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

I built a programming language using Claude Code

ankursethi.com

Post reply on HN
Print view View original

101–110 of 194 posts

Re: I built a programming language using Claude Code

#101

Post by eatsyourtacos »

andsoitis wrote: post #2

> While working on Cutlet, though, I allowed Claude to generate every single line of code. I didn’t even read any of the code. Instead, I built guardrails to make sure it worked correctly (more on that later). Impressive. As a practical matter, one wonders what th point would be in creating a new programming languages if the programmer no longer has to write or read code. Programming languages are after all the inter…

I have been building a game via a separate game logic library and Unity (which includes that independent library).. let's just say that over the last couple weeks I have 100% lost the need to do the coding myself. I keep iterating and have it improve and there are hundreds of unit tests.. I have a Unity MCP and it does 95% of the Unity work for me. Of course the real game will need custom designing and all that; but in terms of getting a complete prototype setup.... I am literally no longer the coder. I just did in a week what it would have taken me months and months and months to do. Granted Unity is still somewhat new to, but still.. even if you are an expert- it can immediately look at all your game objects and detect issues etc.

So yeah for some things we are already at the point of "I am not longer the coder, I am the architect".. and it's scary.

Re: I built a programming language using Claude Code

#102

Post by ModernMech »

dmd wrote: post #89
imiric wrote: post #63

Earlier quoted context omitted.

> every AI coding bot will learn your new language as a matter of course after its next update includes the contents of your website. How will it "learn" anything if the only available training data is on a single website? LLMs struggle with following instructions when their training set is massive. The idea that they will be able to produce working software from just a language spec and a few examples is delusional.…

It's wild to me the disconnect between people who actually use these tools every day and people who don't. I have done exactly the above with great success. I work with a weird proprietary esolang sometimes that I like, and the only documentation - or code - that exists for it is on my computer. I load that documentation in, and it works just fine and writes pretty decent code in my esolang. "But that can't possibly…

The reason it works so well is that everyone’s “personal unique language” really isn’t all that different from what’s been proposed before, and any semantic differences are probably not novel. If you make your language C + transactional memory, the LLM probably has enough information about both to reason about your code without having to be trained on a billion lines.

Probably if you’re trying to be esoteric and arcane then yeah, you might have trouble, but that’s not normally how languages evolve.

Re: I built a programming language using Claude Code

#103

Post by gf000 »

Insanity wrote: post #94
gf000 wrote: post #77

Earlier quoted context omitted.

Go is one of the most verbose mainstream programming languages, so that's a pretty terrible example.

Maybe not a perfect example but it’s more lightweight than Java at least haha

If by lightweight you mean verbosity, then absolutely no.

In go every third line is a noisy if err check.

Re: I built a programming language using Claude Code

#104

Post by gf000 »

giancarlostoro wrote: post #91
gf000 wrote: post #77

Earlier quoted context omitted.

Go is one of the most verbose mainstream programming languages, so that's a pretty terrible example.

To you maybe, but Go is running a large amount of internet infrastructure today.

How does that relate to Go being a verbose language?

Re: I built a programming language using Claude Code

#105

Post by beepbooptheory »

amelius wrote: post #47
geon wrote: post #10

Earlier quoted context omitted.

That’s git commits.

That's arguably not very ergonomic, which is probably the biggest requirement for a programming language.

Why care about ergonomics if you're not going to write the code?

Re: I built a programming language using Claude Code

#106

Post by dmd »

ModernMech wrote: post #102
dmd wrote: post #89

Earlier quoted context omitted.

It's wild to me the disconnect between people who actually use these tools every day and people who don't. I have done exactly the above with great success. I work with a weird proprietary esolang sometimes that I like, and the only documentation - or code - that exists for it is on my computer. I load that documentation in, and it works just fine and writes pretty decent code in my esolang. "But that can't possibly…

The reason it works so well is that everyone’s “personal unique language” really isn’t all that different from what’s been proposed before, and any semantic differences are probably not novel. If you make your language C + transactional memory, the LLM probably has enough information about both to reason about your code without having to be trained on a billion lines. Probably if you’re trying to be esoteric and arca…

No, mine's a esoteric declarative data description/transform language. It's pretty damn weird.

Re: I built a programming language using Claude Code

#107

Post by fcatalan »

almog wrote: post #55
UncleOxidant wrote: post #36

Earlier quoted context omitted.

> but every AI coding bot will learn your new language as a matter of course after its next update includes the contents of your website. That's assuming that your new, very unknown language gets slurped up in the next training session which seems unlikely. Couldn't you use RAG or have an LLM read the docs for your language?

Neither RAG nor loading the docs into the context window would produce any effective results. Not even including the grammar files and just few examples in the training set would help. To get any usable results you still need many many usage examples.

My own 100% hallucinated language experiment is very very weird and still has thousands of lines of generated examples that work fine. When doing complex stuff you could see the agent bounce against the tests here and there, but never produced non-working code in the end. The only examples available were those it had generated itself as it made up the language. It was capable of making things like a JSON parser/encoder, a TODO webapp or a command line kanban tracker for itself in one shot.

Re: I built a programming language using Claude Code

#108

Post by tartoran »

idiotsecant wrote: post #60
spelunker wrote: post #30

Earlier quoted context omitted.

Like everything generated by LLMs though, it is built on the shoulders of giants - what will happen to software if no one is creating new programming languages anymore? Does that matter?

I think the only hope is that AGI arises and picks up where humanity left off. Otherwise I think this is the long dark teatime of human engineering of all sorts.

So you’re hoping for a blackbox uninspectable by humans? That to me sounds like a nightmare, a nightmare worse than all the cruft and stupid rules humanity accrued over time. Let’s hope the future tech is inspectable and understandable by humans.

Re: I built a programming language using Claude Code

#109

Post by giancarlostoro »

gf000 wrote: post #104
giancarlostoro wrote: post #91

Earlier quoted context omitted.

To you maybe, but Go is running a large amount of internet infrastructure today.

How does that relate to Go being a verbose language?

Its not verbose to some of us. It is explicit in what it does, meaning I don't have to wonder if there's syntatic sugar hiding intent. Drastically more minimal than equivalent code in other languages.

Re: I built a programming language using Claude Code

#110

Post by craigmart »

exitb wrote: post #78
craigmart wrote: post #52

Earlier quoted context omitted.

You can make an LLM sound very natural if you simply ask for it and provide enough text in the tone you’d like it to reproduce. Otherwise, it’s obvious that an LLM with no additional context will try to stick to the tone the company aligned it to produce

”I named it Cutlet after my cat. It’s completely legal to do that.” I’ve never seen LLM being able to produce these kind of absurdist jokes. Or any jokes, really.

comedy is a completely different thing than natural tone. I agree that they’re incapable of coming up with decent jokes
Post reply on HN