Thread

1. sznio · 1790095024 · focus · HN ↗

   I'm more excited by the Haiku 5.5 announcement buried in this post. I'm wondering if we will finally get a decently capable fast model.

   1. enraged_camel · 1790097389 · focus · HN ↗

      We use Haiku 4.5 inside our product. It continues to be absurdly capable for converting natural language to structured JSON based on a set of fairly complex business rules.

      1. anthonypasq · 1790098565 · focus · HN ↗

         bro why. its literally the most overpriced model in existence right now. i could name about 10 models off the top of my head that would be better and cheaper

         1. enraged_camel · 1790098935 · focus · HN ↗

            We tried Luna and it scored way lower in our evals. Muse also. We haven't had a chance to test others.

            1. Game_Ender · 1790101386 · focus · HN ↗

               How much time were you able to put into tuning your prompts? And was it worse on all fronts (cost, latency, accuracy) or just some?

Unofficial Hacker News client; not affiliated with Y Combinator.