Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why does Opus 5 feel worse to work with?

mun-logadan.github.io

Post reply on HN
Print view View original

331–340 of 915 posts

Re: Why does Opus 5 feel worse to work with?

#331

Post by tempest_ »

oooyay wrote: post #293
tempest_ wrote: post #212

Earlier quoted context omitted.

"seam" is apparently... according to Claude itself a term from 'Working Effectively with Legacy Code' by Michael Feathers which I have not read. All it took was for one sub agent to use this term and it stated using it everywhere all the time. I have not read the book and prefer other terminology but it only takes 1 sub-agent or 1 usage in the context before it poisons everything else.

An interface is an example of a seam in regular code. It's basically what forms architectural shapes that you can depend on for both design and testing.

Yes, and I prefer that term because no one but claude ever talks to me using the word seam every other paragraph.

I have instructions which is confidently ignores to never use seam and instead say interface.

Re: Why does Opus 5 feel worse to work with?

#332

Post by throwaway_7274 »

throwaway894345 wrote: post #296
barrkel wrote: post #12

The single biggest annoyance with Opus 5 is that it writes too elliptically. Sentences that orbit a point, then jump to it like it's a revealed insight. Unnecessarily abstract phraseology. Constantly using inanimate nouns as the subjects in sentences in order to unlock variety in verb choice, especially when it helps construct a sentence where the real action can 'land' like a surprise at the end. It is definitely mo…

It’s a strange feeling as a native English speaker to read the entire sentence and know every word, for the sentence to be entirely grammatically correct, and still have no idea what it’s trying to communicate. Another problem is that it will open up all sorts of tangents about nits that it encountered, but it will often not tell you that it’s a nit or give you adequate context to realize that this paragraph is excee…

I think it’s no longer speaking human language. It used to, when it was mostly or entirely trained with imitation learning of human-generated text. Now it’s increasingly trained with RLVR, and there’s far less optimization pressure on actually speaking English (or Punjabi or Mandarin). It still uses English words and syntax in its output, but the semantics are drifting more and more. It’s basically speaking in a code that superficially resembles English.

Re: Why does Opus 5 feel worse to work with?

#334

Post by hbn »

Opus 5 feels like dealing with an unstable person that I'm constantly having to wrangle from crashing out. The other day I asked for a fairly specific technical answer in Opus 5, it gave me like a 3 paragraph response with so much fluff.

So out of curiosity I switched to 4.6 in a new chat, gave it the same prompt, and it gave me like 3 sentences with no less overall useful information. And I haven't gone back.

Re: Why does Opus 5 feel worse to work with?

#335

Post by crimsonnoodle58 »

I guess that's the beauty of having access to many models, because they suit everyone differently.

I disagree with this article and find Opus 5 an absolute joy to work with. I just completed an 18,000 line branch with Opus 5 and ran into no issues. It generated clean code in the exact style of our code base, and tested every change.

Fable on the other hand is snarky and outputs walls of text as to why it shouldn't do what I'm asking it.

Opus 4.8 I accidentally went back to in an old chat, and I was frustrated in all the mistakes it made.

So yeah, use the model that works for you.

Re: Why does Opus 5 feel worse to work with?

#336

Post by gwd »

demibabs wrote: post #34
barrkel wrote: post #12

The single biggest annoyance with Opus 5 is that it writes too elliptically. Sentences that orbit a point, then jump to it like it's a revealed insight. Unnecessarily abstract phraseology. Constantly using inanimate nouns as the subjects in sentences in order to unlock variety in verb choice, especially when it helps construct a sentence where the real action can 'land' like a surprise at the end. It is definitely mo…

> Unnecessarily abstract phraseology. Constantly using inanimate nouns as the subjects in sentences in order to unlock variety in verb choice, especially when it helps construct a sentence where the real action can 'land' like a surprise at the end. Example of this? I don’t have a Claude sub so it’s a bit hard to visualize what you mean.

Here's an actual output from Claude from a conversation about rewording a document to make it more readable:

> Start with §1 (Overview) as the register-calibration piece. It's small, it's the section where the skimmability goal bites hardest, and your review of it teaches me the target voice cheaply before the bulk ports (the map and appendix B are the big volume). One review round on §1 is worth more than any amount of me guessing at register.

Hard-to-read phraseology above:

- "the register-calibration piece", rather than "a good example we can use to establish the writing style"

- "skimmability"

- "bites hardest" -- what does it mean for the goal to bite?

- "bulk ports" -- using "porting software" here as an analogy for rewriting / reorganizing sections of the document

- "the big volume"

In normal English I'd write something like the following:

"Start with rewriting §1 (Overview), and letting you review it to set the expected writing style. It's small, and it's a section where the ability to skim through it is most important. Reviewing it will teach me the target 'voice' cheaply, before we do the larger sections (like the map and appendix B). That's a lot more efficient than me trying to guess while rewriting the whole document."

Re: Why does Opus 5 feel worse to work with?

#337

Post by chuckadams »

numeri wrote: post #265
adamcharnock wrote: post #232

My latest trick (literally from yesterday) is to just ask it to write according to ISO 24495-1, the standard for plain language: > [This standard is] for anybody who creates or helps create documents. The widest use of plain language is for documents that are intended for the general public. However, it is also applicable, for example, to technical writing, legislative drafting or using controlled languages. You don'…

Does this actually work for you? Do you provide access to the text of the standard, or literally just say "write according to ISO 24495-1"?

I doubt you have to do anything more than that very prompt. I suspect the model has the full standard in its training set, which means it also gets the gist of it due to not just the general associations it makes but also the amount that it's been cited wherever it's been used.

Re: Why does Opus 5 feel worse to work with?

#338

Post by superdisk »

jbs789 wrote: post #244
MEMORYC_RRUPTED wrote: post #13

It's not even code for me, but the prose it writes. For some reason, the way Opus 5 "talk" elicits frustration in a way that 4.5 to 4.8 never did. Can't put my finger on why, but I've flipped over to Codex because what it produced wasn't worth the frustration.

I found myself swearing at it more recently. It was going off today about having “shipped” something and I was like no… nothing has even been committed. And then it produced an incredibly verbose comment about hypothetical future changes. And all I could think was sure, let’s keep it short, or add a simple test that will break if that hypothetical becomes true. Or maybe I’m just more easily annoyed recently…

So true. The breaking point for me was when it was constantly saying to wrap up because we'd done enough work for the day, but we had barely even done anything. Or constantly estimating that the next steps would take X number of weeks, and then knock it out in a single prompt. I demanded in no uncertain terms to stop giving pointless bogus estimates or telling me to stop working, and it just wouldn't. I also had a project I wanted to let it cook on overnight (a codebase port from Java to C++) and laid out a set of hard and fast rules that it could absolutely not break at any cost. Then I woke up the next day and it had broken all the rules and was just taking shortcuts left and right, and then lying to my face about it, even when I could point to concrete examples.

I cancelled the sub instantly and went to Codex and it's never let me down.

Re: Why does Opus 5 feel worse to work with?

#339

Post by Art9681 »

crimsonnoodle58 wrote: post #335

I guess that's the beauty of having access to many models, because they suit everyone differently. I disagree with this article and find Opus 5 an absolute joy to work with. I just completed an 18,000 line branch with Opus 5 and ran into no issues. It generated clean code in the exact style of our code base, and tested every change. Fable on the other hand is snarky and outputs walls of text as to why it shouldn't do…

Agreed. Opus-5 is top tier. I also use GPT Sol and I much prefer the default persona of Opus. GPT Sol is a workhorse though. Both amazing models.

Re: Why does Opus 5 feel worse to work with?

#340

Post by macrolime »

anentropic wrote: post #304

> stop and ask questions if my intent was unclear, > don't make assumptions without checking, > and don't reinterpret or update my plans without asking. these aren't at all the problems I have with it I have found it good at asking questions, to the extent I rarely use 'plan mode' any more but often it's hard to understand what it's asking me, it's like the question framing has been pulled from the middle of its own…

I have these exact issues with GPT 5.6 Sol too. I haven't tried Opus 5, but I guess it's even worse.

"like the question framing has been pulled from the middle of its own reasoning stream" this describes how it asks things perfectly. It often invents its own jargon and abbreviations for things that its working on, then asking me things like We are nod in the middle of GBAPI-2 and I want to proceed with IG5, should we take CDI-7 or CDI-8? Where all of these abbreviations are then things like stages of its current internal plan or its naming of things it has just implemented, like an abbreviation of a classname, without explaining any of the naming.

Post reply on HN