There's a seedy underbelly of refactoring tools that work most of the time.
For example, grep and sed can perform function renaming. For a small codebase, this works well (you can test or eyeball the result).
Ideally we'd only use fully correct tools, but simplicity often wins.
Related Posts
... 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.
I'm never sure how to convert words with hyphens into SCREAMING_SNAKE_CASE. For example, should built-in function be BUILT_IN_FUNCTION or BUILTIN_FUNCTION?
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?