Schneider says Moderne was well-suited to LLMs due to OpenRewrite’s Lossless Semantic Tree (LST) code representation — a structured representation of source code that enables deeper semantic understanding while retaining the original details (e.g. whitespace, comments, and syntax). Originally, this was designed for an OpenRewrite feature called Recipes, but it ended up being the “ideal data source” for what OpenRewrite is now doing with AI.
You are viewing a single comment's thread from: