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!
That’s awesome.
A way to import a list from ontanimum would be a nice feature.
I already use it. It’s GLORIOUS. I’m free from a lot of stress, although not totally free of it. It’s better, at least.
neat.
deleted by creator
Holy smokes… Freaking awesome!
Of course… Programming is normally a human art…
Programming is of human for human to automate machines…
It is as any of people to be left in the infinite history, to learn from and improve accountably, too…Thank you very much for the marvel… art you do…
There’s the following book I recall on the subject that is an essential for every accountable, astute, and respectful developer, artist, I believe.
…a computer language is not just a way of getting a computer to perform operations but rather that it is a novel formal medium for expressing ideas about methodology. Thus, programs must be written for people to read, and only incidentally for machines to execute.
…the essential material to be addressed by a subject at this level is not the syntax of particular programming-language constructs, nor clever algorithms for computing particular functions efficiently, nor even the mathematical analysis of algorithms and the foundations of computing, but rather the techniques used to control the intellectual complexity of large software systems.
…Our traffic with the subject matter of this book involves us with three foci of phenomena: the human mind, collections of computer programs, and the computer.
Every computer program is a model, hatched in the mind, of a real or mental process. These processes, arising from human experience and thought, are huge in number, intricate in detail, and at any time only partially understood.
They are modeled to our permanent satisfaction rarely by our computer programs. Thus even though our programs are carefully handcrafted discrete collections of symbols, mosaics of interlocking functions, they continually evolve: we change them as our perception of the model deepens, enlarges, generalizes until the model ultimately attains a metastable place within still another model with which we struggle.
The source of the exhilaration associated with computer programming is the continual unfolding within the mind and on the computer of mechanisms expressed as programs and the explosion of perception they generate.
If art interprets our dreams, the computer executes them in the guise of programs!
~ Source: “Structure and Interpretation of Computer Programs” (SICP; or “Wizard Book”) by Harold Abelson, Gerald Jay Sussman, Julie Sussman
Nobody thinks the output of that thing isn’t itself slop?
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.
I mean, realistically speaking that’s what I would do manually. So it’s just making my life easier by automating it.
I don’t expect it to analyse individual files.
Exactly. It can produce false negatives, but by nature of Git’s blaming everyone for every change, it makes it (probably) won’t produce false positives. It’s a give and take in that instance. Do you do a witch hunt and try and track down every LLM generated repo and get some legit repos caught up in an imperfect process. Or do you use actionable evidence to make an informed decision?
In my opinion, witch hunts are really quite unhealthy for society. When possible, I choose projects with blanket no-AI statements, but when not, this expedites the process of choosing between alternatives. Rustic has less AI generated code than Restic, let’s do that. Kitty has hundreds of AI generated commits, let’s delete that immediately.
Yeah, and at least the site shows you the content of the files.
I think there can be a reasonable way for it to get false positives, and it’s when a repo has an
AGENTS.md/<insert-llm-here>.mdfile, or a.skills/,cursor/ortabby/folder, for example, but they’re adversarial (for example, theres awful.system’s AAA-NO-SLOP.md).
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 ;)
https://www.youtube.com/watch?v=qKpik3zS_-o
“She cared for me and put me on this earth Oh, the pain of just a simple birth Right now, I find that she has left me dumb and blind Poisoned, twisted, and destroyed my mind She taught me things that simply were not true She taught me hate for race, that’s why I hate you!”
also crypto bros, ai users, duopoly voters, amazon shoppers…
There’s a self-scan:
- https://slopscore.ava.pet/repo/https://U:T@codeberg.org/polyphony/repo-slopscoreFrom the first glance, it works most of the times better than nothing.
