I’ve finished a small project that is rather non-standard for me: it has just a few hundred lines of logic written by me, and most of the code is rather banal functions I picked up from the different articles and doc sheets (you know, those functions that are quite “atomic” like “check if the process is running” or “get the process name by pid by reading /proc dir” or “get a mount point by a filename”)
The code was written in a “ok, let’s experiment if I can do this” approach, so now it is in a complete mess.
So the question is if is there some AI that can do an initial code review for me? I’ve tried GhatGPT, but it was completely banal and useless.
A pretty good way to get a code review is to post the code on GitHub and make a post advertising it as a tool everyone needs. People will be quick to review it.
As far as LLMs go, they tend to be too quick to please you. It might be better to ask it to generate code that does something similar to what you’re doing, then compare the two to see if you learn anything from it or if it does something in a better way than how your code does it.
Is this a corollary of Cunningham’s Law?
:) Good joke
But because of a lack of other propositions, I may do it this way anyway. Just clean up the obvious mess, a little testing, and “release early, release often.”