‹ BackHN Continuity

Thread

Using Opus 5.5 to discover a new eyewitness record of the dodo

226 points · 79 comments · benbreen

  1. nl · · focus · HN ↗
    > Epistemological weirdness

    > They are also notably bad at judging the historical significance of what they find.

    I use LLMs for some things that are outside the more common use-cases (in my case 3D design for 3D printing) and one thing I've noticed is that the errors it makes are so completely unlike human errors that they are hard to anticipate.

    It will do things like build perfect snap catches but put them so the the pieces they are connecting are rotated 90 degrees from how they should be. It's "dumb" error, but hard to say the model itself if dumb because it does other very hard things so perfectly.

    > seven chord groups

    This sounds a lot more like Opus 5.0 than Opus 5.5 TBH. I wonder if that was an earlier investigation because 5.5 has improved that kind of language a lot.

    1. morpheos137 · · focus · HN ↗
      In general llms are weak with spatial reasoning. This seems to be an unsolved problem. Probably because human language is generally imprecise spatially and humans think about spatial problems in visual terms. I wonder if having an llm make a 3d design in a format an image model could check would result in a better outcome?
      1. nl · · focus · HN ↗
        Having used them heavily for 3D model understanding since February I can say it's nuanced.

        Opus 4.6 and 4.7 were bad, but GPT 5.2 and above were very usable. Opus 4.8 was usable, but the GPT 5.x series was better.

        Fable is great.

        Opus 5.0 was interesting. It could solve some problems that Sol 5.x couldn't solve (applying a G2 curve on a 3 way corner where one face was a Bezier curve) but you had to be super prescriptive ("only answer the question"/"only do what I tell you and stop when done") or it would go on a hugely involved validation journey that didn't really achieve a lot.

        Opus 5.5 is better than that was in that respect.

        Sol 6.x is great, and my daily driver for this (I use Opus for coding though)

        Astra can solve problems that Sol can't but for some reason on easy stuff makes uglier solutions.

        For all models it's very interactive though - we aren't at the "agentic design" phase for most things yet.

        Here&#x27;s a sample of what I&#x27;ve been able to get them to design with me: <a href="https:&#x2F;&#x2F;x.com&#x2F;nlothian&#x2F;status&#x2F;2099023496794018067" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;nlothian&#x2F;status&#x2F;2099023496794018067

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.