Comment by grey-area
1 day ago
Or maybe it's just not as good as it's been sold to be. I haven't seen any small teams doing very big things with it, which ones are you thinking of?
1 day ago
Or maybe it's just not as good as it's been sold to be. I haven't seen any small teams doing very big things with it, which ones are you thinking of?
you are not wrong. the only 'sane' approaches ive seen with vibe coding is making a PoC to see if some concept works. then rewrite it entirely to make sure its sound.
besides just weird or broken code, anything exposed to user input is usually severly lacking sanity checks etc.
llms are not useless for coding. but imho letting llms do the coding will not yield production grade code.
Koko the gorilla understood language, but most others of her ilk simlpy make signs because a thing will happen.
Move hand this way and a human will give a banana.
LLMs have no understanding at all of the underlying language, they've just seen that a billion times a task looks like such and such, so have these tokens after them.
What does it matter if they have understanding of the underlying language or not? Heck, do humans even have the "understanding of the underlying language". What does that even mean?
It's a model. It either predicts usefully or not. How it works is mostly irrelevant.
9 replies →
There’s been a lot of criticism that Koko’s language abilities were overblown and her expressions were overinterpreted as well.
POC approach seems to work for me lately. It still takes effort to convince manager that it makes sense to devote time to polishing it afterwards, but some of the initial reticence is mitigated.
edit: Not a programmer. Just a guy who needs some stuff done for some of the things I need to work on.
For a second I thought PoC meant Piece of Crap XD
A team of 9 people made Base44, a product for vibe-coding apps, and sold it for $80M within 6 months.
https://techcrunch.com/2025/06/18/6-month-old-solo-owned-vib...
That's just an example of surfing on the incestuous hype, they created a vibe-coded tool that was bought by Wix to help vibe-code other stuff.
Is there any example of successful companies created mostly/entirely by "vibe coding" that isn't itself a company in the AI hype? I haven't seen any, all examples so far are similar to yours.
Yeah, that's like those crypto/nft "products" that just let you move crypto/nfts around.
A team of 9 created or vibe-coded a product?
As always, two things can be true. Ignore both the hucksters and the people loudly denigrating everything LLM-related, and somewhere in between you find the reality.
I'm in a tiny team of 3 writing b2b software in the energy space and claude code is a godsend for the fiddly-but-brain-dead parts of the job (config stuff, managing cloud infra, one-and-done scripts, little single page dashboards, etc).
We've had much less success with the more complex things like maintaining various linear programming/neural net models we've written. It's really good at breaking stuff in subtle ways (like removing L2 regularisation from a VAE while visually it still looks like it's implemented). But personally I still think the juice is worth the squeeze, mainly I find it saves me mental energy I can use elsewhere.
I've seen small teams of a few people write non-trivial software services with AI that are useful enough to get users and potentially viable as a business.
We'll see how well they scale.