Live data from Hacker News

Launch HN: A0.dev (YC W25) – React Native App Generator

news.ycombinator.com

101–106 of 106 posts

Re: Launch HN: A0.dev (YC W25) – React Native App Generator

#101

Can Bolt.new not generate react native code?

They launched support for this today. We expect them to be a strong competitor but we think our experience developing indie apps and the fact that we're laser focused on Mobile Apps will help us win.

Re: Launch HN: A0.dev (YC W25) – React Native App Generator

#103

How is this different from just using Cursor on my react-native codebase? Cursor in agent mode means: no copy paste, implements features and fixes errors iteratively, knows my codebase and adheres to existing patterns. If I need changes, I just ask Cursor and preview live app changes locally

Cursor is for programmers. Ultimately, you decide what the code should be. v0/lovable/a0 will replace drag-and-drop "no-code" tools for non-programmers who don't care about code and only decide what the product should do. The tool will likely also manage hosting, either directly or through service providers, to ensure a seamless e2e experience, automatically fix runtime issues etc. The question remains, will there be…

This is good. I really didn't think of that aspect.

Re: Launch HN: A0.dev (YC W25) – React Native App Generator

#104
post #16

Congrats on shipping. I'm curious how commodotized the underlying LLM's are for generating this type of code? (And thereby, how big the moat is for companies like vercel/bolt surrounding v0 et al). What models are you using to power the code editor? Did it require much customization? Is it likely that enterprises would be able to eventually bring their own LLM's, or does the training make that prohibitive?

Bolt is actually open source. You can see how it works https://github.com/stackblitz/bolt.new

Doubly if we're counting. https://github.com/stackblitz-labs/bolt.diy

Re: Launch HN: A0.dev (YC W25) – React Native App Generator

#106
post #22

The chess game it generated is pretty sad: https://ibb.co/5Xk57m5k

This demonstrates pretty much exactly how LLM-first development is in 2025: the hallucinated code compiles, but it's absolutely useless.

Yeah, no. Haven't had an LLM fail at a task in months. Do you seriously think so many people would be Cursor customers if all it produced was useless?
Post reply on HN