They don't though, very few people were anti AI in the early days. Open source projects were largely initially very interested in LLM usage, and generally had a pro AI contribution policy. This changed when it did not help their lives

Eg if you check out Godot, initially they were cool with LLM code, and then had to clamp down on it because it was not leading to anything good

Scaling AI use in highly-collaborative environments, which open source projects are, is very challenging. I totally understand the apprehensiveness around it.

How is it challenging for open source projects? You just write a PR, and try to get it to meet the maintainer's quality bar. That's exactly how all code is written in any environment - you do code review and refine a PR until its good enough to be merged

With AI and how a lot of people use it, the quantity of written PRs goes up, but the quality goes down, and the maintainers of the project, who are often volunteers, now have to deal with this in addition to the standard work they've been doing before.

This doesn't seem to match the claims of 10x productivity that are being levied though. In fact it seems like the overall productivity is lower

Just my experience, but the relatively few fully AI-generated merge requests we've received that were "big features" were all really bad.

For instance, we had one person submit a merge request to convert the entire GIMP codebase into Python, and it was just tons of files with stubcode implementations. Another person submitted a fix for our OpenEXR plug-in to load YCbCr images, and when I reviewed it, they'd "imported" a non-existent version of the library that had an imaginary "OpenYCbCrOpenEXR ()" function. :)