Dev post-trains a VLM to catch game bugs Claude misses: 56% to 81%

OdinLovis · x · 2026-11-18

Developer OdinLovis notes Claude can't truly watch video—it samples screenshots every half second, so one-frame glitches and animation bugs slip through, making game debugging hard.

His fix: post-train a dedicated VLM on a large dataset of video games originally built with Claude. The VLM watches every frame, tells Claude what broke and when, and learns Claude's typical mistakes.

Results:

The project ships soon. He argues post-training remains the key to pushing further even when working with closed-source models.

Original post →

More from coding & agent

coding & agent channel →