• codeinabox@programming.dev
    link
    fedilink
    English
    arrow-up
    6
    ·
    1 day ago

    As the author notes, it is very impressive what generative AI can produce these days.

    The frontier of what the LLMs can do has moved since the last time I tried to vibe-code something. I didn’t expect to have a working interpreter the same day I dreamt of a new programming language. It now seems possible.

    However, as they point out, there’s definitely downsides to this approach.

    The downside of vibe coding the whole interpreter is that I have zero knowledge of the code. I only interacted with the agent by telling it to implement a thing and write tests for it, and I only really reviewed the tests. I reckon this would be an issue in the future when I want to manually make some change in the actual code, because I have no familiarity with it.

    • Lucy :3@feddit.org
      link
      fedilink
      arrow-up
      1
      ·
      1 day ago

      And the barriers of what humans are able to maintain and what “AI” is able to maintain are very, very far apart. And always will. There’s an information limit that we’re approaching fast.