Jdstanhope

This is exactly the case for "porting" Bash to Rust. There is a huge amount of existing tests that can be leverage and when in doubt you can run the same code in bash and Huck and compare the result and then fix the issue.

As few people have mentioned you have to guide the AI to clean up stuff, it doesn't seem to choose that on its own. If prompted it can come up with a lot of things to clean up.

Please check out the code and let me know what you think. I have driven a few large refactorings that I don't think Claude would have done on its own. The two big ones were related to handling tokenization and parsing (Claude's original code had circular dependencies and would scan forward in the lever instead of using the parser to determine structure) and the second was for using subshells for command substitution instead of inline and having dual FD and buffer handling.

I was going to say that it's pretty much exactly like working with an experienced software engineer ... except it never seems to take a step back and look at the bigger picture. It will happily fix the same class of bugs over and over without realizing a bigger change is required.

Working on analyticmind.io to help small teams with the decision making process. I feel like I've lived through a few too many decisions that didn't make sense to me or the rest of the organization.

Is there an example of something built with this other than itself?