To quote from another thread about this program:

Claude directly has over 1100000 lines of direct code contribution. It has pretty much the same amount of code committed directly as the creator has.

His entire coding history before Claude consisted of changing readmes or searching and replacing project name text or modifying a dead link to his own link.

Suddenly in 4 months, without ever producing actual code before, he becomes a very competent coder enough to tackle mCAD, a notoriously difficult coding task that takes many many years with teams to make meaningful progress on?

That is vibe coding.

And his co-contributer "gianlucafiore" is exactly the same story. Has literally only made issues until LLM coding got released and then late 2025 (December) switched to making commits that he badly copied from an LLM such that some of the commits are literally one full line (as direct in-file working of the LLM wasn't as accessible then)

That is vibe coding.

So the top 3 contributes are

1. An LLM
2. Someone that only has committed any code via an LLM
3. Someone who has only made issues before beginning with an LLM and submits clearly generated code

There is likely no human-made code in the entire project besides changing a couple links.

https://lemmy.ml/comment/27294909

If a program written almost entirely by Claude under somebody who has not previously demonstrated any actual competency in this domain isn't vibe coding, I really don't know what is.

Elsewhere in this thread, I can't seem to get the link on my phone:

Rulues was not readed, but i do know most people do not want AI code. So i did know what the issue you point just from your comment

I will not hold post about great FOSS project becuse of AI code.

Thanks.

They admitted that they chose not to read the community rules and appear to have assumed that they were not allowed to post about AI projects, yet chose to post anyway.

Also, translation tools are widely available on the Internet to the extent that they're built into most browsers at this point. While they're obviously not as good as actually being fluent, they work fine for getting the point across. I've used them to read non-English sites with success, even if I maybe missed some of the subtleties of the original text.

It would be far less frustrating if they had at least attempted to read the rules and made a mistake in trying to follow them.