Thread

1. rdli · 1791060574 · focus · HN ↗

   It’s a really good model. Over the past few days, I give Opus some general directives to basically speed up our CI, and telling it I care both about billing minutes and wall clock time. I told it to create a plan after analyzing everything in our CI, run the plan by a Fable subagent, and then focus on low-risk, high-reward changes.

   9 hours later, I had 12 PRs ready to be merged, and the net result is CI time has dropped from ~10 minutes to ~4 minutes, and billing minutes have dropped around 60%. Less than an hour of my attention.

   1. moltar · 1791100318 · focus · HN ↗

      But was the code of high quality or a mess?

      Because I noticed people at my work did similar requests to improve CI. The result was a faster CI, but full of cludges huge inline bash scripts in workflow YAML files, and effectively unmaintainable, unreviewable mess. After just a few rounds of these optimizations the entire CI setup is basically a Rube Goldberg machine but made of duct tape.

      1. Shorn · 1791171980 · focus · HN ↗

         > Less than an hour of my attention.

         There's your answer right there, no need to ask.

         Without human advice and a metric shit-tonne of guidance (either pre or post) - anything that requires active consideration of future maintenance burden will cost you 2x-10x of the time you think "saved" over a medium-term time-frame.

         The alternative is to spend at least 50% (or sometimes up to %100) of the "saved" time in active review and iterative improvement of the solution design.

Unofficial Hacker News client; not affiliated with Y Combinator.