Live data from Hacker News

Vibe Coder vs. Software Engineer

yusufaytas.com

31–39 of 39 posts

Re: Vibe Coder vs. Software Engineer

#31

Earlier quoted context omitted.

It only hallucinates if you use it wrong. Give it enough requirements, context, keep an eye on all it does (like it were a junior developer), and you will get awesome results. AI code assistants are a fantastic tool that can make you 10-100x more productive provided that you know how to use them. Most of the people saying the kind of things you say don't know how to properly use an AI code assistant.

> It only hallucinates if you use it wrong Sorry but this is demonstrably false. For starters, see the "R's in strawberry" meme.

That's just you being pedantic and asking a language model things it can't do.

Ask it to create a program that counts the R's in any text. Now ask it to do it in 20 different languages. It'll get them right immediately.

It's like me asking you who was the proposed King for Finland and calling you a bad programmer because you don't know.

Re: Vibe Coder vs. Software Engineer

#32

Claude is smart enough now to transition a vibe coder into a software engineer if you provide access to SDLC pipeline.

Giving it access to JIRA doesn't make the code it produces more mergable, or reduce the cognitive load and technical debt a massive PR written by AI introduces into complex codebases.

A massive PR written by ANYONE produces cognitive load and technical debt.

Why are you allowing massive PRs at all, fix your process first.

Re: Vibe Coder vs. Software Engineer

#33
post #13

> A vibe coder is someone who wants to test an idea by generating software as a prototype. A software engineer is someone who thinks about the entire software development lifecycle. I don't think it's such a simple dichotomy; And dismissing the possibilites of agentic coding as inherently non-SWE is rather short-sighted: You CAN use agents as a software engineering tool. It's just that it's often misaligned with the…

To comment on the two sibling responses to my post here in parallel.

I think it gives very valuable insights to tackle the question: "What if we wanted to apply 'vibe-coding' as an SWE technique?"

There's a lot of interesting nuance to cover:

- How can we ensure that agents produce the codebases we want?

- How can we reduce the cognitive burden of code review?

- Do we actually need to review everything?

- How can we safely vibe-code in regulated environments (ISO 27001)?

- How can we use vibe-coding to safely evolve production-grade systems?

- ... etc, etc

I find this approach much more interesting than dismissing vibe-coding as non-SWE.

Re: Vibe Coder vs. Software Engineer

#34
These comparisons are tricky, because software in particular has always been a bit weird about what it means by "engineer". The article gestures at this, the majority of the people with the title are not actually engineers at all, although I couldn't prove it, because we don't have a definition.

The best I have is that engineering is the real-world, practical application of the scientific method deployed in service of human values. (The human values bit is important to my mind, as I don't believe experimentation over disconnected, stochastically generated hypothesis counts as science.)

By this definition, vibe-coding does introduce a wrinkle because it becomes more difficult to experimentally verify hypothesis as you have reduced how much you are observing, but it's not a hard impossibility or anything like that.

Re: Vibe Coder vs. Software Engineer

#35
post #34

These comparisons are tricky, because software in particular has always been a bit weird about what it means by "engineer". The article gestures at this, the majority of the people with the title are not actually engineers at all, although I couldn't prove it, because we don't have a definition. The best I have is that engineering is the real-world, practical application of the scientific method deployed in service o…

My definition of an engineer is someone who has a dedicated education as such. We have the same definition for doctor, lawyer, pilot, teacher - why not software engineer?

Re: Vibe Coder vs. Software Engineer

#36
post #33
post #13

> A vibe coder is someone who wants to test an idea by generating software as a prototype. A software engineer is someone who thinks about the entire software development lifecycle. I don't think it's such a simple dichotomy; And dismissing the possibilites of agentic coding as inherently non-SWE is rather short-sighted: You CAN use agents as a software engineering tool. It's just that it's often misaligned with the…

To comment on the two sibling responses to my post here in parallel. I think it gives very valuable insights to tackle the question: "What if we wanted to apply 'vibe-coding' as an SWE technique?" There's a lot of interesting nuance to cover: - How can we ensure that agents produce the codebases we want? - How can we reduce the cognitive burden of code review? - Do we actually need to review everything? - How can we…

We really do need to review everything. Whether that's actually being done in practice with enough competence was already a significant risk before LLMs.

LLMs today can reduce cognitive load, but only when it gets it right (about half of the time). They're better than nothing if you don't have anyone else to help review. They still have a very long way to go compared to two or more human reviewers that know the project well.

I don't have answers for the other questions. They seem irresponsible, not because "vibe code bad", but because there should already be very restrictive templates in place for production and regulated environments. Wanting to vibe anything in there implies those environments are already broken enough to allow shenanigans.

Post reply on HN