Re:Literate programming: Knuth is doing it wrong (2014)
by flir on Monday January 13, 2025 @11:22AM
(#42685129)
LLM's tend to write classic "what, not why" comments/commit messages. The idea of the LLM interrogating the programmer for the "why" is interesting, though.
Or maybe reading the ticket? (That might just be moving the problem somewhere else though).
Re:Literate programming: Knuth is doing it wrong (2014)
by toxik on Monday January 13, 2025 @11:10AM
(#42684993)
I wonder if an LLM could make ”atomic commits” out of my N pending changes.
Re:Literate programming: Knuth is doing it wrong (2014)
by nzach on Monday January 13, 2025 @12:38PM
(#42686102)
It almost can... You can use something like gptcommit to automatically create a commit message. But the results are pretty bad. It can't produce anything beyond placeholder/filler text.
I don't need a message explaining we introduced a if to return when i is greater than len(items). I want a commit explaining why it blew up in production after being in production for over a year. What changed ? Did it had any other implications ? There is any ticket for this bug, or maybe a thread in slack ?
JK, the LLM will get bad input and it will spit out bad output.