A simple tool to figure out just how much LLM generated code has been used in a project. Obviously not perfect, but it automates the task of going through commits for “co-authored by” statements and other signs. In the off chance you don’t want to use the CLI, there’s also a web app!
Nobody thinks the output of that thing isn’t itself slop?
There’s a self-scan:
- https://slopscore.ava.pet/repo/https://U:T@codeberg.org/polyphony/repo-slopscore
From the first glance, it works most of the times better than nothing.
Looks like a very simple heuristic analysis looking for certain files/commiters. In fact it states in the README that it doesn’t go through all the files so it is probably more reliable than those AI “detectors” that also rely on AI.
Its just reading the commit history. It doesnt read the files at all. So it only finds overt slop, anyone who does their commits manually would pass completely.
Edit: https://slopscore.ava.pet/repo/https%3A%2F%2Fgithub.com%2Fcameroncros%2Fedgy-table
This repo is 100% slop (its mine, I know what I did), and it gets marked clean.
It also looks for certain files like AGENTS.md which your repo doesn’t appear to have.
*CameronSlop
Ha, I still hand write most of my code, i used it for that repo to try out local LLMs. Know thy enemy.
I did hand-polish that code as well, just the initial pass was slopped together.
I do know my enemy ;)