As long as it's not as verbose as Opus 5, I am quite happy with a better version that's also less expensive. I will test it tonight. Grok 4.7 was horrible, and for mundane tasks I am relying on DeepSeek Flash 4.1 with great success using OpenCode.
It crushes Fable on benchmarks and even in the blogs "real-world" studies. But... they are communicating like it ~sometimes~ provides Fable intelligence?
A bit confusing, otherwise I would assume this is a complete replacement for Fable across the board??
I have just switched to 5.5. First mistake was stale environment variable, didn't realize it was replaced, "oh my memory had stall data" and that's it. Second one, a powershell command had the wrong syntax. Great for my first two prompts.
I'm glad they specifically called out the prose issue, I was always pinned to Fable 5.1 because I wanted to avoid the unreadableness of other Anthropic models.
> It performs at the level of Claude Fable 5.1 on most work
Fable feels a bit dated after using Astra. Progress is nice (just like Grok 4.7) but I'm looking forward to the next big release as I can't fully commit to Astra atm.
> In the coming weeks we will also be expanding access to our Cyber Verification Program, and verified cybersecurity practitioners will be able to use Opus 5.5 for their work.
I was accepted into the CVP a little while ago. Does this mean I'll need to apply again?
>> On our benchmarks, Claude Opus 5.5 leads in agentic coding, computer use, and knowledge work. That said, at these levels of capability we’ve found that benchmark margins have become a less reliable guide to real-world differences. In our own use, the gap between Opus 5.5 and Claude Fable 5.1 is narrower than these scores suggest.
Finally confirmation that Haiku was not forgotten and will be coming soon, althouhg I find it quite interesting they skipped 5 and directly skip to 5.5 with all models, including Sonnet which is not super old. I suspect they found something breaking that allows to release this. Recently they struggled with keeping up a 50 % weekly limit increase and now they're putting out 30-40% faster and cheaper models even faster, with much more better benchmarks, a limt reset command and five hour limit increase. It seems more like the opposite and as if they never struggled, thus, I very much believe they found something very effective and new.
I'll have to try 5.5 on my work's Cursor account. If they really solved the communication issues, I might consider moving my personal account from Codex back to Claude Code.
> Communication. 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. It puts the most important information up front, and its style makes it a better work partner over long sessions. As one early tester put it, “it writes the way I do.” In our own use, this has made Opus 5.5’s work easier to follow and check—which is a safety benefit as well as a practical one.
I think this is what I'm most interested in. I mostly moved to Astra because I just can't work all day with the Claude Opus 5/Fable writing style. I've don't think Astra is a better model, but it's the first OpenAI one that seemed good enough for me. Definitely keen to try Opus 5.5 and see if this claim is real.
> hi, can you explain how the scheduler works. keep it brief, but include important correctness details
some excerpts:
>Flow:
1. Data arrives. The appender calls prepare/commit around the krolik write. The prepare step leaves a phantom row, so a write that is still in flight is tracked. The commit publishes STREAM_INPUT.
2. Poll. It first reclaims expired leases. Then it sweeps sdirty (a candidate index) in a rotating order, oldest since first, which prevents starvation. It re-derives the exact period and rewind for each candidate from snode_out/snode_in, then claims it: writes the sassign lease plus a per-edge sassign_edge snapshot.
3. Complete. Each edge's watermark is set to the snapshot taken at dispatch. Anything published after that gen stays dirty automatically. A failed or partial job writes nothing, so its dirt persists.
> - Folds are monotone single statements. gen only goes up, extents only grow, processed periods only union, rw_start only moves earlier. So replays, out-of-order writes, and concurrent writes can at worst hold a watermark back. The worst outcome is a spurious rerun, never lost work. There's no read-modify-write and no truncation of the dirty period, so a write that lands during a job can't be swallowed.
> - Rewrites are declared by the publisher, never inferred from overlap. An unflagged write that overlaps already-processed data means "unchanged", which makes retries and redelivered tasks free. Each publisher has its own reason for being sound (see the table in scheduler/CLAUDE.md). A new publisher needs a row in that table.
> - NULL means dirty, and DELETE is the fence. Every node and edge has a row from the moment it's created. A lost parent or a settings-only edit can't be derived, so both go through one forced-rerun path: capture_rewinds reads the processed span before the DELETE, and apply_rewinds publishes it as a rewrite on a config root.
All the non-standard programming jargon is stuff from the repo. I can actually read it and understand what it's talking about. I used Fable to handle Opus 5 as I just couldn't stand it. With this I'll probably go back to Opus.
Oof thanks for sharing, that seems just as bad if not even worse than Opus 5 to me. Just about every sentence is painful. Particular standouts that a human would never write:
> Rewrites are declared by the publisher, never inferred from overlap
That's the standard annoying pattern though: "Rewrites are declared by the publisher, never inferred from overlap." and "NULL means dirty, and DELETE is the fence." - still the same LLMisms. I didn't expect them to disappear, but it's not a radical improvement either.
This one is pretty terrible (right after “The worst outcome is a spurious rerun, never lost work.”). We’ve got lands, hyphenation, strange noun/verb sentence order and an unnecessary analogy word (swallowed).
> There's no read-modify-write and no truncation of the dirty period, so a write that lands during a job can't be swallowed.
That's the main reason I'm using GPT models. I'll ask Fable to analyze something, then pipe its output straight through Astra without even looking at it first.
You are right and make an important insight. While well meaning and amusing, it did not reflect the entire spectrum of outcomes that could arise from the worktree.
Navigating the landscape of agentic levers certainly requires a more detailed approach than this and you were certainly correct to push back.
I had a moment pretty much like that, only a few days after visiting that parody website and thinking it was exaggerated.
I requested a background color change and it added a border. I asked to remove the border and it added a hover state. Removed the hover state and it put the border back. Ended up relenting and keeping it as-is; I imagine during training, always taking generic usability concerns regardless of user intent helps it achieve better scores, but gives it too much “agency” when a human is driving it.
I've been using Opus 5 since it was released and don't understand all the hate it gets. It very well could be something in my own local memories or Claude.MD files that prevents it, but I certainly have never experienced something like that site portrays.
Yes this is a big part of what has turned me off Opus 5 completely. The other (more dangerous) one is how often it gets assumptions wrong. These both (along with Astra) caused me to split my time 50/50 now between the two models.
Not a day goes by when I push back on something, to which Opus 5 very unambiguously say "You were right, I was wrong" - this never happened so often with past models, nor with Fable.
We'll have to see how much Opus's ability to communicate has improved. It's already giving me better summaries of where we are in the conversation.
So far it seems the same. I used Opus 5.5 for an hour this evening and it was just as painfully verbose as Opus 5. It also used the term "load bearing" 4 separate times.
I noticed that when opus 5.5 was on parts on my codebase that had lots of 5.0-generated comments, it picked up its style. Unfortunately I think 5.5 has been trained to mimic what it sees so that you can ease up on the instructions, but this does mean parts of your codebase that 5 touched will be somewhat viral.
I gave it some vibecoded patch someone created with Opus 5 with the task of together figuring out the real root cause and what to do about it.
Big mistake. The rest of the session was all claude-speak up until I've rage-quit and restarted with Qwen and no context other than "here's what I think we've missed in the current implementation. How could we approach that?"
GLM felt like it got at least 20 IQ points dumber just from being exposed to claude's writing.
If anything it seems worse. I'm experiencing about -10% insufferable jargon, but +30% more verbosity. It's unredeemable. There also seems to be even less structured output (headings, bullets, etc).
I'm surprised that you're getting so many replies saying it's the same. So far in my usage today Opus 5.5 does seem like a noticeably better writer. Opus 5 frequently made me want to strangle it while 5.5 has been producing a lot less incomprehensible gobbledygook.
Yeah I’m having a much better time reading Opus 5.5 output today vs. 5’s wall of nonsense. You still get a few telltale turn of phrases, though the load-bearing smoking guns haven’t turned up yet. It’s still a bit verbose compared to what I’d ideally like, but it’s tolerable now.
Code-wise it seems to still nitpick, especially in reviews, but it doesn’t seem to rabbit hole quite as badly on tangents and scope-creep. These are just first impressions though. It’ll take a few weeks of regular use to really have a sense of it.
I know we're all experiencing NDFSMs differently, like that's part of the whole problem, but 5.5 just gave me "The truncating quantizer collides two oranges", which is a new low for me.
Like the sibling comment says, text is always "true" in the sense that it's reacting to context correctly. So yes, true, but insufferable.
Ironically, what I'm working on a post-processing hook for colorizing and summarizing responses without degrading the session quality. So "truncating" = summarizing, "quantizer" = char limits and thresholds, "collides" = conflicts, "two oranges" is referring to the "alert level colors" where a second model (Haiku/Sonnet) colorizes text based on the perceived (or suggested) priority of a response's statements (e.g. "just so you're aware, I didn't commit" is fucking useless and it needs to be blacked out).
So the original insufferable statement translates to something like "The code that checks whether a sentence is too verbose was conflicting with the part that colorizes the text."
P.S. Let me know if there's something out there that exists like this- something that adds a dimension like color or tabular reporting on a per-response basis. So far all I've seen is 2 dozen ~100k starred GitHub plugins that add zero value or make things worse.
I worked with Astra for two weeks and the output was really bad compared to Opus. It made so many wrong decisions within C++, Go, Python and Typescript code bases. My college made the same experience and we moved back to Claude.
I don't know what they did but opus is really good while Astra/Sol are comparably bad. For my own tests and taste this might be the first time (fable perhaps excluded) where claude models are better than openai, since codex 5.3.
I would happily pay more for a claude model that performs the same but speaks normal English. The proliferation of claudespeak in the workplace is driving me insane. Every ticket, every PR feedback, every comment in the codebase is poisoned with its ridiculous unnatural vocabulary
So is it cheaper? Are we AGI yet? Am I left behind? I didn't have patience for the intro animation on the website... maybe one day, Claude Code will understand accessibility but that day is not today.
Excellent, maybe Anthropic can use it to fix Claude Code Desktop kicking me back to login every week or so, and forgetting whole state (opened windows = the only way of managing active working set) when I sign back in, if it's that good.
Seriously, both flagship GUI apps (OpenAI and Anthropic) are a full of glaring UX issues (for ChatGPT it's not naming their windows, so window switcher has 10 entries of "ChatGPT" and you can cycle them all to find the one you want).
I don't care how good their models get, I won't sign up for one of their plans until they define "X" in their pricing. 5X of this plan, 20X of that plan means nothing when they never tell you what "X" is.
Maybe this model can finally figure it out for them.
258 comments
[ 0.15 ms ] story [ 5.8 ms ] threadI tried Opus 5 and Astra.
A bit confusing, otherwise I would assume this is a complete replacement for Fable across the board??
Fable feels a bit dated after using Astra. Progress is nice (just like Grok 4.7) but I'm looking forward to the next big release as I can't fully commit to Astra atm.
I was accepted into the CVP a little while ago. Does this mean I'll need to apply again?
Wdym Opus 5.5 scores 14.7% higher than GPT Astra for Terminal Bench 4.0?
How would this alleged difference (most likely bs) actually show up in reality?
GPT Astra was literally the best model in the world by a margin until 1 hour ago or so.
>> On our benchmarks, Claude Opus 5.5 leads in agentic coding, computer use, and knowledge work. That said, at these levels of capability we’ve found that benchmark margins have become a less reliable guide to real-world differences. In our own use, the gap between Opus 5.5 and Claude Fable 5.1 is narrower than these scores suggest.
> how would this alleged difference (most likely bs) actually show up in reality?
Furthermore: so they admit it's bs but still placate it like its the next sh*t ... alright
All I'm saying I refuse to buy into it anymore – yet many on here still do, including ... you?
I think this is what I'm most interested in. I mostly moved to Astra because I just can't work all day with the Claude Opus 5/Fable writing style. I've don't think Astra is a better model, but it's the first OpenAI one that seemed good enough for me. Definitely keen to try Opus 5.5 and see if this claim is real.
> hi, can you explain how the scheduler works. keep it brief, but include important correctness details
some excerpts:
>Flow: 1. Data arrives. The appender calls prepare/commit around the krolik write. The prepare step leaves a phantom row, so a write that is still in flight is tracked. The commit publishes STREAM_INPUT. 2. Poll. It first reclaims expired leases. Then it sweeps sdirty (a candidate index) in a rotating order, oldest since first, which prevents starvation. It re-derives the exact period and rewind for each candidate from snode_out/snode_in, then claims it: writes the sassign lease plus a per-edge sassign_edge snapshot. 3. Complete. Each edge's watermark is set to the snapshot taken at dispatch. Anything published after that gen stays dirty automatically. A failed or partial job writes nothing, so its dirt persists.
> - Folds are monotone single statements. gen only goes up, extents only grow, processed periods only union, rw_start only moves earlier. So replays, out-of-order writes, and concurrent writes can at worst hold a watermark back. The worst outcome is a spurious rerun, never lost work. There's no read-modify-write and no truncation of the dirty period, so a write that lands during a job can't be swallowed.
> - Rewrites are declared by the publisher, never inferred from overlap. An unflagged write that overlaps already-processed data means "unchanged", which makes retries and redelivered tasks free. Each publisher has its own reason for being sound (see the table in scheduler/CLAUDE.md). A new publisher needs a row in that table.
> - NULL means dirty, and DELETE is the fence. Every node and edge has a row from the moment it's created. A lost parent or a settings-only edit can't be derived, so both go through one forced-rerun path: capture_rewinds reads the processed span before the DELETE, and apply_rewinds publishes it as a rewrite on a config root.
All the non-standard programming jargon is stuff from the repo. I can actually read it and understand what it's talking about. I used Fable to handle Opus 5 as I just couldn't stand it. With this I'll probably go back to Opus.
> Rewrites are declared by the publisher, never inferred from overlap
> NULL means dirty, and DELETE is the fence
> There's no read-modify-write and no truncation of the dirty period, so a write that lands during a job can't be swallowed.
> Rewrites are declared by the publisher, never inferred from overlap.
This style of writing is idiotic because it conveys no additional information. It's no different from stating
> Rewrites are declared by the publisher, never when moons collide.
The two sentences are actually logically identical. No idea why these models keep writing like this.
Navigating the landscape of agentic levers certainly requires a more detailed approach than this and you were certainly correct to push back.
I requested a background color change and it added a border. I asked to remove the border and it added a hover state. Removed the hover state and it put the border back. Ended up relenting and keeping it as-is; I imagine during training, always taking generic usability concerns regardless of user intent helps it achieve better scores, but gives it too much “agency” when a human is driving it.
Fable 5.1 is a lot better than Fable 5 btw. Not sure about opus 5.5 yet since I’ve only got one session in so far.
Not a day goes by when I push back on something, to which Opus 5 very unambiguously say "You were right, I was wrong" - this never happened so often with past models, nor with Fable.
We'll have to see how much Opus's ability to communicate has improved. It's already giving me better summaries of where we are in the conversation.
and i think i was generally more tolerant of 5.1's writing style than most people.
I gave it some vibecoded patch someone created with Opus 5 with the task of together figuring out the real root cause and what to do about it.
Big mistake. The rest of the session was all claude-speak up until I've rage-quit and restarted with Qwen and no context other than "here's what I think we've missed in the current implementation. How could we approach that?"
GLM felt like it got at least 20 IQ points dumber just from being exposed to claude's writing.
Code-wise it seems to still nitpick, especially in reviews, but it doesn’t seem to rabbit hole quite as badly on tangents and scope-creep. These are just first impressions though. It’ll take a few weeks of regular use to really have a sense of it.
Ironically, what I'm working on a post-processing hook for colorizing and summarizing responses without degrading the session quality. So "truncating" = summarizing, "quantizer" = char limits and thresholds, "collides" = conflicts, "two oranges" is referring to the "alert level colors" where a second model (Haiku/Sonnet) colorizes text based on the perceived (or suggested) priority of a response's statements (e.g. "just so you're aware, I didn't commit" is fucking useless and it needs to be blacked out).
So the original insufferable statement translates to something like "The code that checks whether a sentence is too verbose was conflicting with the part that colorizes the text."
P.S. Let me know if there's something out there that exists like this- something that adds a dimension like color or tabular reporting on a per-response basis. So far all I've seen is 2 dozen ~100k starred GitHub plugins that add zero value or make things worse.
Seriously, both flagship GUI apps (OpenAI and Anthropic) are a full of glaring UX issues (for ChatGPT it's not naming their windows, so window switcher has 10 entries of "ChatGPT" and you can cycle them all to find the one you want).
Maybe this model can finally figure it out for them.