynn »

paulmd wrote: post #130
jonahbenton wrote: post #108

Earlier quoted context omitted.

Define understand, and does an analog to Godel's incompleteness apply.

> does an analog to Godel's incompleteness apply not GP but this seems like quite an attractive idea that many people have reached: a brain of a given "complexity" cannot comprehend the activity of another brain of equal or higher complexity. I'm positive I'm cribbing this from scifi somewhere, maybe Clarke Or Asimov, but, it's the same idea as the Chomsky hierarchy, and the Godel theorems seem like a generalization…

This is so lovely, and my gut says it's spot on (, but that's far from proof. :)

The biological machine simulation theory of consciousness has some rigor behind it. I am reminded of the Making Sense podcast episode #178 with Donald Hoffman (author of The Case Against Reality). More succinct overview: https://www.quantamagazine.org/the-evolutionary-argument-aga...

I don't know that I am with him on the "reality is a network of conscious agents" endpoint of this argument. But it's interesting!

I think that the brain is doing lots of hallucinating. We get stimulus of various kinds, and we create a story to explain the stimulus. Most of the time it is correct, and the story of why we see or smell something is because it is really there. Just as you mention with examples that are too fast for the brain to be doing anything other than reacting, but we create a story about why we did whatever we did, and these stories are absolutely convincing.

If our non-insane behavior can be described as doing predictable next-actions (if a person's actions are sufficiently unpredictable or non-sequitur, we categorize them as insane)... being novel or interesting is ok, but too much is scary and bad. This is not very different from chatGPT "choose a convincing next word". And if it was just working like this under the hood, we would invent a story of an impossibly complex and nuanced consciousness that is generating these "not-too-surprising next actions". In a sense I think we are hallucinating the hard problem of consciousness in much the same way that we hallucinate a conscious reason that we performed an action well after the action was physiologically underway.

I think tool making will be a consequence of the most important sign of intelligence, which is goal-directed curiosity. Or even more simply: an imagination. A simulation of the world that allows you to craft a goal in the form of a possible future world-state that can only be achieved by performing some novel action in the present. Tools give you more leverage, greater ability to impact the future world-state. So I see tools as just influencing the magnitude of the action.

The more important bit is the imagination, the simulation of a world that doesn't yet exist and the quality of that simulation, and curiosity.

Re: What is ChatGPT doing and why does it work?

#238

Post by Agentlien »

thomashop wrote: post #137
britzkopf wrote: post #132

Earlier quoted context omitted.

The thing I'm sort of confused about, but maybe someone can explain why I shouldn't be, is, why does there seem to be no implication for language translation? Or is there but coverage is overwhelmed by the fascination with chatGPT? In short, is machine language translation now a fully solved problem? A couple years ago when I tested Google translate in a non-esoteric conversation with my Russian speaking girlfriend a…

I think general translation is kind of solved when it comes to popular languages. Try DeepL. I dont know how well it works for different language pairs to the languagesi know. I dont even know if deepl uses one of the newer large language models

What qualifies as popular languages in your opinion?

I use DeepL a lot as a first draft when translating stuff from Swedish (~10 million native speakers) or Dutch (~30 million native speakers) to English. While it's good enough as a starting point it regularly negates the meaning of fairly simple sentences, completely misses the use of popular idioms (often resulting in a non sequitur) and more often than not spits out grammatically incorrect nonsense for any sentence relying on implied context.

Re: What is ChatGPT doing and why does it work?

#239

Post by tshaddox »

gowld wrote: post #117
jmoak3 wrote: post #87

Earlier quoted context omitted.

I saw a great comment here, and I will repeat it without the attribution it deserves: We may have realized it's easier to build a brain than to understand one

We've known that for thousands of years. Any Dick and Jane can build a brain.

And that’s just growing a new one from the seeds that already contain all the information and machinery required. Perhaps even more impressive is that this design itself was constructed without any understanding.

Re: What is ChatGPT doing and why does it work?

#240

Post by eslaught »

cm2012 wrote: post #188
jeremyjh wrote: post #179

Earlier quoted context omitted.

But if you ever a have a conversation with it you know it isn't a brain. I'm not talking about detection here; its whole point is to generate credible text so it is going to evade detection well. But can't you just tell from talking to it that there is nothing there?

For now. Give it a truly persistent memory and 100x the size of the dataset I think most people would change their tune.

Hasn't it already been trained on what is effectively the entire contents of the scrapable internet? There isn't another 10x to be had there, let alone 100x.

I assume that whatever future improvements we get from improving algorithms (or perhaps through throwing more compute at it), not through larger datasets.

Post reply on HN