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

151–160 of 213 posts

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

#151

Post by __MatrixMan__ »

simonw wrote: post #51
SCdF wrote: post #5

So what have we redefined vibe coding to mean exactly? The original tweet[1] talked very specifically about not caring about quality, just accepting whatever code the AI produces blindly, as long as you get the black box output you're looking for, and just randomly try again if you didn't. Are people now using this term to mean "giving an AI agent broad tasks"? [1] https://x.com/karpathy/status/1886192184808149383?la…

I wrote about this last month: "Not all AI-assisted programming is vibe coding" - https://simonwillison.net/2025/Mar/19/vibe-coding/ Vibe coding is when you don't review the code at all. If you're using LLMs to help you write code but you're actually reviewing what they produce (and iterating on it) that's not vibe coding any more. This battle is almost certainly lost already, but dammit I'm gonna keep fighting anywa…

re: "semantic diffusion", sometime the opposite happens. Consider "meme" which was once very general and is now much more specific. "semantic speciation"?

It's as if the culture wants a certain level of specificity for a phrase and if you start too far from it, it'll ignore your wishes and drift to that level anyway.

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

#152

Post by firesteelrain »

ehnto wrote: post #147
Workaccount2 wrote: post #136

Earlier quoted context omitted.

AI is to SWEs what self-driving cars (or like features on new cars) are to taxi drivers. A neat thing that may make some basic things a little easier. But it's the wrong perspective. Think instead what a self driving car is to someone who cannot drive. It doesn't matter if it sometimes disengages to have an operator step in or can only handle basic local trips. It's a total game changer. AI is unlocking computers for…

> AI is unlocking computers for people who have never written a line of code in their life. I don't think I can dispute the claim, but it feels more like someone who can't build a house being able to do it now that they have YouTube tutorials. Unless the person was already quite smart and competent, the house will probably have significant structural issues. Is that a bad thing? For housing, governments the world ove…

I disagree that coding doesn’t have regulation. If you have never developed code in a professionally regulated industry such as Airworthiness then you haven’t been exposed yet to an area that requires rigorous process. There are regulated areas where software is regulated.

I have DIY’d an addition onto my house with professionally architected blueprints and engineering seal. During various stages, I would call the City who would send code inspection officials to incrementally sign off on my project’s progress. Other than pouring a new slab of concrete and electrical, I built it all myself to code. I followed YouTube tutorials.

My point is that DIY isn’t the issue - lack of oversight is. With standards, expert input, and review processes, even non-experts can safely build. AI-assisted coding needs the same approach.

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

#153

Post by otabdeveloper4 »

bluefirebrand wrote: post #73
senko wrote: post #66

Earlier quoted context omitted.

We do need a simple term for "used AI to write code (semi)autonomously, but checked and/or tweaked the result and I care about the quality". Vibe-but-verify? Faux-Vibe? AiPair? (... I'll see myself out...)

The term for this is "unicorn" Entirely fictional creature that doesn't exist Every person who I have seen embracing AI coding has been getting lazier and lazier about verifying

> yeah bro, leave the easy and fun part (googling and typing code) to an AI, and let the human deal with the tedious and error-prone part (checking all the edge cases)

What did you really expect?

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

#154

Post by shikon7 »

spaceywilly wrote: post #12
SCdF wrote: post #5

So what have we redefined vibe coding to mean exactly? The original tweet[1] talked very specifically about not caring about quality, just accepting whatever code the AI produces blindly, as long as you get the black box output you're looking for, and just randomly try again if you didn't. Are people now using this term to mean "giving an AI agent broad tasks"? [1] https://x.com/karpathy/status/1886192184808149383?la…

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…

> Sure they can copy paste the error into the LLM and hope for the best, but what happens when that doesn’t fix it?

Then you throw the code away and start newly from scratch. Or you accept that your problem cannot be solved by vibe coding.

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

#155

Post by BlueTemplar »

simonw wrote: post #85
diggan wrote: post #81

Earlier quoted context omitted.

I don't know if it's you and I (and some others) who are just uptight sticklers or something, but it bothers me a ton too. Same thing happening with "open source" in connection to LLMs, where suddenly some companies have decided to try to redefine the meaning, people lack the care to make the distinction. In a dream world, each new terminology goes through an RFC to figure out a meaning we all (some of us) can agree…

Yeah that "open source" thing is SO frustrating. We have a very well established definition for what "open source" means: https://opensource.org/osd I have a suspicion that Facebook insist on calling their open weights models "open source" because the EU AI act says "This Regulation does not apply to AI systems released under free and open-source licences" but doesn't do a good job of defining what "open-source" mean…

Also, with LLMs, the traditional Four Freedoms of free software are no longer enough :

https://elevenfreedoms.org/freedoms/

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

#156

Post by trog »

firesteelrain wrote: post #152
ehnto wrote: post #147

Earlier quoted context omitted.

> AI is unlocking computers for people who have never written a line of code in their life. I don't think I can dispute the claim, but it feels more like someone who can't build a house being able to do it now that they have YouTube tutorials. Unless the person was already quite smart and competent, the house will probably have significant structural issues. Is that a bad thing? For housing, governments the world ove…

I disagree that coding doesn’t have regulation. If you have never developed code in a professionally regulated industry such as Airworthiness then you haven’t been exposed yet to an area that requires rigorous process. There are regulated areas where software is regulated. I have DIY’d an addition onto my house with professionally architected blueprints and engineering seal. During various stages, I would call the Ci…

All true but tell the average programmer that you think their industry should be regulated and they should potentially be held liable for their code.

This is not a popular opinion on software development circles - unless you're already in one of those regulated fields, like where a software engineer (a literal accredited engineer) is required.

But it's been an increasingly common talking point from a lot of experts. Bruce Schneier writes about it a lot - he convinced me long ago that our industry is pretty pathetic when it comes to holding corporations liable for massive security failures, for example.

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

#157

Post by atmavatar »

Workaccount2 wrote: post #136
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…

AI is to SWEs what self-driving cars (or like features on new cars) are to taxi drivers. A neat thing that may make some basic things a little easier. But it's the wrong perspective. Think instead what a self driving car is to someone who cannot drive. It doesn't matter if it sometimes disengages to have an operator step in or can only handle basic local trips. It's a total game changer. AI is unlocking computers for…

> AI is unlocking computers for people who have never written a line of code in their life.

And this is why the holodeck tries to kill its occupants in half the episodes in which it is featured.

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

#158

Post by herbst »

frereubu wrote: post #3

> treat the AI like a super-speedy but junior developer on your team That sounds like it's going to take a lot more time that just writing the code for an experienced developer. The issue with AI for me is that it produces plausible-looking code which requires a lot of attention to read through, because things that look superficially "right", including any justification in code comments, can actually have really prob…

Except you ask it to not to. Sure it's far from perfect but honestly that is not an issue. If you ask Claude to study and document the codebase and then write unit tests I am sure there are only very few broken ones, less hallucination more like real small bugs.

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

#159

Post by herbst »

vunderba wrote: post #15
neural_thing wrote: post #7

What percentage of companies can hire an engineer who writes better code than o3?

Given that o3 just spun its wheels endlessly trying to correct a CSS issue by suggesting to create a "tailwind.config.X" file despite being given the package JSON which contained a clear reference to Tailwind 4x - I'd say any engineer capable of reading and learning from basic documentation. For reference, Tailwind 4 will not read in config files by default (which is the older behavior) - the encouraged practice is t…

Tell the AI to comment above the include why it uses a specific version, ask it to document the version and it's specific quirks after fixing it with it.

Not sure how o3 is generally at coding, but this kind of meta information works well for me to avoid version missmatches with Claude and Gemini

It's kinda important that the AI finds the issues itself so it can properly document it in her own words.

Post reply on HN