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

111–120 of 362 posts

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

#111

Post by nly »

FpUser wrote: post #70
matt_heimer wrote: post #45

Earlier quoted context omitted.

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 am curious about what causes some to choose Java for HFT. From what I remember the amount of virgin sacrifices and dances with the wolves one must do to approach native speed in this particular area is just way too much of development time overhead.

"HFT" means different things to different people.

I've worked at places where ~5us was considered the fast path and tails were acceptable.

In my current role it's less than a microsecond packet in, packet out (excluding time to cross the bus to the NIC).

But arguably it's not true HFT today unless you're using FPGA or ASIC somewhere in your stack.

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

#112

Post by newsoftheday »

fixxation92 wrote: post #102

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.

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

#113

Post by ChrisMarshallNY »

"working" != "shipping."

When we start selling the software, and asking people to pay for/depend upon our product, the rules change -substantially.

Whenever we take a class or see a demo, they always use carefully curated examples, to make whatever they are teaching, seem absurdly simple. That's what you are seeing, when folks demonstrate how "easy" some new tech is.

A couple of days ago, I visited a friend's office. He runs an Internet Tech company, that builds sites, does SEO, does hosting, provides miscellaneous tech services, etc.

He was going absolutely nuts with OpenClaw. He was demonstrating basically rewiring his entire company, with it. He was really excited.

On my way out, I quietly dropped by the desk of his #2; a competent, sober young lady that I respect a lot, and whispered "Make sure you back things up."

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

#114

Post by qsera »

niemandhier wrote: post #41
IAmGraydon wrote: post #26

Earlier quoted context omitted.

This is a pipe dream and “sufficiently advanced” is doing a lot of heavy lifting. You really think people would rather spin up and debug their own self-made software rather than pay for something that has been tested, debugged, and proven by thousands of users? Why would anyone do that for anything more than a very simple script? It makes zero sense unless the LLM outputs literally perfect one-shot software reliably.

Perplexity just launched a tool that builds and hosts small bespoke tools. I tried it works wells. I can do the same thing in my Linux machine, but even my 12 year old now can get perplexity to build him a tool to compare ram prices at different chinease vendors.

Yes, LLMs can be a better search tool.

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

#115

Post by ryandrake »

serial_dev wrote: post #71
s1mon wrote: post #52

Earlier quoted context omitted.

Yep. As much as the rest of it resonated with LLM coding experiences I'm having, the NFT thing is unfortunate.

The way I see it, the NFT part is actually just for convenience to distribute AI generated images. It could have been a web app, but with NFTs and Farcaster miniapps, you market to people who are willing and able to spend using their wallet instead of asking “normies” for credit card information for a 2 dollar custom image (that you could also prompt out of a free Gemini session). With Farcaster, you also already hav…

I think there's simply a huge overlap between the Crypto Bros, the NFT Bros, and now the AI Bros. The same sorts of people are pumping each one. I knew a guy who was into LeadGen and Drop Shipping in the 2000s, then got into online poker, then of course, got into Crypto, then inevitably NFTs. I haven't kept up with him, but I'm almost 100% sure he's pumping some AI related scheme now. These guys get into this pipeline and at each stage they are convinced that they're going to get rich off it.

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

#116

Post by nly »

WarmWash wrote: post #74
sieste wrote: post #43

Earlier quoted context omitted.

Related anecdote: My 12yo son didn't like the speed cubing online timer he was using because it kept crashing the browser and interrupted him with ads. Instead of googling a better alternative we sat down with claude code and put together the version of the website that behaved and looked exactly as he wanted. He got it working all by himself in under an hour with less than 10 prompts, I only helped a bit putting it…

I don't think people are grasping yet that this is the future of software, if by no metric other than "most software used is created by the user".

Wont happen.

The average user just has no interest in building things.

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

#117

Post by jopsen »

phillipclapham wrote: post #85

[flagged]

Yeah, communicating what you want can be hard.

I'm doing a simple single line text editor, and designing some frame options. Which has a start end markers.

This was really hard to get the LLM to do right.. until just took a pen and paper, drew what I wanted, took a photo and gave it to the llm

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

#118

Post by nly »

jsdalton wrote: post #69
lacedeconstruct wrote: post #9

Earlier quoted context omitted.

I dont want that though, I want someone to spend much more time than I can afford thinking about and perfecting a product that I can pay for and dont worry about it

The metaphor that’s popped into my head recently is baking bread. You can learn to bake good bread. It’s not _that_ hard. And it’ll probably taste better than store bought bread. But it almost certainly won’t be cheaper. And it’ll take a more more time and effort. Still, sometimes you might bake your own bread for kicks. But most of the time, you’ll just buy the bread someone else has already perfected.

Baking bread also takes hours of waiting.

I can have fresh bread anytime I want from a handful of nearby stores.

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

#119

Post by DennisP »

fixxation92 wrote: post #102

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.

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

#120

Post by zahlman »

sieste wrote: post #43
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.

Related anecdote: My 12yo son didn't like the speed cubing online timer he was using because it kept crashing the browser and interrupted him with ads. Instead of googling a better alternative we sat down with claude code and put together the version of the website that behaved and looked exactly as he wanted. He got it working all by himself in under an hour with less than 10 prompts, I only helped a bit putting it…

... So at no point in this did anyone even question why it should be a website?
Post reply on HN