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. chewchewchew · 1791060895 · focus · HN ↗

      9 hours?!

      1. rdli · 1791061182 · focus · HN ↗

         Yes. It spawned multiple subagents to run different experiments to benchmark a lot of different things, reviewed CI logs from past runs, etc. In the end, there were changes to what/how we cached, various code quality checks, speeding up test runners, and many other things.

         1. Tade0 · 1791063459 · focus · HN ↗

            I dare not ask about the cost, having burned $60 on a task running for 1h 16min once.

            1. rdli · 1791063886 · focus · HN ↗

               I’m on the $100/month subscription; this session took about $500 in token-equivalent costs.

               (Note that it wasn’t all Opus 5.5; I have a setup that uses Fable 5.1 as an advisor, Sonnet 5.5 for mechanical changes, etc.)

               1. tripleee · 1791065126 · focus · HN ↗

                  God I hope the prices drop quick. Once they stop subsidizing it these kinds of workflows will be unaffordable for anyone who isn't already wealthy

                  1. wyre · 1791067794 · focus · HN ↗

                     Pricing is dropping quick. Inference is so cheap, I think they are losing a lot less money selling subscriptions than you think. It might even be more expensive managing the load, than actually selling the tokens at subscription prices.

                     We are seeing with OpenAI, allegedly through their new pricing scheme, as intelligence and model efficiency increases they offer the same throughput while advertising 1/2 as much usage, letting Astra consume more usage, essentially only being available to those wealthy enough to afford it while still offering essentially unlimited Sol and Luna to their subscription tiers.

                     Also if you're cache hit rate is high enough a billion tokens tokens from Deepseek 4.1 Flash costs less than $15.

Unofficial Hacker News client; not affiliated with Y Combinator.