alt Hacker NewsDeveloped by Jordan Hubbard of NVIDIA (and FreeBSD).
My understanding/experience is that LLM performance in a language scales with how well the language is represented in the training data.
From that assumption, we might expect LLMs to actually do better with an existing language for which more training code is available, even if that language is more complex and seems like it should be “harder” to understand.
Replies
A lot of this depends on your workflow. A language with great typing, type checking and good compiler errors will work better in a loop than one with a large surface overhead and syntax complexity, even if it's well represented. This is the instinct behind, e.g. https://github.com/toon-format/toon, a json alternative format. They test LLM accuracy with the format against JSON, (and are generally slightly ahead of JSON).
Additionally just the ability to put an entire language into context for an LLM - a single document explaining everything - is also likely to close the gap.
I was skimming some nano files and while I can't say I loved how it looked, it did look extremely clear. Likely a benefit.
Blackpill is that, for this reason, the mainstream languages we have today will be the final (human-designed) languages to be relevant on a global scale.
Eventually AIs will create their own languages. And humans will, of course, continue designing hobbyist languages for fun. But in terms of influence, there will not be another human language that takes the programming world by storm. There simply is not enough time left.
> My understanding/experience is that LLM performance in a language scales with how well the language is represented in the training data.
This isn't really true. LLMs understand grammars really really well. If you have a grammar for your language the LLM can one-shot perfect code.
What they don't know is the tooling around the language. But again, this is pretty easily fixed - they are good at exploring cli tools.
I mostly agree, and I think a combination of good representation and tooling that lets it self-correct quickly will do better than new language in the short term.
In the long term I expect it won't matter - already GPT3.5 was able to reason about the basic semantics of programs in languages "synthesised" zero-shot in context by just describing it as a combination of existing languages (e.g. "Ruby with INTERCAL's COME FROM") or by providing a grammar (e.g. simple EBNF plus some notes on new/different constructs) reasonably well and could explain what a program written in a franken-language it had not seen before was likely to do.
I think long before there is enough training data for a new language to be on equal grounds in that respect, we should expect the models to be good enough at this that you could just provide a terse language spec.
But at the same time, I'd expect the same improvement to future models to be good enough at working with existing languages that it's pointless to tailor languages to LLMs.
It's not just how well the language is represented. Obscure-ish APIs can trip up LLMs. I've been using Antigravity for a Flutter project that uses ATProto. Gemini is very strong at Dart coding, which makes picking up my 17th managed language a breeze. It's also very good at Flutter UI elements. It was noticeably less good at ATProto and its Dart API.
The characteristics of failures have been interesting: As I anticipated it might be, an over ambitious refactoring was a train wreck, easily reverted. But something as simple as regenerating Android launcher icons in a Flutter project was a total blind spot. I had to Google that like some kind of naked savage running through the jungle.
I think it's depressingly true of any novel language/framework at this point, especially if they have novel ideas.
I wonder if there is a way to create a sort of 'transpilation' layer to a new language like this for existing languages, so that it would be able to use all of the available training from other languages. Something that's like AST to AST. Though I wonder if it would only work in the initial training or fine-tuning stage.
Claude is very good with Elm, which there should be quite little training data.
Not my experience, honestly. With a good code base for it to explore and good tooling, and a really good prompt I've had excellent results with frankly quite obscure things, including homegrown languages.
As others said, the key is feedback and prompting. In a model with long context, it'll figure it out.
I don’t think that assumption holds. For example, only recently have agents started getting Rust code right on the first try, but that hasn’t mattered in the past because the rust compiler and linters give such good feedback that it immediately fixes whatever goof it made.
This does fill up context a little faster, (1) not as much as debugging the problem would have in a dynamic language, and (2) better agentic frameworks are coming that “rewrite” context history for dynamic on the fly context compression.