Hacker News Reader

Comment by te_chris | Hacker News Reader

This, 100%. I’ve rewritten some hydrology code in rust using codex sol to first a) profile and create comprehensive tests of the python, b) create full benchmark suites, c) create full scientific benchmark suites, then d) port to rust using a few different techniques.

It works, it’s at least 5x faster, sometimes much more, and memory use is like 10x less and even less in cases where lots of map tiles are involved.

This shit rules.

What I’m wondering now is can we reliably evolve python and have codex act as an extremely unreliable transpiler to the rust.

View on HN

> What I’m wondering now is can we reliably evolve python and have codex act as an extremely unreliable transpiler to the rust.

Why you even start with Python at this point? Just write the Rust version straight up instead of porting things?

Personally I used to use dynamic languages for most things, because development and maintenance is so much faster and easier, particularly for larger projects (granted you know how to work with those sort of languages), but now when the LLM writes most of the code, I'm able to work as fast with Rust as with I used to be able to do with Clojure or other dynamic languages.

Because it’s a port of a scientific process and that’s what the scientists work in.

Ah, sorry, I didn't understood you weren't the original author of the program you're porting :) Cheers for the additional context.

What happens when LLMs will become either too expensive or unavailable?

It's becoming increasingly evident this is not how things are going to shake out. Even without frontier models, running Qwen 3.8 27B has demonstrated for me and others a "good enough" competency at general programming. Additionally, large open weight models have proven themselves as viable alternatives and we're still in the early years of dedicated hardware

I guess lots of Rust developers will find a lot of employment?

I mean what happens with network engineers when the biggest network of them all goes down?

This AI thing is not at all similar to networking. It is up to a point, but in fact it isn’t.

I'm not saying developing with LLMs is the same as network engineering. The point being that almost all professions have some point of failures, that sometimes when we work, that single point is broken, yet we need to continue working anyway. Same goes for every professional almost.

Reply on news.ycombinator.com