This new AI model is crazy fast at coding 🤯
Farhan
Visit on X@mhdfaran78K followers
60,769 views
This new AI model is crazy fast at coding 🤯
It fixed a broken backend in one prompt and around 83 seconds.
I tested Space Bunny inside OpenCode with a FastAPI repo. It had 3 failing tests caused by broken order filtering, unsafe money calculations and incorrect product ranking.
I didn’t tell it where the bugs were.
It read the product contract, inspected the code, found the root causes and fixed everything. Then it added 2 edge-case tests on its own.
The final result:
3 failing tests → 6 passing tests
Only 2 files changed
Public API untouched
It made one small CLI mistake during the run, but the final patch was clean.
Tbh this is the kind of speed I expect from a Flash-level model.
Not just fast output. Fast useful work.
3 Comments
Comments from the original post on X (Twitter)

@AndrewBolis
Adding edge case tests on its own is a nice touch.

@abxxai
Fast code is nice, but fast bug hunting is the real test.

@GeniusPothead
fastapi repo bugs gone that fast honestly kinda scary good
