Earlier quoted context omitted.
A human can deal with right-to-left evaluation by moving the cursor around to write in that direction. An LLM can’t do that on its own. A human given an editor that can only append would struggle too.
Idea: feed the language model the parse tree instead of the textual sequence.
Yep, that's exactly what my MCP server is doing -- write in a Python-like language (I called in Qython), parse into AST tree, write the q code.