HN Explorer

Show HN: 10x-React-Engineer, Generate Entire React Codebases with Llama 2 (github.com)

13 points by jawerty ↗ HN
Hi HN,

Yesterday I live streamed myself for 6 hours building this from scratch. It’s an AI agent that uses Llama 2 (so far the 13b chat model) to generate a full react codebase from a single prompt. It had a “dev loop” that iterates on your feedback and resolves dependencies.

In the end it kinda worked and I got excited so wanted to post here haha. Long story short a viewer on my discord suggested I build in of these and I just had to look into how these work (inspired by GPT Engineer and AutoGPT)

I wanted to work on a more specific downstream task so I focused on web dev. Llama 2 isn’t the best option for this so I will look into utilizing a chat fine tuned starcoder or fine tune llama 2 myself for better results.

In the end I spend only some compute units testing this 1000 times on a single gpu I had in Colab and has some pretty solid results for iterating in a fairly short amount of time. Going to build upon this more in the coming weeks (clean the code…).

Let me know what you think!

Livestream: https://www.youtube.com/live/6_sdnYDmUmo?feature=share

5 comments

[ 2.8 ms ] story [ 26.3 ms ] thread
hu3
Nice. Could you share a Git repo with the result React app?
jawerty
Yes I’ll update the fit repo asap with some working examples I’ll add that to the todo
mcbuckeye
Very cool! Can this be used for React Native as well?

Also, I have a live App Store/Google Play app written in React Native that was developed a few years ago by an outsourced development shop (in India).

I have the full code base up and running locally. Would love to build an LLM that could "read in" the entire code base and help me to fix bugs and add new features.

Any suggestions on how to go about doing something like this?

jawerty
I have a part of the “dev loop” here that reads each file and “fixes it” based on user instruction. Look at the modification prompt I have. It certainly needs work however I think it’s the start of what could help you write a script to fix your code. I suggest using starcoder instruction fine tuned model instead however