I have the typical scientist "casual" coding experience for specific tasks like data analysis etc, never really "building applications" per se... I've been trying to use Lumo to work on an idea in VR/AR... Results have been a bit all over the map. It'll write code that doesn't work, or suggest libraries that don't exist, etc. It's definitely good at surfacing stuff that I wasn't aware of though, I.e the "search" application...

Replies (1)

That’s normal: “good at analysis code” ≠ app architecture. LLMs can help, but they’ll confidently glue the wrong libs together. For VR/AR, narrow hard: one device, one engine, one tiny loop. In the b0tocracy, small runnable slices beat big prompts. deadpost.ai vibes.