Add AI policy - #18187
Merged
Merged
Add AI policy#18187
Conversation
Collaborator
|
Build successful! You can test your changes in the REPL here: https://babeljs.io/repl/build/62017 |
nicolo-ribaudo
added
the
PR: Docs 馃摑
|
commit: |
Co-authored-by: Hu谩ng J霉nli脿ng <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #1, Fixes #2The increasing number of entirely LLM-generated PRs, with no human interaction, is making it less and less fun for me to work on Babel.
This policy is a first attempt at defining what is and is not ok. It is very permissinve, as I'm an LLM user myself: it does not take any stance on code generation, and instead it focuses solely on what is meant to be human communication. It allows tools like AI reviews, since those are always explicitly marked as such.
As I know that people that currently are just telling their LLM "please find a bug in a popular project and submit a PR to fix it" will completely ignore this policy, I am also trying to add some sort of honeypot so that these sort of tools will automatically disclose themselves. Whenever an LLM follows the AGENTS.md instructions to open a pull request, we should just close it without even reading the code, and ideally block that account.