Live data from Hacker News

The 100 hour gap between a vibecoded prototype and a working product

kanfa.macbudkowski.com

191–200 of 362 posts

Re: The 100 hour gap between a vibecoded prototype and a working product

#191

What I really want to know is... as a software developer for 25+ years, when using these AI tools- it is still called "vibecoding"? Or is "vibecoding" reserved for people with no/little software development background that are building apps. Genuine question.

As a software developer over 30 years, AI is not a tool, it is not deterministic, it is an aide.

Don't have it do things for you. Have it do things with you.

Re: The 100 hour gap between a vibecoded prototype and a working product

#192
i found that to be effective is to use multiple AI tools at once. I'm using Gemini newest model i cant think of at the top of my head right now, and Claude newest model. i have each for its purpose with rustover IDE to speed things up. Rustover is particularly helpful because of how rust is worked with, the constant cargo cli commands and database interactions right in the IDE. i know visual code has this to a certain limit but IMO i prefer Rustover. Using multiple models is because i know what each one is good at and how my knowledge works with their output, makes my life way easier and drives frustration down, which is needed when you need creativity at the forefront. This is being said it def helps to know what you are doing if not 100% at least 60% of the things you are asking the models to do for you, I have caught mistakes and know when a model might make mistake which im fine with, sometimes i just want to see how something is done like the structure for a certain function of crate as im reading cargo.io doc constantly to learn what im doing.

There are plenty of ways to code and use code, which-ever works for you is good just improve on it and make it more effective. I have multiple screens on my computer, i don't like jumping back and fourth opening tabs and browsers so i have my set up the best way that works for me. As for the AI models, they are not going to be that helpful to you if you don't understand why its doing what its doing in a particular function or crate (in case of rust) or library. I imagine the the over the top coder that has years of experience and multiple knowledge in various languages and depth knowledge in libraries, using the same technique he can replace a whole Department by himself technically.

Re: The 100 hour gap between a vibecoded prototype and a working product

#193
post #188
post #116

Earlier quoted context omitted.

Wont happen. The average user just has no interest in building things.

Many parents are extremely interested in quickly building digital tools for their kids (education and entertainment) that they know are free from advertising, social media integration, user monitoring etc.

I'm saying this with all my love and respect: you are living in a very small bubble

Re: The 100 hour gap between a vibecoded prototype and a working product

#194

Earlier quoted context omitted.

There’s a big gap between reality and the influencer posts about LLMs. I agree with you that LLMs do provide some significant acceleration, but the influencers have tried to exaggerate this into unbelievable numbers. Even non-influencers are trying to exaggerate their LLM skills as a way to get hired or raise their status on LinkedIn. I rarely read the LinkedIn social feed but when I check mine it’s now filled with c…

> I rarely read the LinkedIn social feed but when I check mine it’s now filled with claims from people about going from idea to shipped product in N days (with a note at the bottom that they’re looking for a new job or available to consult with your company). This always seems to be the pattern. "I vibe coded my product and shipped it in 96 hours!" OK, what's the product? Why haven't I heard of it? Why can't it repla…

I regret only having one upvote for this.

I note that games are mostly art assets and things like level design, and players are already happy to instantly consign such products to the slop bin.

The whole thing is "market for lemons": app stores filling with dozens of indistinguishable clones of each product category will simply scare users off all of them.

Re: The 100 hour gap between a vibecoded prototype and a working product

#195
It seems like the entire "product" here is just a ChatGPT system prompt: "combine this image of a person with this image of a dinosaur".

The only thing he needed to code was an NFT wrapper, which presumably is just forking an existing NFT wholesale.

The interesting, user-facing part of the project isn't code at all! It's just an HTML front end on someone else's image generator and a "pay me" button.

Very disappointing.

Re: The 100 hour gap between a vibecoded prototype and a working product

#197

What I really want to know is... as a software developer for 25+ years, when using these AI tools- it is still called "vibecoding"? Or is "vibecoding" reserved for people with no/little software development background that are building apps. Genuine question.

Steve Yegge has been a dev for several decades with lead spots at Amazon and Google, has completely converted to using AI, wrote a book about it using it effectively for large production-ready projects, and still calls it vibe coding.

I don't think I'll ever adopt this term, I'm not a fan of it at all. I find myself saying "I was working with AI" and just leave it at that. It is a collaboration afterall.

Re: The 100 hour gap between a vibecoded prototype and a working product

#198
post #87

I work as a DevOps/SRE and have been doing it FinTech (bank, hedge funds, startups) and Crypto (L1 chain) for almost 20 years. My thoughts on vibe coding vs production code: - vibe coding can 100% get you to a PoC/MVP probably 10x faster than pre LLMs - This is partly b/c it is good at things I'm not good at (e.g. front end design) - But then I need to go in and double check performance, correctness, information flow…

> - This is partly b/c it is good at things I'm not good at (e.g. front end design) Everyone thinks LLMs are good at the things they are bad at. In many cases they are still just giving “plausible” code that you don’t have the experience to accurately judge. I have a lot of frontend app dev experience. Even modern tools (Claude w/Opus 4.6 and a decent Claude.md) will slip in unmaintainable slop in frontend changes. I…

Yes I’ve seen this at work where people are promoting the usage of LLMs for.. stuff other people do.

There’s also a big disconnect in terms of SDLC/workflow in some places. If we take at face value that writing code is now 10x faster, what about the other parts of the SDLC? Is your testing/PR process ready for 10x the velocity or is it going to fall apart?

What % of your SDLC was actually writing code? Maybe time to market is now ~18% faster because coding was previously 20% of the duration.

Re: The 100 hour gap between a vibecoded prototype and a working product

#199
post #56

Earlier quoted context omitted.

I think the main issue is treating LLM as a unrestrained black box, there's a reason nobody outside tech trust so blindly on LLMs. The only way to make LLMs useful for now is to restrain their hallucinations as much as possible with evals, and these evals need to be very clear about what are the goal you're optimizing for. See karpathy's work on the autoresearch agent and how it carry experiments, it might be useful…

> there's a reason nobody outside tech trust so blindly on LLMs. Man, I wish this was true. I know a bunch of non tech people who just trusts random shit that chatgpt made up. I had an architect tell me "ask chatgpt" when I asked her the difference between two industrial standard measures :) We had politicians share LLM crap, researchers doing papers with hallucinated citations.. It's not just tech people.

We were working on translations for Arabic and in the spec it said to use "Arabic numerals" for numbers. Our PM said that "according to ChatGPT that means we need to use Arabic script numbers, not Arabic numerals".

It took a lot of back-and-forths with her to convince her that the numbers she uses every day are "Arabic numerals". Even the author of the spec could barely convince her -- it took a meeting with the Arabic translators (several different ones) to finally do it. Think about that for a minute. People won't believe subject matter experts over an LLM.

We're cooked.

Re: The 100 hour gap between a vibecoded prototype and a working product

#200

Earlier quoted context omitted.

> I rarely read the LinkedIn social feed but when I check mine it’s now filled with claims from people about going from idea to shipped product in N days (with a note at the bottom that they’re looking for a new job or available to consult with your company). This always seems to be the pattern. "I vibe coded my product and shipped it in 96 hours!" OK, what's the product? Why haven't I heard of it? Why can't it repla…

> Where are all of the actual shipping vibecoded products that millions of users are using? Claude Code and OpenClaw - they are vibecoded. And I believe more coming.

Claude Code is not vibecoded, it is made using Claude Code but it is not vibecoded using Claude Code.
Post reply on HN