News for hackers. Stuff that matters.

A comment on Ask HN: Have any successful startups been made by 'vibe coding'?. Parent comment

Re:Ask HN: Have any successful startups been made by 'vibe c... by stavros on Tuesday August 19, 2025 @11:27AM (#44952694)
What's the largest app you've entirely vibe-coded with this architecture? For me, everything fails at a few hundred lines, no matter how micro you keep your services.

Mind you, we're talking zero review at all, just using whatever the LLM produces.

[ Parent | on HN ]
Re:Ask HN: Have any successful startups been made by 'vibe c... by paulcole on Tuesday August 19, 2025 @02:07PM (#44954456)
Funny how devs here used to love bragging about how their job isn't to write code and that they shouldn't be measured on LOC.

Now suddenly the problem is that AI can't write a lot of code.

[ Parent | on HN ]
Re:Ask HN: Have any successful startups been made by 'vibe c... by surgical_fire on Tuesday August 19, 2025 @02:58PM (#44954994)
Both can be true.

LLMs have an unsolvable problem of "hallucination". It is a bad description of what the problem is because hallucination is all they do, it just also happens to be correct in many cases. The larger the codebase or the problem space, the less accurate LLMs tend to be.

And developers to a lot more than generating LOC.

[ Parent | on HN ]
Re:Ask HN: Have any successful startups been made by 'vibe c... by stavros on Tuesday August 19, 2025 @02:15PM (#44954539)
No, the problem is the AI can't avoid making mistakes often. I'm not measuring it on LOC.
[ Parent | on HN ]
Re:Ask HN: Have any successful startups been made by 'vibe c... by JohnBooty on Tuesday August 19, 2025 @09:39PM (#44957909) 

   Now suddenly the problem is that AI can't write a lot of code.
That's not the problem at all. AI can obviously write lots of code faster than a human.

The problem is that AI can't currently write large quantities of correct and maintainable code to create a larger app.

(For some value of "larger")

[ Parent | on HN ]