[wat10000]

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.

[anticensor]

Idea: feed the language model the parse tree instead of the textual sequence.

[gabiteodoru]

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.

[wat10000]

Might help. You could also allow it to output edits instead of just a sequence. Probably have to train it on edits to make that work well, and the training data might be tricky to obtain.