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

GPT-4 Designed a Programming Language

lukebechtel.com

Post reply on HN
Print view View original

21–30 of 338 posts

Re: GPT-4 Designed a Programming Language

#21

Post by HervalFreire »

swatcoder wrote: post #13
HervalFreire wrote: post #11

quotation from the link: "LLMs in the GPT family have read every programming language in the world, billions of times. It's been known for some time that these agents can write small snippets of code with some limited success. However, to my knowledge, none of these agents have ever been asked to make their own programming language. This type of task is a bit more complex, and requires a bit more creativity and fores…

I was reading the quote you included and was sure you were going to lambast him for his arrogance (nobody else has asked it to design a language? hah!) and for bringing an elephant sized straw man to the depthful analytic discussion many of us are trying to have about this new technology, but you went a different way with it. Huh.

You were expecting me to be a stochastic parrot and just imitate what every other idiot says?

Well I hate to tell you this, I fed that quote into GPT-3 and had it respond to that quote. Who's the parrot now? Just kidding.

Re: GPT-4 Designed a Programming Language

#22

Post by marviel »

satisfice wrote: post #12

GTP is interesting enough without people pretending that it is more interesting than it is. This "new programming language" doesn't look new at all. It looks like the same old thing.

You should read further down in the article where it expands on some more advanced concepts -- but in general you're right -- it is really similar to existing languages.

I wonder as its power changes, what paradigms it might suggest we break out of.

I'd also recommend reading its responses that are non-code in detail -- for instance, in the comment where it introduces TenetLang, GPT-4 actually calls out that it's re-using ideas. I would assume intentionally, because it knows what people are most familiar with.

> GPT-4

> In this new language, called "TenetLang," we'll combine a simple syntax inspired by Python with some features from functional and object-oriented languages. Here is an overview of some design choices:

- Indentation-based scoping, similar to Python.

- Strong typing with type inference, inspired by TypeScript and Kotlin.

- First-class functions and closures, similar to JavaScript.

- Immutable data structures by default, with optional mutable counterparts.

- A concise lambda syntax for anonymous functions.

- Pattern matching and destructuring, inspired by Haskell and Rust.

- Built-in support for concurrency using async/await and lightweight threads.

- Interoperability with other languages using a Foreign Function Interface (FFI).

Re: GPT-4 Designed a Programming Language

#23

Post by swatcoder »

marviel wrote: post #18
swatcoder wrote: post #13

Earlier quoted context omitted.

I was reading the quote you included and was sure you were going to lambast him for his arrogance (nobody else has asked it to design a language? hah!) and for bringing an elephant sized straw man to the depthful analytic discussion many of us are trying to have about this new technology, but you went a different way with it. Huh.

Wasn't trying to be arrogant, I just wasn't aware of an existing implementation and thought it would be fun to try. :) Do you have links to other efforts? I'd love to know more about it, and would be happy to add references to other existing literature to the article if it improved its quality.

I’ve done it casually and I’m sure many many others have, but a very quick and lazy Google (it’s not dead yet) brought up this writeup from December:

https://judehunter.dev/blog/chatgpt-helped-me-design-a-brand...

Re: GPT-4 Designed a Programming Language

#24

Post by doctoboggan »

Recently I've been wondering about a somewhat related idea - a programming language designed specifically for a LLM to write in. I wonder how different (if at all) it would be from our current crop of language designed for humans to use.

I am a little less impressed by the example given in the post. It seems GPT4 still falls in the trap of being overly dependent on previous responses.

Re: GPT-4 Designed a Programming Language

#25

Post by HervalFreire »

kaczordon wrote: post #14
HervalFreire wrote: post #11

quotation from the link: "LLMs in the GPT family have read every programming language in the world, billions of times. It's been known for some time that these agents can write small snippets of code with some limited success. However, to my knowledge, none of these agents have ever been asked to make their own programming language. This type of task is a bit more complex, and requires a bit more creativity and fores…

Future data will still have to come from someone e.g. a person.

Future data that's posted on the internet will be curated by humans. Humans don't post things that are incorrect or outright wrong.

That curation IS human data and will allow data from LLMs to further improve LLMs.

Additionally, there's a randomness element that are part of LLMs that allow LLMs to generate non-deterministic responses that when further curated by humans potentially allows LLMs to become Even better.

Re: GPT-4 Designed a Programming Language

#26

Post by raincole »

HervalFreire wrote: post #25
kaczordon wrote: post #14

Earlier quoted context omitted.

Future data will still have to come from someone e.g. a person.

Future data that's posted on the internet will be curated by humans. Humans don't post things that are incorrect or outright wrong. That curation IS human data and will allow data from LLMs to further improve LLMs. Additionally, there's a randomness element that are part of LLMs that allow LLMs to generate non-deterministic responses that when further curated by humans potentially allows LLMs to become Even better.

> Humans don't post things that are incorrect or outright wrong.

Are you using ChatGPT to write this comment?

If not, I mean... are you okay?

Re: GPT-4 Designed a Programming Language

#27

Post by HervalFreire »

marviel wrote: post #16
raincole wrote: post #15

Earlier quoted context omitted.

I'm not so sure. The first sample is: > Indentation-based scoping, similar to Python. Then... > class Person { To me, it's very clear it doesn't really understand what "indentation-based scoping" means. For a human programmer, using both intentation-based and bracket-based scoping is a very unusual design choice, and is begging for further explanation. It talked pages of abstraction, modularity, etc, but not this ? I…

Author here -- I think it is a stochastic parrot, don't get me wrong. But my argument is that humans are also , at some level, sufficiently advanced stochastic parrots. At least, as it pertains to many creative endeavors. You're always building on the back of something that comes before. We're all just remixing ideas we've heard before. I mean even this comment -- none of the words I'm saying are new, and many of the…

yeah, but colloquially when people start using the term "stochastic parrot" they're referring to something far stupider. From a Technical and pedantic standpoint it could be said ALL intelligence is isomorphic to a stochastic parrot so it's not reasonable to assume in common communication that people are referring to the technical definition when they talk.

Your point in the article is basically saying that chatGPT is not as stupid as people think and also suggesting the fact that humans can be stupid in a similar way to chatGPT as well.

Re: GPT-4 Designed a Programming Language

#28

Post by Jensson »

brucethemoose2 wrote: post #20
Jensson wrote: post #9

This actually isn't a bad idea, GPT takes commonly talked about things and distils them into a response to you, so the language you get when you ask it to make a programming language is probably a mix of well liked programming features that many people added to a language they themselves wanted. When you design a language on your own you will be too biased towards your own cases, this is a way to get around that and…

Nah, GPT has its own biases too. Its preference for Pythonic/JS syntax is a simple but good example, as those are likely the most popular languages in its dataset.

You could probably ask it for a more specific programming language to get around that, like say you want a programming language with static typing and garbage collection.

But yeah, if it just prints javascript and python styles then it isn't very helpful, but it is pretty good at source ideas in most cases.

Re: GPT-4 Designed a Programming Language

#29

Post by HervalFreire »

raincole wrote: post #15
HervalFreire wrote: post #11

quotation from the link: "LLMs in the GPT family have read every programming language in the world, billions of times. It's been known for some time that these agents can write small snippets of code with some limited success. However, to my knowledge, none of these agents have ever been asked to make their own programming language. This type of task is a bit more complex, and requires a bit more creativity and fores…

I'm not so sure. The first sample is: > Indentation-based scoping, similar to Python. Then... > class Person { To me, it's very clear it doesn't really understand what "indentation-based scoping" means. For a human programmer, using both intentation-based and bracket-based scoping is a very unusual design choice, and is begging for further explanation. It talked pages of abstraction, modularity, etc, but not this ? I…

>The advent of chatGPT had millions of people on the internet trying to downplay the intelligence of chatGPT by continuously trying to re-emphasize the things it gets wrong.

Again the parroting. AI has been getting things wrong for decades. It's old news.

The paradigm shift here is in the things it gets right. Because some of the things it gets right can not be attributed to anything else other than the concept of "understanding".

Re: GPT-4 Designed a Programming Language

#30

Post by HervalFreire »

raincole wrote: post #26
HervalFreire wrote: post #25

Earlier quoted context omitted.

Future data that's posted on the internet will be curated by humans. Humans don't post things that are incorrect or outright wrong. That curation IS human data and will allow data from LLMs to further improve LLMs. Additionally, there's a randomness element that are part of LLMs that allow LLMs to generate non-deterministic responses that when further curated by humans potentially allows LLMs to become Even better.

> Humans don't post things that are incorrect or outright wrong. Are you using ChatGPT to write this comment? If not, I mean... are you okay?

What I meant was... humans don't deliberately post WRONG output from chatGPT on the internet. IF they use it to write some blog post or something they will curate the output from chatGPT such that the output fits the topic and is correct to the context. Then when that data gets scraped for training it will be "curated" so bad data generated by the LLM isn't visible.

This is the scenario that occurs when the majority of text on the internet becomes generated by an LLM. Training data from humans is STILL fed back into the LLM via curation of the LLMs own data.

Also please don't ask if I'm "ok" just respond to the comment.

Post reply on HN