Live data from Hacker News

AI didn't simplify software engineering: It just made bad engineering easier

robenglander.com

111–119 of 119 posts

Re: AI didn't simplify software engineering: It just made bad engineering easier

#112

I’m an AI skeptic and in no sense is it taking my peers job. But it does save me time. I can do research much better than Google, explore a code base, spit out helper functions, and review for obvious mistakes.

So what do you mean with being a sceptic? I thought you meant you weren't convinced of it's usefulness, and therefore don't use it. But you do seem to use it, so what is it you're sceptible about?

I’m skeptical that it’s very smart, that it can solve hard problems, and that it’s accelerating.

I’m skeptical vibe coding is really viable or saves you time.

Re: AI didn't simplify software engineering: It just made bad engineering easier

#113

Earlier quoted context omitted.

I do agree with you, but don't underestimate the projects where you can actually apply this 10x. For example, I wanted to get some analytics out of my database. What would have been a full weekend project was now done in an hour. So for such things there is a huge speed boost. But once software becomes bigger and more complex, the LLM starts messing up, and the expert has to come in. That basicaly means your months p…

I think there will also be a lot of work in how to modularize month long projects into plugin sized pieces.

People have been thinking about that a long time though. For that objective, LLMs don't seem to open up any new capabilities. If that problem could be solved, with really clean abstractions that dramatically reduce context needed to understand one "module" at a time, sure LLMs will then be able to take that an run. But it's a fundamentally hard problem.

Re: AI didn't simplify software engineering: It just made bad engineering easier

#114

Earlier quoted context omitted.

So what do you mean with being a sceptic? I thought you meant you weren't convinced of it's usefulness, and therefore don't use it. But you do seem to use it, so what is it you're sceptible about?

I’m skeptical that it’s very smart, that it can solve hard problems, and that it’s accelerating. I’m skeptical vibe coding is really viable or saves you time.

Ok, so what are you actually using it for?

Re: AI didn't simplify software engineering: It just made bad engineering easier

#115

Earlier quoted context omitted.

I’m skeptical that it’s very smart, that it can solve hard problems, and that it’s accelerating. I’m skeptical vibe coding is really viable or saves you time.

Ok, so what are you actually using it for?

Oh sorry, I see in your original post you use it for research, codebase exploration, and small coding tasks.

I think you hit the nail on the head with that AI is ultimately not smart, it'll be dependent on humans for a long time, and we have to review their work, so they won't easily replace us.

In that sense I'm also sceptical; the idea that AI can soon replace us.

But I'm not sceptical about the power of AI as a tool for humans. I'm actually quite convinced by that by now. Hence my confusion of your remark. But I think we understand the misunderstanding now.

Re: AI didn't simplify software engineering: It just made bad engineering easier

#116
post #21

I disagree with the premise. It made all engineering easier. Bad and good. I believe vibe coding has always existed. I've known people at every company who add copious null checks rather than understanding things and fixing them properly. All we see now is copious null checks at scale. On the other hand, I've also seen excellent engineering amplified and features built by experts in days which would have taken weeks.

`On Error Resume Next`
Post reply on HN