chore: add human communication rule to CONTRIBUTING.md (#32089)

This commit is contained in:
bo0tzz
2026-10-05 14:59:58 +02:00
committed by GitHub
parent 69f06a29ca
commit f938b2faa7
+3 -2
View File
@@ -25,11 +25,12 @@ If you find bugs or other problems while working on something, we appreciate tha
We ask you not to open PRs generated with an LLM. We find that code generated like this tends to need a large amount of back-and-forth, which is a very inefficient use of our time. Even a one line change can have significant impact. We cannot have any confidence in an LLM, so if it's non-trivial for us to verify it works and you don't show that you fully understand all implications of the change, reviewing the PR is not worth our time. If we want LLM-generated code, it's much faster for us to use an LLM ourselves than to go through an intermediary via a pull request.
If you use an LLM to translate a PR description or title, that is fine. Please make sure however that you stick to the PR template and that the text is written concisely.
Communication should be between humans. We want to hear from you in your own words. Posting descriptions or comments that have been generated by an LLM is not acceptable, and may be grounds for us to close a thread without further comment.
If you use an LLM to translate a PR description or title, that is fine, although we recommend using purpose-built machine translation tools instead. Please make sure either way that you stick to the PR template and that the text is written concisely.
LLMs must not be used to fix GitHub issues labelled good first issue. These issues are generally not urgent, and are intended to be learning opportunities for new contributors to get familiar with the codebase. Whether you are a newcomer or not, fully automating the process of fixing this issue squanders the learning opportunity and doesn’t add much value to the project. Using LLMs to fix issues labelled as “good first issue” is forbidden, and those PRs will be closed automatically.
Misrepresenting LLM use, contribution farming (automated low-effort PRs), or repeatedly hitting auto-close rules may be grounds for a block at maintainer discretion.
Misrepresenting LLM use, contribution farming (automated low-effort PRs, generated discussion answers), or repeatedly hitting auto-close rules may be grounds for a block at maintainer discretion.
## Feature freezes