[MapServer-dev] LLM tool policy for MapServer?

[Seth G]

Hi Even, all,

+1 on using the GDAL policy (with the updates from Steve). I also think we should allow LLMs to be used to review code in a PR which I'm not sure is covered in:

"LLMs may only be used as an improved auto-completion mechanism, or for repeated tasks (mechanical refactoring) that could potentially be completed with a deterministic algorithm."

In the case of https://github.com/MapServer/MapServer/pull/7535 I think this could be acceptable under the new policy? The author has declared use of AI, responded to questions, and knows enough about the code they are adding to create a real-world example and documentation. Having said that I don't know anything about the algorithm, and I'm not able to scan through the C code and tell if it is nonsense or not. I'm happy to test the PR locally though. 

I think we should continue to encourage MapServer users / power-users to contribute, whilst closing any drive-by LLM PRs, or PRs from "entities" with no interest or connection to the project. 

Seth


--
web:https://geographika.net & https://mapserverstudio.net
mastodon: @geographika at mastodon.social

On Mon, Jun 22, 2026, at 2:09 AM, Even Rouault via MapServer-dev wrote:
> Hi,
>
> It would have been surprised if we'd have been spared by that plague. 
> See https://github.com/MapServer/MapServer/pull/7535
>
> Adopt https://gdal.org/en/stable/community/ai_tool_policy.html with 
> s/GDAL/MapServer and minus the Mitigation paragraph since we don't have 
> project-wide funding vehicle ?
>
> Even
>
> -- 
> http://www.spatialys.com
> My software is free, but my time generally not.
> LLMs contribute to global warming and brain rot
>
> _______________________________________________
> MapServer-dev mailing list
> MapServer-dev at lists.osgeo.org
> https://lists.osgeo.org/mailman/listinfo/mapserver-dev