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. nicoburns · 1790630353 · focus · HN ↗

            It was really verbose and pedantic. I'm sure that made it more thorough. But compared to Fable (which it wasn't much cheaper than) where you could get the same rigour and more with a lot more concision, it was a tough sell. 5.5 is a lot cheaper and seems a lot better balanced.
         2. taurath · 1790635307 · focus · HN ↗

            Read its output, and especially comments

Unofficial Hacker News client; not affiliated with Y Combinator.