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

Which programming languages are most token-efficient?

martinalderson.com

Post reply on HN
Print view View original

21–30 of 96 posts

Re: Which programming languages are most token-efficient?

#21

Post by solomonb »

I'm biased by my preferred style of programming languages but I think that pure statically typed functional languages are incredibly well suited for LLMs. The purity gives you referential transparency and static analysis powers that the LLM can leverage to stay correctly on task.

The high level declarative nature and type driven development style of languages like Haskell also make it really easy for an experienced developer to review and validate the output of the LLM.

Early on in the GPT era I had really bad experiences generating Haskell code with LLMs but I think that the combination of improved models, increased context size, and agentic tooling has allowed LLMs to really take advantage of functional programming.

Re: Which programming languages are most token-efficient?

#22

Post by eru »

solomonb wrote: post #21

I'm biased by my preferred style of programming languages but I think that pure statically typed functional languages are incredibly well suited for LLMs. The purity gives you referential transparency and static analysis powers that the LLM can leverage to stay correctly on task. The high level declarative nature and type driven development style of languages like Haskell also make it really easy for an experienced d…

I'm inclined to agree with you in principle, but there's much, much less Haskell examples in their training corpus than for JavaScript or Python.

Re: Which programming languages are most token-efficient?

#24

Post by eru »

muyuu wrote: post #20
janalsncm wrote: post #19

This is kind of just a measurement of how representative a language is in the distribution of the tokenizer training. You could have a single token equal to “public static void main”.

You could, but you wouldn't when those keywords can all change in equivalent contexts.

What do you mean?

`public` might have a token by itself, even though you can have `pub` occurring in other contexts, too.

Re: Which programming languages are most token-efficient?

#25

Post by kstrauser »

eru wrote: post #22
solomonb wrote: post #21

I'm biased by my preferred style of programming languages but I think that pure statically typed functional languages are incredibly well suited for LLMs. The purity gives you referential transparency and static analysis powers that the LLM can leverage to stay correctly on task. The high level declarative nature and type driven development style of languages like Haskell also make it really easy for an experienced d…

I'm inclined to agree with you in principle, but there's much, much less Haskell examples in their training corpus than for JavaScript or Python.

And yet the models I've used have been great with Rust, which pales in lines of code to JavaScript (or Python or PHP or Perl or C or C++).

Re: Which programming languages are most token-efficient?

#26

Post by eru »

kstrauser wrote: post #25
eru wrote: post #22

Earlier quoted context omitted.

I'm inclined to agree with you in principle, but there's much, much less Haskell examples in their training corpus than for JavaScript or Python.

And yet the models I've used have been great with Rust, which pales in lines of code to JavaScript (or Python or PHP or Perl or C or C++).

I've also had decent experiences with Rust recently. I haven't done enough Haskell programming in the AI era to really say.

But it could be that different programming languages are a bit like different human languages for these models: when they have more than some threshold of training data, they can express their general problem solving skills in any of them? And then it's down to how much the compiler and linters can yell at them.

For Rust, I regularly tell them to make `clippy::pedantic` happy (and tell me explicitly when they think that the best way to do that is via an explicit ignore annotation in the code to disable a certain warning for a specific line).

Pedantic clippy is usually too.. pedantic for humans, but it seems to work reasonably well with the agents. You can also add clippy::cargo which ain't included in clippy::pedantic.

Re: Which programming languages are most token-efficient?

#27

Post by solomonb »

eru wrote: post #22
solomonb wrote: post #21

I'm biased by my preferred style of programming languages but I think that pure statically typed functional languages are incredibly well suited for LLMs. The purity gives you referential transparency and static analysis powers that the LLM can leverage to stay correctly on task. The high level declarative nature and type driven development style of languages like Haskell also make it really easy for an experienced d…

I'm inclined to agree with you in principle, but there's much, much less Haskell examples in their training corpus than for JavaScript or Python.

You are right that there is significantly more Javascript in the training data, but I can say from experience that I'm a little shocked at how well opus 4.5 has been for me writing Haskell. I'm fairly particular and I end up re-writing a lot of code for style reasons but it can often one shot an acceptable solution that is mostly inline with the rest of the code base.

Re: Which programming languages are most token-efficient?

#28

Post by solomonb »

eru wrote: post #26
kstrauser wrote: post #25

Earlier quoted context omitted.

And yet the models I've used have been great with Rust, which pales in lines of code to JavaScript (or Python or PHP or Perl or C or C++).

I've also had decent experiences with Rust recently. I haven't done enough Haskell programming in the AI era to really say. But it could be that different programming languages are a bit like different human languages for these models: when they have more than some threshold of training data, they can express their general problem solving skills in any of them? And then it's down to how much the compiler and linters…

> But it could be that different programming languages are a bit like different human languages for these models: when they have more than some threshold of training data, they can express their general problem solving skills in any of them? And then it's down to how much the compiler and linters can yell at them.

I think this is exactly right.

Re: Which programming languages are most token-efficient?

#29

Post by awesome_dude »

I'm finding that I have to share more and more code to ensure that various standards are being kept.

For example I shared some Model code with Claude and Gemini (both via web interfaces) and they both tried to put Controller code into the Model, despite me multiple times telling them that the code wasn't wanted nor needed in there.

I had to (eventually) share the entire project with the models (despite them having been working with the code all along) before they would comply with my request (whilst also congratulating me on my far superior architecture..)

That costs more tokens for each problem than just saying "her look at this section and work toward this goal"

Re: Which programming languages are most token-efficient?

#30

Post by moelf »

janalsncm wrote: post #19

This is kind of just a measurement of how representative a language is in the distribution of the tokenizer training. You could have a single token equal to “public static void main”.

the most efficient languages are pretty unpopular, so this argument makes them even more efficient in reality?...
Post reply on HN