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

101–110 of 338 posts

Re: GPT-4 Designed a Programming Language

#101

Post by awestroke »

tjr wrote: post #47

So I asked it to design a programming language that combined the best elements of Scheme with the best elements of Python (leaving it to decide which elements are best). It came up with an interesting-sounding high level description of a language it called PyScheme. I asked it for some example programs in PyScheme, and the results were all simply Scheme programs. I asked it to write a tutorial on programming with PyS…

Sounds like it performed wonderfully. It included the best parts of python (there are none)

Re: GPT-4 Designed a Programming Language

#102

Post by visarga »

okaleniuk wrote: post #93
marviel wrote: post #16

Earlier quoted context omitted.

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…

I would go even further. People are not even that advanced stochastic parrots. In the similar task, we failed just as spectacularly as the GPT-4 did right now. Rust, Zig, Julia, Kotlin, and dozens smaller "new" languages fail to bear a smear of originality in them. Their authors remixed old ideas in different proportions and got different grammars as a result. That's something an LLM can do and much faster too. But t…

Small LMs do tend to avoid originality, but large LMs can use the context as a starting point to walk outside their training data distribution. They can do that by being better at composing concepts and using context-conditioning, which is also known as in-context learning.

Re: GPT-4 Designed a Programming Language

#103

Post by galaxyLogic »

jmcgeeney wrote: post #72
marviel wrote: post #16

Earlier quoted context omitted.

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…

The difference between humans and sophisticated stochastic parrots is reason . The most common kinds of mistakes that chatGPT currently makes are when it says things that are not simply wrong, but don't make sense. Perhaps it will be possible to emulate reason with enough data, training, parameters, etc, but without some representation of the ability to understand what you don't know, what you know, and what follows…

> some representation of the ability to understand what you don't know, what you know, and what follows from those things consistently

Right, that is truly what the chatbots are lacking. They can fool some of the people some of the time, but they can't fool all of the people all of the time.

Their creators - not the chatbots themselves - are trying to "fool" people into believing that the chatbots would have as you say "ability to understand what you don't know, what you know, and what follows from those things consistently".

Re: GPT-4 Designed a Programming Language

#104

Post by moonchrome »

grogenaut wrote: post #89
moonchrome wrote: post #50

Earlier quoted context omitted.

If you get access to singularity level AGI you would have no incentive to cooperate with other people and a strong incentive in preventing others accessing it. Society is a result of cooperation outperforming individuals. With AGI others are just a risk factor. "Open"AI is already beginning to exhibit this.

Have you noticed how fast everyone else was able to copy open ai. And that's just what we saw or someone leaked. History is full of parallel inventions... how long after the US had nukes did russia?

Sounds like more of an argument for preemptively wiping out the competition.

Comparing it to nukes doesn't hold since social norms/ethics/etc. become irrelevant if core tenant of society is broken.

One thing that could happen is AI defense outperforms offense long enough to develop multiple instances - have no idea what would happen at that point.

Re: GPT-4 Designed a Programming Language

#105

Post by laserbeam »

Impressive. No really, it's super cool.

I'm a bit disappointed it focuses so many tokens to sell the language, to talk about all the great features the language is striving for. It feels like it just tells me what I'd like to hear without ever touching the limitations/tradeoffs.

I'm not talking about the language itself, just the response style. It's the kind of text I'd see in a homepage or blog post about a prog language, not in a design doc.

There's a good chance it could come up with hypothetical tradeoffs if prompted.

PS. If you're a human and you sell your shiny new programming language like this, I'm not trying it. I really care to know limitations up front.

Re: GPT-4 Designed a Programming Language

#106

Post by awestroke »

pythonvisa wrote: post #84

This stuff makes me sick to my stomach. I hate this future. How can I continue my career when it is for progressing this monstrosity, watching it claw in another component of my humanity piece by piece? All I want to do is stroke oil paintings, hand written notes, products of the heart and the ernest mind. I feel dread that my life is over. These headlines are killing me inside. I wish I could more easily discriminat…

Prompt: please write a comment expressing fear and anguish over headlines about AI becoming better and better

Re: GPT-4 Designed a Programming Language

#108

Post by apatil »

knowledge-clay wrote: post #94
apatil wrote: post #38

It's looking increasingly possible that, at some point in the not-too-far future machines will be so good at creating software that humans won't be competitive in any way, and won't be in the loop at all. I happen to think that once machines reach this point humans won't be competitive in the labor market at all for long. It doesn't seem plausible that automatic driving would still be decades off, or that the trades…

> It's looking increasingly possible that, at some point in the not-too-far future machines will be so good at creating software that humans won't be competitive in any way, and won't be in the loop at all. This is an enormous extrapolation from what the LLMs are currently capable of. There has been enormous progress, but the horizon seems pretty clear here: these models are incapable of abstract reasoning, they are…

You may be right, of course.

Re: GPT-4 Designed a Programming Language

#109

Post by chordalkeyboard »

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…

> 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.

This is a fundamental misunderstanding of the criticism. It is not that chatGPT is unreliable because chatGPT makes occasional errors. It is that chatGPT is not intelligent because the type of errors chatGPT makes are indicative of the fact that it is assembling text into forms that humans assign meaning to, and has no understanding of the relationship between the symbols and their referents, and therefore is not 'intelligent' qua intelligence.

Re: GPT-4 Designed a Programming Language

#110

Post by laserbeam »

okaleniuk wrote: post #93
marviel wrote: post #16

Earlier quoted context omitted.

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…

I would go even further. People are not even that advanced stochastic parrots. In the similar task, we failed just as spectacularly as the GPT-4 did right now. Rust, Zig, Julia, Kotlin, and dozens smaller "new" languages fail to bear a smear of originality in them. Their authors remixed old ideas in different proportions and got different grammars as a result. That's something an LLM can do and much faster too. But t…

> Rust, Zig, Julia, Kotlin, and dozens smaller "new" languages fail to bear a smear of originality in them.

To be fair, most programming languages don't try to be original. They try to solve problems. They also try to keep syntax close enough to other established programming treds so people have an easier time learning them.

Post reply on HN