Comment by sosodev
1 day ago
In my experience, even with basic project concepts the small models struggle to spin up greenfield stuff. There's just too many decisions to be made and they're not good at that.
Modifying existing code is way easier if you don't expect it to be smart about it. Don't say "add X feature" and let it explore the codebase and build its own understanding. Point it at the relevant files and say "the goal is to add X feature to this code, follow Y guidelines". Now you've done the hardest part of making the decisions and it just has to follow instructions while coloring within the lines.
>Point it at the relevant files and say "the goal is to add X feature to this code, follow Y guidelines".
Is that not how you would work with any model, local or not? I wouldn't trust it to make the right decisions unattended. I just know the moment I look away it's going to do something utterly braindead.
Claude Opus with xhigh thinking is surprisingly good at figuring our details. Granted I'm only using it for little hobby projects, nothing overly complicated.
I had good results doing an open box reimplementation. Gave qwen access to my old projects and it rebuilt it on JAX.
https://github.com/verdverm/pge-jax