I built a tree format for LLM code edits. Against a fair baseline, it only wins where structure matters
When an LLM edits code, it usually works on text: it rewrites the file, or it finds a string and replaces it. I wanted to try the other way around. The model edits a tree , a checker validates it before anything is written, and a printer is the only thing that produces source. That's Nodast ( Node…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-06 00:36 · DEV Community — AI
I built a tree format for LLM code edits. Against a fair baseline, it only wins where structure matters