Thread

1. seunosewa · 1790793463 · focus · HN ↗

   I use a different LLM family to review commits and write detailed descriptions. If a commit was written with Fable/Opus, I use Sol/Astra to write a well reasoned commit message. If the message doesn't match my intent, then that triggers a manual review.

   1. loopmonster · 1790793643 · focus · HN ↗

      If the second LLM is just describing the content of the commit doesn't that defeat the purpose of the description, to capture the context that doesn't make it to the code?

      1. seunosewa · 1790794092 · focus · HN ↗

         The second LLM is prompted to actually research the code, not just the diff, with fresh eyes to figure out what it does and why, before writing the commit message.

         1. GrinningFool · 1790795197 · focus · HN ↗

            But the code doesn't always have the answer to "why". At best that means the commit-writer has 'guessed' at why.

Unofficial Hacker News client; not affiliated with Y Combinator.