←back to thread

Introducing tmux-rs

(richardscollin.github.io)
857 points Jtsummers | 1 comments | 03 Jul 25 15:03 UTC | HN request time: 0.208s | source
Show context
parhamn ◴[03 Jul 25 16:37 UTC] 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 #
TechDebtDevin ◴[03 Jul 25 16:41 UTC] 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 #
parhamn ◴[03 Jul 25 17:08 UTC] 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 #
1. TechDebtDevin ◴[03 Jul 25 17:23 UTC] No.44457281[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.