Related:

This is in a PR where Shougo, another long-time contributor, communicates entirely in walls of unparseable AI slop text: https://github.com/vim/vim/pull/19413

Thank you for the detailed feedback! I’ve addressed all the issues:

Thank you for the feedback! I agree that following the Vim 8+ naming convention makes sense.

Thank you for the feedback on naming!

Thanks for the suggestion! After thinking about this more, I believe repeat_set() / repeat_get() is the right choice:

Thank you for the feedback. A brief clarification.

https://hachyderm.io/@AndrewRadev/116176001750596207

@[email protected]

  • AVengefulAxolotl@lemmy.world
    163·
    2 days ago

    Having an AI understand your codebase, and potentially answering an issue, which might not be an issue is great I think.

    The problem I see here is that you have no idea that a bot is answering. Why isnt there a ‘shougo-bot’ / ‘vim-helper-bot’ / whatever named bot user for it?

    “Talking” to an AI should always be disclosed, everyone feels betrayed whenever they find out that a clanker is on the other side of the channel.

    • riccardo@lemmy.mlEnglish
      9·
      2 days ago

      I don’t think those comments are generated and posted automatically by a bot plugged to their github repo. I think they are generated by the author using an LLM and copy-pasted there - or if the account is plugged to some LLM, they are at least manually reviewed. The answer to the replied-to comment are posted from 10 minutes to some hours later. I don’t think they lost their mind to the point of giving unvetted access to their reputable account to an AI that simply posts for them. That said, they could al least strip the obvious/uneasy parts that give very LLM vibes, specifically those quoted in the op