• Boost@lemmy.world
    link
    fedilink
    English
    arrow-up
    4
    ·
    15 hours ago

    I use Claude every day for actual production software used in a real product and I can say with confidence that even the most advanced publicly available models totally lack the higher order thinking required to build good software. They’re pretty good at writing code, when directed well. They are not good at architectural or design decisions and they’re even worse at actually following decisions made outside of their context. Those are the actually challenging parts of software engineering and you have to beat them into the model every step of the way or your software quickly becomes an unmaintainable mess.

    • red_tomato@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      7 hours ago

      Most human programmers are bad at architecture. They’re making lots of mistakes too. Perfection is not a criterion for intelligence. In that case no human is intelligent.

      • aksdb@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 hours ago

        Intelligence isn’t a one-dimensional axis either. Intelligence exists in many facets. Agents (so LLMs combined with tools, memory, etc.) overlap pretty much with one aspect that we perceive as intelligent. The main risk is basically the same as with humans of similar one-sided intellect: if you expect them to be equally intelligent in other areas, you will get disappointed or even hurt.

    • redballooon@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      arrow-down
      1
      ·
      6 hours ago

      Use Spec driven development and a good verification loop to overcome the “beat it into the model at every step”.