RE: mastodon.gamedev.place/@eniko/Eniko is correct and eloquent and sweary in the thread.It writes code approximately as good as Stack Overflow examples.Which scales about as well as that would.You only run into trouble when you want more than a few lines of code written to illustrate a point; and instead want it to be effective, scalable, secure, legible, maintainable and efficient.It is reviewing the pull requests at work, and that is definitely catching bugs. Some of them even important ones. It is also definitely wasting time on chasing non-bugs.It is possible the ridiculously detailed error coverage in the code is even better code, in some sense. If it matters how you crash and what error you report when you do so and you don't mind reams and reams of error-handling.It may improve. I think I do have a responsibility to be aware of what it can and can't do. If only to fight the people who seem to want to pipe it into root on the prod servers, just for upgrades.And to know when or if it becomes good.I've worked with worse coders, but they also improved. We'll see how well Claude can generalize from textbook examples to effective, scalable, secure, legible, maintainable and efficient over time I guess.I wouldn't rule it out, but there isn't nearly as much training data.#ai #programming

you are viewing a single comment's thread
view the rest of the comments
[–] [S] 1 point 1 month ago (4 children)

@simeon Is that a good line though?There is so much boiler-plate. A huge amount of programming is basically copying and pasting anyway.How AI does your AI have to be to not just be writing the boiler-plate?As a union drawing a line at which we withdraw work it's a good line.But it will mean lots of fairly pointless minor editing of boilerplate which could otherwise be automated.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 1 point 1 month ago (3 children)

    @pre I’m trying to find a workable balance between generate all the code and have no idea how it works, and do have an idea how it works. Yes, there’s a lot of boiler plate that we can gen. But I also notice that the gen slope is covered in soap, and the more I gen, the less I read, all the way beyond the boiler plate, all the way to someone asking “why did you implement it like that” and I have to answer “let me ask my agent” which, I hope you agree, is unworkable?

  • source
  • parent
  • hideshow 3 child comments
  • [–] [S] 1 point 1 month ago (2 children)

    @simeon It does not seem sane to allow the bad-guys bullets while the good guys aren't allowed even shields.And AI is already pointed at code more than the "many eyes" of early open source days.There are a torrent of bugs. It can not be right to turn the fixes down?

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 1 month ago (1 child)

    @pre To your point:“Nobody in their sane mind would want to reject a cure to a disease only because it was made solely by AI.”giorgio.gilest.ro/the-weimar-o

  • source
  • parent
  • hideshow 1 child comment