you are viewing a single comment's thread
view the rest of the comments
[–] -3 points 3 days ago (3 children)

I can't say I agree with this.

AI writes shallow tests.

It definitely did in the past. But not any more. It's far better at writing tests than humans and I haven't seen a single nonsense test out of Opus 5.5.

AI writes overly complex ccode

This one I will kind of give him. AI does seem to like being super paranoid - writing tons of checks for things that we don't really need to check, and adding config flags for absolutely everything. You can just tell it not to do that though. Annoying that you have to, but it does work.

Reliance on AI decreases human understanding

Yes but does it matter? Does your manager understand the codebase? Does his manager?

AI moves too quickly to maintain a high quality bar

It's too quick for thorough human code review definitely, but I don't think that means you can't have a high quality bar. There are other ways to ensure a high quality product. Traditional QA testing for example.

  • source
  • hideshow 3 child comments
  • [–] 5 points 3 days ago (2 children)

    AI writes overly complex ccode

    100%. It doesn't have a concept of maintainability. If you tell it to do X it will happily rewrite half o the codebase to achieve it where a person would stop and look for alternative solution. I see this as the biggest issue with current models. They can implement anything but someone still needs to check if the solution makes sense. AI can't tell.

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

    Funny I've seen the opposite. I want it to rewrite half the codebase to do things properly. A human shouldn't do that because of the effort, but it's no issue for AI.

    However it very often says "that's too big of a change so I'll do this workaround instead" which is not what I want at all.

    But I agree they sometimes implement things that don't actually make sense to do. Mostly you can solve that by just asking how to program / code works at a high level without needing to read every line.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 2 days ago

    Yes, sometimes it's the opposite. I guess the issue is simply that AI can't tell between those two. It's great a big rewrites because it has such a huge context but it will often try to sneak in some things you didn't ask for or skip some parts because... no one knows why. Then on other occasions it will add tons of code to fix a bug in some extremely unlikely path. It's very smart and very stupid at the same time.

  • source
  • parent