Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vibe Coding is not an excuse for low-quality work

addyo.substack.com

Post reply on HN
Print view View original

161–170 of 213 posts

Re: Vibe Coding is not an excuse for low-quality work

#161

Post by closewith »

ken47 wrote: post #134

The hype levels are so overwhelming that AI coding could never hope to meet them. I've tried having a highly-ranked AI coding app write unit tests for a relatively complex codebase. 80% of the generated test cases failed. But an experienced human such as myself could use those as a starting point since it took care of some of the tedious boilerplate. It genuinely saved me some time and annoyance, but could never hope…

I'd like to know which app and model you were using, along with the prompts.

We have had a steep learning curve in prompt preparation (what we're doing is certainly not engineering), but Claude Code is now one-shotting viable PRs in our legacy codebases that are, well, good.

Saying LLMs are only good for boilerplate acceleration is so far from my experience that it sounds absurd.

Re: Vibe Coding is not an excuse for low-quality work

#162

Post by RossBencina »

candiddevmike wrote: post #43
dheera wrote: post #31

Earlier quoted context omitted.

I absolutely hate the polarization around "vibe coding". The whole point of AI agents is to eventually get good enough to do this stuff better than humans do. It's okay to dogfood and test them now and see how well they do, and improve them over time. Software engineers will eventually become managers of AI agents. Vibe coding is just version 0.1 pre-alpha of that future.

> Software engineers will eventually become managers of AI agents. Source? This seems very optimistic on both ends (that AI will replace SE work, AND SEs will still be employed to manage them).

> "And then in twelve months, we may be in a world where AI is writing essentially all of the code," Anthropic CEO Dario Amodei said at a Council on Foreign Relations event on Monday. [last week]

https://www.businessinsider.com/anthropic-ceo-ai-90-percent-...

The entire Council on Foreign Relations on stage chat is on YouTube.

Re: Vibe Coding is not an excuse for low-quality work

#163

Post by lloeki »

ehnto wrote: post #150
dheera wrote: post #31

Earlier quoted context omitted.

I absolutely hate the polarization around "vibe coding". The whole point of AI agents is to eventually get good enough to do this stuff better than humans do. It's okay to dogfood and test them now and see how well they do, and improve them over time. Software engineers will eventually become managers of AI agents. Vibe coding is just version 0.1 pre-alpha of that future.

I think the issue most of us have, is that vibe-coding is not being treated as a dog fooding experiment, but as a legitimate way to deliver production code. I am already seeing "vibe coding experts" and other attempts to legitimize the practice as a professional approach to software development. The issue is clear, if you have accepted all PRs with no reviews as vibe-coding suggests, you will end up with security and…

> but as a legitimate way to deliver production code.

Beyond the developer side of the hype that gets talked a lot, I'm witnessing a trend on the "company side" that LLM coding is a worthy thing to shell out $$$ to, IOW there is an expected return on investment for that $$$/seat, IOW it is expected to increase productivity by at least twice that much $$$.

Companies already have a hard time throwing away the prototype - god forbid you showcase a flashy PoC - and priorise quality tasks (which may need to run over a quarter) over product items (always P0), and in that ROI context I don't see that LLM-assisted trend helping with software quality at all.

Re: Vibe Coding is not an excuse for low-quality work

#164

Post by afiodorov »

Barrin92 wrote: post #96
afiodorov wrote: post #80

I think it is a losing battle. People are energy preserving creatures and we skip paying attention if we can. Because paying attention is effort. Vibe coding is exactly this, low effort development and thus is enticing. Now if we can get away with low effort why shouldn’t we? I am not advocating serious NATO missions to be vibe coded for trajectories, no. When billions are at stake no way. But what if billions are no…

>People are energy preserving creatures and we skip paying attention if we can. Paying attention saves you energy in the long run. In the words of Gus Levy, nothing wrong with being greedy, but there's two types of greed, long term and short term; the latter is stupid. Of course for a throwaway project it's irrelevant by definition. But the problem is in professional work you cannot get away with low effort, you're j…

Running AI itself is not low effort though, far from it at current efficiency levels it burns way more energy to produce outputs than humans. Setting latest advanced models to think about the problem on your behalf doesn't necessarily make it low effort overall.

Vibe coding is first and foremost moving some of your problems to the AI and that can be suffice even in professional setting where there's a lot of mundane requests, e.g. setting up slack alerts, running simple data transforms or figuring out one-off data analysis. Maintainability is less of an issue on tasks where it can be done from scratch if need be.

If your situation is result-driven and easily verifiable AI-driven solutions are absolutely appropriate.

Re: Vibe Coding is not an excuse for low-quality work

#165

Post by afiodorov »

tehjoker wrote: post #93
afiodorov wrote: post #80

I think it is a losing battle. People are energy preserving creatures and we skip paying attention if we can. Because paying attention is effort. Vibe coding is exactly this, low effort development and thus is enticing. Now if we can get away with low effort why shouldn’t we? I am not advocating serious NATO missions to be vibe coded for trajectories, no. When billions are at stake no way. But what if billions are no…

I for one advocate NATO using vibe coded lowest-bidder technology. It will make the world a safer place.

NASA* :D

Re: Vibe Coding is not an excuse for low-quality work

#166

Post by dkersten »

musicale wrote: post #35
spaceywilly wrote: post #12

Earlier quoted context omitted.

From that tweet: > I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it That sums up vibe coding, imo. The article talks about code quality with vibe coding, but I think that misses the point. The real problem is code knowledge. When a vibe coder inevitably needs to debug something, if they have no idea what any of the code does, or why it is the w…

> When a vibe coder inevitably needs to debug something, if they have no idea what any of the code does, or why it is the way it is, they are not going to have a good time Kernighan's law still applies. https://www.laws-of-software.com/laws/kernighan/

I strongly believe it also applies to the AI itself.

If the AI wrote the code to the top of its ability, it doesn’t have the capability to debug said code, because its ability to detect and correct issues has already been factored in.

You end up with a constant stream of “I see the issue, it’s: ”, which is consistent with my experience of trying to have LLM’s debug their own code without basically doing the work myself and pointing them to the specific actual issue.

Re: Vibe Coding is not an excuse for low-quality work

#167

Post by interleave »

anonzzzies wrote: post #148

I mainly use vibe coding to figure out how hard something is to do if I would do it 'for real', so I vibe code working prototypes, often to find out there is no way this is feasible and, more often, finding it is easier than I thought it would be. When I have an issue, I search for a library to solve that issue, but to figure it it does and if it does in a friendly way, I have to try it, so I ask claude to give me my…

Wanted to say something similar : high-quality code is not an excuse to make something that doesn't "work" (in regards to sales, usefulness, iterations, learning - all for which vibe coding are a perfect fit IMHO)

Re: Vibe Coding is not an excuse for low-quality work

#169

Post by dbbk »

closewith wrote: post #161
ken47 wrote: post #134

The hype levels are so overwhelming that AI coding could never hope to meet them. I've tried having a highly-ranked AI coding app write unit tests for a relatively complex codebase. 80% of the generated test cases failed. But an experienced human such as myself could use those as a starting point since it took care of some of the tedious boilerplate. It genuinely saved me some time and annoyance, but could never hope…

I'd like to know which app and model you were using, along with the prompts. We have had a steep learning curve in prompt preparation (what we're doing is certainly not engineering), but Claude Code is now one-shotting viable PRs in our legacy codebases that are, well, good. Saying LLMs are only good for boilerplate acceleration is so far from my experience that it sounds absurd.

LLMs don’t even understand fucking TypeScript, which you would expect a computer program to be able to understand. I can’t get it to write valid Drizzle code to save my life, it will confidently hallucinate method imports that don’t even exist.

Re: Vibe Coding is not an excuse for low-quality work

#170

Post by closewith »

dbbk wrote: post #169
closewith wrote: post #161

Earlier quoted context omitted.

I'd like to know which app and model you were using, along with the prompts. We have had a steep learning curve in prompt preparation (what we're doing is certainly not engineering), but Claude Code is now one-shotting viable PRs in our legacy codebases that are, well, good. Saying LLMs are only good for boilerplate acceleration is so far from my experience that it sounds absurd.

LLMs don’t even understand fucking TypeScript, which you would expect a computer program to be able to understand. I can’t get it to write valid Drizzle code to save my life, it will confidently hallucinate method imports that don’t even exist.

The question is which LLM, invoked how?

Claude Code refactored numerous projects for us into TS, often one-shotting it. Saying LLMs don't understand TS (which may be true, in that LLMs questionably understand anything) says more about your perception than model and agent abilities.

Post reply on HN