In many respects I feel an LLM benefits from a monorepo. I've vibe coded a bunch of helper CLIs recently and end up repeating the same preferences for all of them.
I want all my CLIs to use clippy, parse arguments with clap, etc. They're distinct tools in distinct repos though.
Related Posts
It's always seemed odd to me that the Rust stdlib is so lean (no random numbers, regex, HTTP) yet clippy is so big (correctness, performance, style preferences, even 'too many arguments').
Maybe it's because cargo is mature but clippy doesn't have an extension ecosystem?
One interesting consequence of the rise of LLMs: there's more demand for tools that handle untrusted input.
Arbitrary HTML+JS can be safely run in a browser. Lean can check an arbitrary proof.
These work really well with an LLM that can be wrong, but sometimes gives exactly what you want. Are there other tools in this family?
... and my third refactoring with Cursor changed some function calls that I didn't want it to modify. Subtle.
I've had the most success with AI coding tools when I know exactly what I want the output to look like.