alt Hacker NewsI have a colleague who vibes the shit out of his part, and it results in large commits that take a lot of time to understand, and that makes cooperation practically impossible. LLMs are not team players.
Replies
That's a you guys problem. Maybe one or both of you.
Have you thought about pair programming together with the AI?
My LLM outputs are intentional, in my style, and tightly reviewed by myself.
I'm also emitting Rust, which I've found to be the very best language to work with in AI. The AST and language design is focused around control flow and error handling. The borrow checker, sum types, filtering and mapping makes it such that good design is idiomatic.
There's a lot JavaScript, Python, PHP, and Java in the world. A lot of it isn't great. The architectures and styles are wildly varied too. Rust doesn't have that problem. The training data is really solid and idiomatic.
I get much different results than others when using these tools. Turns out there is some skill in wielding them, and knowing the domain in which you do.