Thread

Claude Opus 5.5

1806 points · 1134 comments · km144

sharkjacobs · 1790095175 · focus · HN ↗
> “Verbose, hard-to-follow output has been my biggest frustration with frontier models, and Claude Opus 5.5 fixes it
God I hope so
1. kantahayashi · 1790096121 · focus · HN ↗
  The improvement in writing sounds great! I want OpenAI to follow it. Writing in recent models is a disaster.
2. mavamaarten · 1790096337 · focus · HN ↗
  That's literally all I'm hoping for. Is it an insufferable cunt and does it write awful text, or is it nice to work with?
3. lgessler · 1790096849 · focus · HN ↗
  I thought about taking a shot every time Opus 5 said "load bearing", "bites", "teeth" (real oral fixation it had), "real {concern,issue,problem,...}" and realized I'd be dead of acute alcohol poisoning by lunch if I did so.
  1. bibimsz · 1790099390 · focus · HN ↗
    load bearing is oral? what kind of load we talking about?
  2. nonethewiser · 1790101173 · focus · HN ↗
    whats your provenance on that?
4. boc · 1790097038 · focus · HN ↗
  So far in the past 20 minutes it sounds much better in my sessions. Way better than 5.0 so far.
5. fastball · 1790097129 · focus · HN ↗
  It hasn't just fixed it, it has introduced a new paradigm in anti-obscurity.
6. mikeocool · 1790097149 · focus · HN ↗
  That's the load-bearing seam in this blog post.
7. neilellis · 1790097454 · focus · HN ↗
  'frontier models' - seriously, it was you and only you!
8. drbscl · 1790097484 · focus · HN ↗
  So did I. Unfortunately it's even more verbose according to <a href="https://artificialanalysis.ai/models/claude-opus-5-5#token-use" rel="nofollow">https://artificialanalysis.ai/models/claude-opus-5-5#token-u...
  1. Trasmatta · 1790097843 · focus · HN ↗
    The problem with 5 wasn't just the verbosity, but its insane way of communicating. It had this bizarre circuitous sentence structure that always buried the lede, and always tried to be faux profound. I'm okay with verbosity if it's actually readable.
9. unddoch · 1790098060 · focus · HN ↗
  It is hilarious to me that in the examples they show side by side Opus 5.5 still uses 4 times more words than it needs to use. IME, if you eyeball how many words the thing they're trying to say actually needs, and tell them to use only this many words, they become excellent communicators. I assume something about Anthropic's grader for writing just really wants to tick all its tidy tiny boxes of information the models need to cite. It's terrible.
10. thefourthchime · 1790134811 · focus · HN ↗
  I have to say so far Opus 5.5 gives me much better results than Fable 5.1 did. I can actually understand what it's talking about.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.