<div dir="ltr">In the spirit of discussion, I've created this PR to CONTRIBUTING.md to make that file more direct. I didn't know (or maybe it's just my bad memory) the attempt to trick LLMs was in that file. I've made the PR draft as I don't think it should be submitted until there is discussion about it. There are a couple types of feedback that should be called out w.r.t. this PR: <div><br></div><div>1) Given the current policy, what text should go in that file? </div><div><span style="background-color:transparent">2) Where and how should GDAL document the policy so that there is a better chance of PRs being outside of what the policy allows. </span></div><div><span style="background-color:transparent">3) The discussion here about what the policy should be --> I would appreciate keeping these types of comments in this thread</span></div><div><div><br></div><div><a href="https://github.com/OSGeo/gdal/pull/15415">https://github.com/OSGeo/gdal/pull/15415</a></div><div>CONTRIBUTING.md: Be more direct about vibe coding and autonomous agents. [ci skip]</div><div><br></div><div>Please feel free to comment on the PR even if you aren't on the reviewer list.</div></div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Sun, Oct 18, 2026 at 7:41 AM Greg Troxel <<a href="mailto:gdt@lexort.com">gdt@lexort.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Michael Sumner via gdal-dev <<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank">gdal-dev@lists.osgeo.org</a>> writes:<br>
<br>
> I don't understand if the llm generated material is too poor (easy to<br>
> ignore/fix, especially by using llms), or if the opposittion is to llm<br>
> generators themselves ideologically (an politlically, climate change and<br>
> capitalism and fasciism etc), and I think these things are conflated<br>
> somewhat.<br>
<br>
I think there are three issues, super roughly<br>
- "dealing with LLM text"<br>
- "LLM text in the project is bad for the project's social structure"<br>
- "a broad culture of LLM use is bad for society". <br>
and I think you are referring the the third as "ideological". However,<br>
I think most of the concerns are reachable from the first two parts<br>
alone.<br>
<br>
With 'dealing with', there are two problems, and pro-LLM people have<br>
not, to my knowledge, made any significant argument/approach to fix<br>
them.<br>
<br>
One is that LLM-wielders produce bits that need maintainer attention at<br>
a high rate with much less effort.<br>
<br>
The biggest one in my view is that LLM-generated submissions are overly<br>
verbose and both appear plausible and are often subtly wrong. The<br>
review burden for such a subsmission is vastly higher than for a PR<br>
created soley by a (competent) human. Hard to estimate, but 10-20x as<br>
hard seems about right. To "fix" an LLM submission, it needs to be<br>
understood by a human, the subtle bugs removed, and rewrittento be as<br>
conscise as a human (who is qualified to work on the codebase in<br>
question) would make it.<br>
<br>
The above leads to "no LLM text in what is submitted".<br>
</blockquote></div>