Re:
by wat10000 on Wednesday July 09, 2025 @11:13AM
(#44511022)
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.
[ Parent
| on HN ]
Re:
by anticensor on Wednesday July 09, 2025 @12:44PM
(#44512149)
Idea: feed the language model the parse tree instead of the textual sequence.
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.
Re:
by gabiteodoru on Sunday July 13, 2025 @06:06PM
(#44554200)
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.