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

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

kanfa.macbudkowski.com

Post reply on HN
Print view View original

51–60 of 362 posts

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

#51

Post by westurner »

I keep seeing things that were vibe coded and thinking, "That's really impressive for something that you only spent that much time on".

To have a polished software project, you must spend time somewhat menially iterating and refining (as each type of user).

To have a polished software project, you need to have started with tests and test coverage from the start for the UI, too.

Writing tests later is not as good.

I have taken a number of projects from a sloppy vibe coded prototype to 100% test coverage. Modern coding llm agents are good at writing just enough tests for 100% coverage.

But 100% test coverage doesn't mean that it's quality software, that it's fuzzed, or that it's formally verified.

Quality software requires extensive manual testing, iteration, and revision.

I haven't even reviewed this specific project; it's possible that the author developed a quality (CLI?) UI without e2e tests in so much time?

Was the process for this more like "vibe coding" or "pair programming with an LLM"?

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

#53

Post by potro »

jimnotgym wrote: post #37

I have not been coding for a few years now. I was wondering if vibe coding could unstick some of my ideas. Here is my question, can I use TDD to write tests to specify what I want and then get the llm to write code to pass those tests?

You absolutely can. This is one of recommended directions with agentic coding. But you can go farther and ask llm to write tests too. The review/approve them.

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

#54

Post by CuriouslyC »

jcgrillo wrote: post #46
niemandhier wrote: post #4

With sufficiently advanced vibe coding the need for certain type of product just vanishes. I needed it, I quickly build it myself for myself, and for myself only.

How many products are actually like that? If I could easily replace github, datadog/sentry/whatever, cloudflare, aws, tailscale that would be great. In my view building and owning is better than buying or renting. Especially when it comes to data--it would be much better for me to own my telemetry data for example than to ship it off to another company. But I don't think you (or anyone) will be vibecoding replacement…

Github is on the chopping block as a tool (it's sticky as a social network). The other stuff not so much.

The things that are going away are tools that provide convenience on top of a workflow that's commoditized. Anything where the commercial offering provides convenience rather than capabilities over the open source offerings is gonna get toasted.

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

#55

Post by xp84 »

pydry wrote: post #40
keyle wrote: post #8

Earlier quoted context omitted.

I built a jira with attachments and all sorts of bells and whistles. Purrs like a kitten. Saas are going extinct. At least the jobs that charged $1000 a day to write jira plugins.

jira is a perfect example of an abysmal product that was marketed well.

Yes, it seems like it got to some tipping point around 2013 where so many product and management people were familiar with it, and from there it became this “industry standard” that management always wanted everyone to use.

Also though, I feel like being attached to Confluence helped it because there is a lot less competition in the world of documentation wikis than there is in task management.

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

#56

Post by mtrovo »

matt_heimer wrote: post #45
alexpotato wrote: post #10

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…

I'm building a Java HFT engine and the amount of things AI gets wrong is eye opening. If I didn't benchmark everything I'd end up with much less optimized solution. Examples: AI really wants to use Project Panama (FFM) and while that can be significantly faster than traditional OO approaches it is almost never the best. And I'm not taking about using deprecated Unsafe calls, I'm talking about using primative arrays b…

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 for what you're doing.

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

#58

Post by hebrides »

I’ve had a similar experience. I’ve been vibecoding a personal kanban app for myself. Claude practically one-shotted 90% of the core functionality (create boards, lanes, cards, etc.) in a single session. But after that I’ve now spent close to 30 hours planning and iterating on the remaining features and UI/UX tweaks to make the app actually work for me, and still, it doesn’t feel "ready" yet. That’s not to say it hasn’t sped up the process considerably; it would’ve taken me hours to achieve what Claude did in the first 10 minutes.

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

#59

Post by 101008 »

keyle wrote: post #8
niemandhier wrote: post #4

With sufficiently advanced vibe coding the need for certain type of product just vanishes. I needed it, I quickly build it myself for myself, and for myself only.

I built a jira with attachments and all sorts of bells and whistles. Purrs like a kitten. Saas are going extinct. At least the jobs that charged $1000 a day to write jira plugins.

SaaS are not going exctinct. This reminds me of the LinkedIn posts saying they clone Slack in two hours, copying the UI, etc. Yeah, if you think Slack is private chat rooms then you should use IRC for your company.

One of the most valuable things about Slack is the ecosystem: apps, API support, etc. If you need to receive notifications from external apps (like PageDuty or Incident.io or something like that), good luck expecting them having a setup for your own version of the app. Yeah, some of them provide webhooks (not all of them), but in the end you have to maintain that too...

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

#60

Post by capitalsigma »

fzeroracer wrote: post #22

I can't say I'm impressed by this at all. 100+ hours to build a shitty NFT app that takes one picture and a predefined prompt, then mints you a dinosaur NFT. This is the kind of thing I would've seen college students slam out over a weekend for a coding jam with no experience and a few cans of red bull with more quality and effort. Has our standards really gotten so low? I don't see any craftsmanship at play here.

Also the process sounds like a nightmare: "it broke and I asked 4 different LLMs to fix it; my `AGENTS.md` file contained hundreds of special cases; etc." I thought this article was intended to be a horror story, not an advertisement
Post reply on HN