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

811–820 of 915 posts

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

#811

Post by not_paid_by_yt »

zeafoamrun wrote: post #158
purplepatrick wrote: post #63

Earlier quoted context omitted.

Agreed. CC’s comms capabilities have decreased gradually since 4.6, and it’s a real challenge. I think the issue is that what works well for code (succinctness) doesn’t work well in prosaic English. CC’s communication violates almost every grammatical rule that’s tested on, say, the SAT. And yet I’m sure if you had Claude take the verbal section of the exam it would ace it. Biggest issues: dense sentences, constant m…

I think a lot of Claudisms are compressed steering cues for the model’s reasoning: “load-bearing” raises causal importance; “quietly” flags a hidden failure mode; “the one thing” collapses attention onto a discriminator; “on the record” invokes auditability; “at the width the evidence supports” calibrates confidence; “by construction” marks structural inevitability; and “converged” terminates further review loops. Th…

It could be, but without evidence that remains a just so story, no particular reason to think it's required or useful or even harmless to the model performance or anything other than an artifact of some early silicon valley writing style being injected into the model and continuous retraining on the output of older models.

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

#812

Post by not_paid_by_yt »

intrasight wrote: post #149
purplepatrick wrote: post #63

Earlier quoted context omitted.

Agreed. CC’s comms capabilities have decreased gradually since 4.6, and it’s a real challenge. I think the issue is that what works well for code (succinctness) doesn’t work well in prosaic English. CC’s communication violates almost every grammatical rule that’s tested on, say, the SAT. And yet I’m sure if you had Claude take the verbal section of the exam it would ace it. Biggest issues: dense sentences, constant m…

Tell it to write like an engineer and comment like a programmer;) But for the life of me, I don't get why anyone would care about the comments. All code is "machine language" now. The only document you should be reading is your spec.

The spec your principal engineer one-shoted through Claude and didn't even proof read afterwards before dumping it on the team?

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

#813

Post by ldng »

mlsu wrote: post #428
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…

Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…

What an amazing way to inflate token spending ! /s

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

#814

Post by quibono »

I hate the Opus 5 writing style. I’m not sure if it’s just how much exposure I’ve had to it recently but working with it is incredibly tiring.

I know the “instruct model to change output style” is supposed to reduce efficiency - but has anyone experimented with prompts like that? At this point I’m happy to take a slight intelligence/ effectiveness loss for less verbose, artisan and elliptic writing.

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

#815

Post by ricardobayes »

IgorPartola wrote: post #540
Panoramix wrote: post #500

Earlier quoted context omitted.

You're right, and the load-bearing part of the argument is not what you think it is. Two ambiguities worth resolving before moving on: whether what you wrote also applies to ChatGPT, and whether you have custom instructions set up. Failure mode worth flagging explicitly: I didn't read TFA. (I'm becoming allergic to how these things write).

I am curious why LLM writing has such an uncanny valley feel to it. Like if I was talking to a person who constantly used a phrase they liked I would notice it and it is possible I might get irritated by it, but I wouldn’t necessarily. In high school I had a teacher that would say “that type of thing” a lot. One time my friend and I counted it during one class period and he averaged to use the phrase every 48 seconds…

I suspect because the English colloquial text training data it had access to was early 2000's message boards and social media. Therefore it uses "honestly" and other expressions that took hold in the late 90s and early 2000s.

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

#816

Post by kaizenb »

quibono wrote: post #814

I hate the Opus 5 writing style. I’m not sure if it’s just how much exposure I’ve had to it recently but working with it is incredibly tiring. I know the “instruct model to change output style” is supposed to reduce efficiency - but has anyone experimented with prompts like that? At this point I’m happy to take a slight intelligence/ effectiveness loss for less verbose, artisan and elliptic writing.

"Save in memory to always use ASD-STE100 Simplified Technical English when you talk to me"

Fixed for me. Now the text outputs and comments are pretty easy to follow and read.

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

#817

Post by kaizenb »

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…

"Save in memory to always use ASD-STE100 Simplified Technical English when you talk to me"

Use this to reduce the text output.

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

#818

Post by quibono »

lubujackson wrote: post #724
zmmmmm wrote: post #674

I'm with the author and others in this comment thread, speculating that effectively the balance has tipped to where humans are no longer the target audience of post training - other agents are. Whether it's through the reasoning / CoT, or whether it's in handing off to subagents etc, the focus has moved to agents communicating in "agent-speak" to themselves or other agents. And human niceties are just kind of, noise…

Every round of models (plus all the secret tweaks) require new strategies to stay afloat as a human. My new tactic for Fable and Opus is to give them a line limit, both during planning and code creation. It os amazing how well that works for keeping them on task and avoiding premature optimization, pointless tests or any of those "robustness" ideas that are not planned or asked for.

Could you provide more detail please? Sounds interesting.

Is this a hardcoded limit or something relative to the input prompt etc.?

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

#819

Post by hgomersall »

Panoramix wrote: post #500
mlsu wrote: post #428

Earlier quoted context omitted.

Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…

You're right, and the load-bearing part of the argument is not what you think it is. Two ambiguities worth resolving before moving on: whether what you wrote also applies to ChatGPT, and whether you have custom instructions set up. Failure mode worth flagging explicitly: I didn't read TFA. (I'm becoming allergic to how these things write).

It also picks up and obsesses about weird details. You're in the middle of a deep technical discussion and it will divert to point out that it made a mistake in some example code it's just found.
Post reply on HN