alt Hacker NewsAs much as it's true that a novice will generally use AI to build a sloppy mess, I've also had success unsloppifying through some careful prompting.
Replies
I wish I had current-day AI (and a big credit card) for my previous job, they had a big legacy mess made by a productive but not very good developer, but my job was to rebuild it.
If I had AI tooling at the time I'd probably be more inclined to have it both refactor / optimize the existing application, add automated regression tests etc, and use it to extract all of the features and requirements for it for a potential rebuild.
But honestly I think if that application was properly designed and factored (instead of nesting JS in HTML in strings in JS or concatenating XML from query results only for it to be converted to JSON taking up 50% of response time) its lifetime could've been extended, especially if it was then containerized into a HHVM or similar php optimizer.
But, hindsight.
Any tips on how you unsloppify things? Are you using things like claude.md/copilot.md (or similar) to guide better, do you have specific types of prompts that you run, or do you adjust your code review practices in some way to more efficiently review lots of slop code?
One of my particular complaints is how code-gen LLMs tend to re-create the same code over and over again. Case in point, a use-case where a team name is generated from a list of team member names. The LLM re-generates this code in-line every time it needs to display the team name, rather than simply writing and reusing a utility style function.
I know I need to fix this. At this point I'm planning to just prompt something like "please list all the places where team names are generated/calculated", plus manually search through the codebase, then perform the abstraction myself. But I'm unsure how to prevent this (both this example, and other cases that could benefit from similar utility functions) continuing to occur in the future.
Absolutely. I really don't think the future will be humans reading and picking apart an AI-generated codebase, there will be tech debt agents or whatever running overnight.
or linters
Yeah, v1 is sloppy, then I tell the LLM to clean it up. Every 1 prompt of building tends to require 1-5 prompts of clean up. Simple, fast, clean good code.
The chasm between "Software Developer" and "Software Engineer" is getting wider. Articles like this and the comments under it give away who is an Engineer and who is just a coder.