←back to thread

Introducing tmux-rs

(richardscollin.github.io)
857 points Jtsummers | 8 comments | | HN request time: 0.425s | source | bottom
1. parhamn ◴[] No.44456815[source]
Interesting, this article and the comments make no mention of LLMs for the initial translation. Really surprising given that would be the first thing I'd reach for for a translation/porting task (though verification could get tricky).

Now I really wonder how a good model like Sonnet 4 would have performed.

replies(5): >>44456868 #>>44456878 #>>44456881 #>>44457002 #>>44457317 #
2. TechDebtDevin ◴[] No.44456868[source]
It wouldnt have gotten 2% finishd. It wouldn't have compiled. Its a waste of time to even consider.
replies(1): >>44457142 #
3. Jtsummers ◴[] No.44456881[source]
> Interesting, this article and the comments make no mention of LLMs.

https://richardscollin.github.io/tmux-rs/#ai-tools

replies(1): >>44457125 #
4. smj-edison ◴[] No.44457002[source]
Check the bottom :)

> I did start trying out Cursor towards the end of the development process. I ended up stopping using it though because I felt like it didn’t actually increase my speed. It only saved me from finger pain. That’s because when using cursor to translate the code it would still occasionally insert bugs, just like me. So, I spent as much time reviewing the generated code as it would have taken me to write it myself. The only thing it saved was my hands. Doing this large amount of refactoring is really hard on your fingers.

5. parhamn ◴[] No.44457125[source]
Using Cursor to refactor the unsafe code is quite a different task than using an LLM to translate into safe rust. I was just curious how it would perform.
6. parhamn ◴[] No.44457142[source]
> It wouldnt have gotten 2% finishd

What do you mean by this? I'd assume the process would be very very incremental. One function + accompany tests at a time, verify and continue and keep moving up the tree.

It's an interesting problem because I imagine in the future lots of things will be ported like this.

replies(1): >>44457281 #
7. TechDebtDevin ◴[] No.44457281{3}[source]
You've been duped my friend.

-edit Good luck reading 100k lines of Claude generated Rust that you know nothing about lol. LLMS are not the tool for this.

8. keybored ◴[] No.44457317[source]
The people demand the AI angle.