What is this doing on Hacker News.

Curious, has it been proven that typed languages are easier for LLMs to work with as they dont have to infer types?

Do they infer anything? Correct me if I'm wrong but having the types right there in the source for training data just means more context.

I'm not aware of any rigorous study on it, but my personal anecdote is that I don't even bother with Claude Code or similar unless the language is Haskell, the deployment is Nix, the config is Dhall, and I did property tests. Once you set it up like that you just pour money in until its too much money or its stuck, and thats how far LLMs can go now.

I used to yell at Claude Code when it tried to con me with mocks to get the TODO scratched off, now I laugh at the little bastard when it tries to pull a fast one on -Werror.

Nice try Claude Code, but around here we come to work or we call in sick, so what's it going to be?

There are researches backing some sort of "typed language is better for LLM". Like https://arxiv.org/abs/2504.09246, Type-Constrained Code Generation with Language Models, where LLM's output is constrainted by type checkers.

Also https://arxiv.org/abs/2406.03283, Enhancing Repository-Level Code Generation with Integrated Contextual Information, uses staic analyzers to produce prompts with more context info.

Yet, the argument does directly translate to the conclusion that typed language is rigorously better for LLM without external tools. However, typed language and its static analysis information do seem to help LLM.

Dynamically typed languages are far from "untyped". Though they may well require more effort to analyze from scratch without making assumptions, there is nothing inherently preventing type-constrained code generation of the kind the first paper proposes even without static typing.

A system doing type-constrained code-generation can certainly implement its own static type system by tracking a type for variables it uses and ensuring those constraints are maintained without actually emitting the type checks and annotations.

Similarly, static analyzers can be - and have been - applied to dynamically typed languages, though if these projects have been written using typical patterns of dynamic languages the types can get very complex, so this tends to work best with code-bases written for it.

this is just the kind of sass I needed today. cheers!

First poster could have approach better too. Like "Cool site! I think I may see an error on one item?". Instead of going right to a 'wrong' angle as if all the data should be discredited. I get highly triggered by this too.

this overly positive attitude triggers a bunch of people too. wrong data should just be called out, especially if that's your main selling point.

Nobody disagrees with that. But tact exists.

Interesting! I never heard of Cyclone before. Looks like another Bell Labs contribution.

Yep I program in some niche languages like Pike, Snobol4, Unicon. Vibe coding is out of the question for these languages. Forced to use my brain!

You could always feed it some documentation and example programs. I did it with a niche language and it worked out really well, with Claude. Around 8 months ago.

Yet in Gates' recently released memoir, if you do a ctrl+f for Kildall there are zero results. Unsure how Gates, as a programmer and business founder , could write a memoir without a single blurb for Gary.

The bio is in three parts. If he mentions Gary it will be in part 2.

Interesting, thx wasn't aware!

Personally I find a good linter like SonarLint can actually teach you a lot.

Thanks for sharing this. It's crazy to see videos like this and think how these people had no idea what was coming in the future.

Thanks this is a great recommendation - runs perfect in Wine. There definitely seems to be a habit with developers making calculators that still fall into a 70s form factor. This is a great departure.

I really do want to clone that thing, except cross platform, and enhanced with 64 bit native math. I want the same exact REPL calculator and function library running natively and starting instantly from a no-install binary on every platform I might ever touch.

Oh, and make it open source, so that people that know more than I about all things math can contribute. If you hadn't noticed, SpeQ Math is not open source.

There's always a comment like this I find. Some extra layer of data people want to see that explains the first layer, and it never ends - the data on data. Sometimes we just want to know the damn burrito prices and don't care about the excuses.

If you want to know the burrito price, you open the app/website and look at the burrito price... you don't go to a "Taconomics" website comparing taco prices across a continent. As it stands, there are a number of uncontrolled variables that mean this is not an effective analysis of "How economical is your local Taco Bell?"

> you don't go to a "Taconomics" website comparing taco prices across a continent

but that's what people do, in aggregate. It's why manufacturing all went to china in the last 2 decades.

Maybe you just want to find the cheapest branch in a 10 mile radius.

Yah but if you want to click around on a neat lil web page this is great.

Shift-click to zoom out.

It’s hard to compare prices for 10 nearby Taco Bells in the Taco Bell app. This site makes it quite easy.