‹ BackHN Continuity

Thread

Claude Opus 5.5

1806 points · 1134 comments · km144

  1. Catloafdev · · focus · HN ↗
    > Opus 5.5 communicates more naturally than prior models. Early testers found its writing clearer and easier to follow, which addresses some of the common feedback we heard about Opus 5.

    Sounds like they noticed the complaints. I'm curious to see what LLM-isms this one may have.

    1. gekoxyz · · focus · HN ↗
      It was difficult to not notice them. Opus 5 was unusable, most of my team went back to Opus 4.6 for most of their work. I hope we can move forward now.
      1. ithkuil · · focus · HN ↗
        It's unbearable but nothing that couldn't be fixed with postprocess.
        1. mavamaarten · · focus · HN ↗
          How? Explicit instructions, memories and even skills have not been able to keep Claude from saying "genuinely" every two sentences and keep it from explaining heavily what something _isn't_.
          1. ithkuil · · focus · HN ↗
            "please repeat, ELI5 without analogies (I'm not a child, just ADHD)"

            works quite well

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.