Use case:
Building a personal RAG system as a weekend project.
Tool used:
OpenHands and Trea, both running in Docker.
Cost in $:
$60
Cost frequency:
One-time (over 3 weekends)
Cost includes:
Mostly API usage and infrastructure
Satisfaction:
Low (10%?) — the final system worked much worse than `ripgrep`.
The AI often produced unusable or overcomplicated results.
I ended up spending more time debugging than... vibing.
Usefulness:
AI is helpful for certain programming tasks, and GitHub Copilot can be useful (when it’s not overeager). But in this case, the “vibe coding” approach felt inefficient and frustrating. Might’ve been better with higher-end tools, but hard to say.
I tried getting ChatGPT to generate a Goldberg polyhedron in Three.js. No matter what prompt adjustments I tried, the most it could come back with was a spinning blob of random polygons mushed together like a crumpled up ball of paper
Here’s what my experience looked like.