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

201–210 of 338 posts

Re: GPT-4 Designed a Programming Language

#201

Post by marviel »

dirkt wrote: post #196
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…

> But my argument is that humans are also, at some level, sufficiently advanced stochastic parrots. But humans have a feedback loop called "consciousness" that sits above the stochastic parrot level, can reason about it, and can separate the wheat from the chaff. AI still has to reach this level. ChatGPT cannot judge if its answers are right or wrong. It just claims things confidently, and as long as it is parroting…

I don't disagree we're still better in a number of ways, but if GPT-4 was given a database, and a "while" loop -- do you think it would gain consciousness?

Re: GPT-4 Designed a Programming Language

#202

Post by sparkie »

yowzadave wrote: post #141

Last year, when Blake Lemoine was fired by Google for claiming his AI was sentient, a lot of people on this website sensibly noted that the danger of these chatbots was not that they were sentient, but that average people could easily be tricked into thinking that they were. And now here we are: it seems we tech people are every bit as susceptible to this kind of thinking as the average joes we looked down on. Actual…

> It’s just a mishmash of features from the most commonly blogged-about existing programming languages. It has no conceptual insights, no original ideas, no taste that isn’t cribbed from one of the few languages it’s copying from.

It will also learn all the bugs and reproduce them.

Programmers who think ChatGPT is going to replace their job must have a very low opinion of their own skill set.

Re: GPT-4 Designed a Programming Language

#203

Post by tasuki »

> If you were going to design a new programming language that encompassed all of these ideas, what would it's syntax look like?

Why this obsession with syntax? Semantics are way more important! GPT rightly chooses to ignore the question and answers with a high level proposal of design.

Re: GPT-4 Designed a Programming Language

#204

Post by KyeRussell »

Jensson wrote: post #156
cyclotron3k wrote: post #153

Earlier quoted context omitted.

It seems only yesterday that we were marvelling at the capabilities of ChatGPT - it's ability to parse the sum knowledge of humankind and synthesise not trivial responses to questions we posed. But look how far we've come since those heady and carefree days. We're already able to pour buckets of scorn on its capabilities, and brush them aside as if designing a language (albeit a derivative and uninspired one) is a tr…

> We're already able to pour buckets of scorn on its capabilities No we don't, we are just trying to put a damper on all the "the singularity is here!" style comments that seems to flood any discussion about GPT.

Oh please. This community is filled to the brim with people that are addicted to negativity and contrarianism. LLM criticisms very typically go far far beyond “this isn’t the singularity”, well toward “LLMs do nothing of value, snd certainly can’t I - the esteemed developer - with anything I find hard in my job!”

Re: GPT-4 Designed a Programming Language

#205

Post by ummonk »

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…

Really? As far as I know, Rust’s borrow checker was a newly developed approach to memory safety. There have been other non-GC/RC approaches to memory safety in e.g. Cyclone or Ada but Rust’s system is novel.

Likewise, Julia’s use of just in time compilation of dynamic dispatched code to achieve zero overhead execution was rather groundbreaking.

Re: GPT-4 Designed a Programming Language

#206

Post by KyeRussell »

eitland wrote: post #198
geraneum wrote: post #185

Earlier quoted context omitted.

> designing a language (albeit a derivative and uninspired one) is a trivial task that any human could achieve. It is, isn’t it? You just need to be able to read and write words and symbols that reassemble a programming language coherently and follow the pattern. This is what humans do after all; remixing. Anyone can do this.

Sorry if I am missing something here, but I think we all know well functioning, productive humans, maybe even in our field, who wouldn't have been able to create this language or a similarly well thought out one. I know a competent man should be able to "change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take…

Don’t bother. Hacker News takes the throne for “I could do this in a weekend” rhetoric.

Re: GPT-4 Designed a Programming Language

#207

Post by marviel »

nethdeco wrote: post #33

TenetLang with all the features from different languages, I wonder how would it actually function in a more realistic environment. Will it also inherit the underlying problems of all the said language. I wonder.

I bet it would have some of the same issues. But I'm super interested in going for longer design sessions with the agent, to see how deep we can get into the edge cases.

For instance, perhaps just pointing out "hey we had this bug because we thought X was Y but actually it was Z"

And then telling the agent to do a "5 Whys" type analysis to get to the root of the problem, and then tell it to try to make a language level patch to eliminate that class of issue.

Speculation, but for the first time ever I feel like that kind of thing may be in reach soon-ish

Re: GPT-4 Designed a Programming Language

#208

Post by Jensson »

sparkie wrote: post #202
yowzadave wrote: post #141

Last year, when Blake Lemoine was fired by Google for claiming his AI was sentient, a lot of people on this website sensibly noted that the danger of these chatbots was not that they were sentient, but that average people could easily be tricked into thinking that they were. And now here we are: it seems we tech people are every bit as susceptible to this kind of thinking as the average joes we looked down on. Actual…

> It’s just a mishmash of features from the most commonly blogged-about existing programming languages. It has no conceptual insights, no original ideas, no taste that isn’t cribbed from one of the few languages it’s copying from. It will also learn all the bugs and reproduce them. Programmers who think ChatGPT is going to replace their job must have a very low opinion of their own skill set.

It will also combine correct things in incorrect ways, so even if everything it is trained on is correct it will still print incorrect things.

We see it in this article, both the statement "Indentation-based scoping, similar to Python" and the code with bracers were probably correct in their original contexts, but combined they are no longer correct. LLMs will make such errors no matter what kind of data you train it on, there is no known way to avoid that class of errors.

Re: GPT-4 Designed a Programming Language

#209

Post by RHSman2 »

HervalFreire wrote: post #168
worrycue wrote: post #146

Earlier quoted context omitted.

> According to your logic that's proof that humans don't understand anything. Well, it's reasonable to conclude that the people who constantly making "stupid mistakes, assumptions, and biases leaps in logic" don't actually know what they are talking about.

Right but can you make the claim that they don't understand anything at all? That they're stochastic parrots? Because that's the direction where your own logic is taking you. I'll concede one thing, LLMs can't use vicious insults and subtle slights to cover up the lack of a good argument. That's a human specialty done by people who are too scared to admit that they're wrong.

We learn that skill in our training. We are highly trained LLM’s skilled in the nuances.

Everyone is acting like LLM model is the finished product.

It is a baby. Do you remember your nuanced language capability at 5, 8, 10, 20?

Are you the finished product? Do you still make massive leaps of awareness? Yes.

Re: GPT-4 Designed a Programming Language

#210

Post by marviel »

Nasreddin_Hodja wrote: post #107

But do we need yet another language? Python's syntax is almost ideal. Maybe GPT would improve it's performance instead making it 100 times faster?

Love python -- wish it had better types still, and that people were better about putting them in.

May be getting better -- but more often than not I'm seeing totally untyped python libs when I try to crack something new open.

Coming from Typescript makes me feel like I'm missing home.

Post reply on HN