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

111–120 of 194 posts

Re: I built a programming language using Claude Code

#111

Post by heavyset_go »

bobjordan wrote: post #58

I've been working on a large codebase that was already significant before LLM-assisted programming, leveraging code I’d written over a decade ago. Since integrating Claude and Codex, the system has evolved and grown massively. Realistically, there’s a lot in there now that I simply couldn't have built in a standard human lifetime without them. That said, the core value of the software wouldn't exist without a human a…

> I believe the author owns the language.

Not according to the US Copyright Office. It is 100% LLM output, so it is not copyrighted, thus it's free for anyone to do anything with it and no claimed ownership or license can stop them.

Re: I built a programming language using Claude Code

#112

Post by jonfw »

calvinmorrison wrote: post #59
raincole wrote: post #51

Earlier quoted context omitted.

> every AI coding bot will learn your new language If there are millions of lines on github in your language. Otherwise the 'teaching AI to write your language' part will occupy so much context and make it far less efficient that just using typescript.

Uh not really. I am already having Claude read and then one-shot proprietary ERP code written in vintage closed source language OOP oriented BASIC with sparse documentation.... just needed to feed it in the millions of lines of code i have and it works.

I'm sure claude does great at that, but it would be objectively better, for a large variety of reasons, if claude didn't have to keep syntax examples in it's context.

Re: I built a programming language using Claude Code

#113

Post by nineteen999 »

LtWorf wrote: post #85
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.

Well LLMs are made to be extremely verbose so it's a good match!

I think there's a huge range here - ChatGPT to me seems extra verbose on the web version, but when running with Codex it seems extra terse.

Claude seems more consistently _concise_ to me, both in web and cli versions. But who knows, after 12 months of stuff it could be me who is hallucinating...

Re: I built a programming language using Claude Code

#114

Post by Maxatar »

raincole wrote: post #51
marssaxman wrote: post #26

Earlier quoted context omitted.

The constraints enforced in the language still matter. A language which offers certain correctness guarantees may still be the most efficient way to build a particular piece of software even when it's a machine writing the code. There may actually be more value in creating specialized languages now, not less. Most new languages historically go nowhere because convincing human programmers to spend the time it would ta…

> every AI coding bot will learn your new language If there are millions of lines on github in your language. Otherwise the 'teaching AI to write your language' part will occupy so much context and make it far less efficient that just using typescript.

I have not found this to be the case. My company has some proprietary DSLs we use and we can provide the spec of the language with examples and it manages to pick up on it and use it in a very idiomatic manner. The total context needed is 41k tokens. That's not trivial but it's also not that much, especially with ChatGPT Codex and Gemini now providing context lengths of 1 million tokens. Claude Code is very likely to soon offer 1 million tokens as well and by this time next year I wouldn't be surprised if we reach context windows 2-4x that amount.

The vast majority of tokens are not used for documentation or reference material but rather are for reasoning/thinking. Unless you somehow design a programming language that is just so drastically different than anything that currently exists, you can safely bet that LLMs will pick them up with relative ease.

Re: I built a programming language using Claude Code

#115

Post by imiric »

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…

My comment is based precisely on using these tools frequently, if not daily, so what's wild is you assuming I don't.

The impact that lack of training data has on the quality of the results is easily observable. Try getting them to maintain a Python codebase vs. e.g. an Elixir one. Not just generate short snippets of code, but actually assist in maintaining it. You'll constantly run into basic issues like invalid syntax, missing references, use of nonexistent APIs, etc., not to mention more functional problems like dead, useless, or unnecessarily complicated code. I run into these things with mainstream languages (Go, Python, Clojure), so I don't see how an esolang could possibly fair any better.

But then again, the definitions of "just fine" and "decent" are subjective, and these tools are inherently unreliable, which is where I suspect the large disconnect in our experiences comes from.

Re: I built a programming language using Claude Code

#116

Post by nineteen999 »

eatsyourtacos wrote: post #101
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…

100% same experience with Claude and Unreal Engine 5 over here. And as the game moves from "less scaffolding" towards "more code", Claude actually is getting better at one-shotting things than it ever was - probably due to there being a lot more examples in the codebase of how to handle things under different scenarious (world compositing, multiplayer etc etc).

Re: I built a programming language using Claude Code

#117

Post by wild_egg »

heavyset_go wrote: post #111
bobjordan wrote: post #58

I've been working on a large codebase that was already significant before LLM-assisted programming, leveraging code I’d written over a decade ago. Since integrating Claude and Codex, the system has evolved and grown massively. Realistically, there’s a lot in there now that I simply couldn't have built in a standard human lifetime without them. That said, the core value of the software wouldn't exist without a human a…

> I believe the author owns the language. Not according to the US Copyright Office. It is 100% LLM output, so it is not copyrighted, thus it's free for anyone to do anything with it and no claimed ownership or license can stop them.

Do you have a citation for that?

Re: I built a programming language using Claude Code

#118

Post by wizzwizz4 »

dmd wrote: post #106
ModernMech wrote: post #102

Earlier quoted context omitted.

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.

You may underestimate the weirdness of existing declarative data transformation languages. On a scale of 1 to 10, XSLT is about a 2 or 3.

Re: I built a programming language using Claude Code

#119

Post by heavyset_go »

wild_egg wrote: post #117
heavyset_go wrote: post #111

Earlier quoted context omitted.

> I believe the author owns the language. Not according to the US Copyright Office. It is 100% LLM output, so it is not copyrighted, thus it's free for anyone to do anything with it and no claimed ownership or license can stop them.

Do you have a citation for that?

Yes[1]. Copyright applies to human creations, not machine generated output.

It's possible to use AI output in human created content, and it can be copyrightable, and substantiative, transformative human-creative alteration of AI output is also copyrightable.

100% machine generated code is not copyrightable.

[1] https://newsroom.loc.gov/news/copyright-office-releases-part...

Re: I built a programming language using Claude Code

#120

Post by dmd »

wizzwizz4 wrote: post #118
dmd wrote: post #106

Earlier quoted context omitted.

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

You may underestimate the weirdness of existing declarative data transformation languages. On a scale of 1 to 10, XSLT is about a 2 or 3.

Mine's a weird, bad copy of Ab Initio's DML. https://www.google.com/search?q=ab+initio+dml+language
Post reply on HN