Follow the same LLM policy as rust-lang/rust - #7081
Conversation
Link to the same policy followed by rust-lang/rust.
This also follows what rust-lang/rust is doing.
|
This is great! Well, since I was asked, 😄 I just want to share one minor point of feedback on the policy itself. Let me know if I should share this elsewhere. I think the following section can plausibly be understood to carve out an allowance for fully autonomous LLM posting of experimental PRs. That is probably not the intent(?), but I think it is not a stretch to anticipate that sort of usage in today's climate.
I would reword this to make it specifically about code generation and possibly add a subpoint that using an LLM to autonomously post a PR is prohibited. I would also caveat here that the person posting should have a personal understanding of why the particular experiment may be of value before posting even though the code may not be thoroughly reviewed. |
I think that should probably adjust the wording on the actual Forge policy. Maybe worth discussing in #project-llm-policy? |
|
The majority of us are in agreement here so I'm going to go ahead and merge this. Thank you all for taking a look and voting 😁 |
Re-posted there, thanks. |
Linking to the same policy established by rust-lang/rust.
I want to make sure the majority of us agree with applying the policy: @rust-lang/rustfmt @rust-lang/rustfmt-contributors.
Contributing.mdtakes language from Add LLM policy mdBook#3195