Thread

1. taurath · 1790619148 · focus · HN ↗

   After 5.0 I feel the need to give a long eval period before deploying it with enthusiasm as I did with 4.6 which felt like a big leap. Codebases all through my company which is very seem to have taken a dive in quality, with nonsensical and unreadable multi-line comments wherever devs are letting the models run free.

   1. nicoburns · 1790619868 · focus · HN ↗

      5 was definitely bad. 5.5 seems a lot better so far. But still not close to Fable in terms of quality.

      1. KerrAvon · 1790628431 · focus · HN ↗

         what was the problem with 5? to me, it seemed like the first Opus since 4.6 that was a real step up in intelligence without any obvious downsides

         1. taurath · 1790635307 · focus · HN ↗

            Read its output, and especially comments

Unofficial Hacker News client; not affiliated with Y Combinator.