Ask HN: Is Opus 5.5 another step change? | Hacker News Reader

Ask HN: Is Opus 5.5 another step change?

19 pointsconsumer45120 comments

This feels like another moment, like earlier this year, and the year prior. I am thrilled for my use cases in the applications that I build with CC, and for the LLM API usage that I sell. However, it honestly scares the crap out out of me.

Is "the exponential" an actual thing?

View on HN

Yes, Opus 5.5 and Astra-6 are big improvements over Opus 5 and Sol-5.6. I'm at a point where I can automate much of my workflow, even for complicated tasks, which I could never do before.

Also the new Xiaomi model, Mimo v2.6, is outstanding as a light and cheap model. For coding, the new meta is using Astra-6-Max for orchestration and architecture, and Mimo for grunt work.

Yep, I'm personally finding Opus 5.5 to be the first real leap I've felt since Opus 4.5. The time-to-first-token seems dramatically better in Claude Code compared to Fable 5.1/Opus 5 as well, which really helps both interactivity and also overall time-to-completion.

It also burns Claude subscription quota much more slowly than Fable, which is nice.

Anthropic's naming convention seems to follow an S-curve. So Opus 5 is actually a little worse than 4.7, but by the time it hits 5.5, it's at the steep part of the new S-curve.

Similar with Claude 4 being worse than 3.7, but peaking at 4.5. At 4.6 they started to hit the restrictions and 4.7 seemed to patch what they made worse.

I’m also finding Opus 5.5 to be a significant advance. In the past few days, I’ve given it several complex tasks related to two long-term dictionary-building projects [1, 2], and it handled them impressively—similar to Fable but with much lower token consumption. It also communicates better than Opus 5.1; I don’t think I’ve seen any obvious Claudisms yet.

[1] https://www.tkgje.jp/

[2] https://tkgally.github.io/eex-dict/index.html

i dont see any massive changes between opus 5 and opus 5.5 i think it burns more tokens then opus 5

I have Opus 5.5 running subagents for the last 20h without any input from me after developing a plan and it seems to be going well somehow... but I will find out soon...

20h with no input is insane

at that point the hard part is just trusting it didnt quietly go off track somewhere imo

I've been checking it and it's doing great I'm sure there are some bugs but it's doing a huge bulk of tedious simulation logic for my game. I was previous in the loop quite a bit but I found myself never having to redirect it so I tried the here a giant plan /loop until its done

First of all, I consider it very expensive, somehow in the range of Fable:

I activated Opus 5.5 when the invitation popup showed up, and Im already paying as a pro-user - nontheless the usage of Opus 5.5 charged massivly additional on the last few days, around 12-13 USD per day.

Im still fine with Opus 4.6 or 4.8 for daily development.

I just love that it knows how to form its thoughts into meaningful statements without rambling again.

I find that Opus 5.5 compared to previous versions (after 4.6) is the first update in the right direction.

It's the first model that I feel I can just use freely without crashing into the 5 hour limits. I just manage to get my work done and still have tokens left over

I stopped thinking that much about quota usage, there is less of accidental +10% weekly quota in 5 minutes.

Feels like a faster and cheaper fable, which yes is a big jump.

yea, apparently you dont need to know Rust

"Personally, I felt that Opus 5.0's performance dropped a bit right before 5.5 was released. When 5.5 came out, it felt slightly better than the 5.0 at that time."

well, not really , it is not that much of big step.

It's less shit, so that's good I think.

astra on ultra still blows it out of the water

No. Next question ?

Reply on news.ycombinator.com