• Modern_medicine_isnt
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    6
    ·
    7 days ago

    One… use --dangerously… they asked for speed, thats how you get it. Two… if you have great tests, you don’t really need to know every detail of the code. The risk just shifts from a dev designing bad code, to a dev designing bad tests.

    • criss_cross
      link
      fedilink
      English
      arrow-up
      1
      ·
      6 days ago

      I dunno I’ve seen too many times where Claude Code will just rewrite a test it doesn’t like and say it’s good. Combining that with —dangerously or —yolo is a recipe for disaster.

      • Modern_medicine_isnt
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 days ago

        You do have to keep some tests for yourself, and don’t let claude touch those (or even see them ideally).
        Though I have been reading that you can actually have a second agent manage tests. That way it’s motivation is to find bugs. So if anything it will hallucinate failures.
        That said… if corp is pushing AI, then they get the result. Most of the time it will be fine. When it isn’t it’s the AI we have been encoraged to use’s fault.