I have a hunch (based on using the Kimi models to write some clojure) that the article's AST point is exactly wrong. I had to spend a lot of time cleaning up when it miscounted closing parens, which implies that while the LLM may be operating on the AST, mapping to and from the token stream is harder, not easier, when the individual tokens carry less information.
If the author is finding that it works well, I suspect there's something else (code or comment style, maybe) that's compensating for it which didn't seem worth mentioning.
If the author is finding that it works well, I suspect there's something else (code or comment style, maybe) that's compensating for it which didn't seem worth mentioning.