• AggressivelyPassive@feddit.de
    link
    fedilink
    English
    arrow-up
    14
    arrow-down
    2
    ·
    1 year ago

    How can you verify that it’s actually running safely? If you’d have a comprehensive testing framework in place, you wouldn’t need AI driven refactoring in the first place.

    • bionicjoey@lemmy.ca
      link
      fedilink
      English
      arrow-up
      5
      ·
      1 year ago

      You could code review the commits it makes I suppose. Saves you having to think of how to refactor something but still makes it fairly easy to mitigate the AI doing something terribly wrong.