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

161–170 of 915 posts

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

#161

Post by gundugi-man »

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…

> The single biggest annoyance with Opus 5 is that it writes too elliptically.

This is even more painful for non-native English speakers like myself.

I feel fairly comfortable reading academic papers or in general, communicating in professional context.

But with Opus 5, it feels like reading a literature book: load-bearing, inert, wholesale, hunk, verbatim, and so on... I can figure out the meaning, but working with CC became unenjoyable.

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

#162

Post by the_af »

ACS_Solver wrote: post #100
Retr0id wrote: post #84

Earlier quoted context omitted.

I've tried telling it to "fix" comments with varying degrees of specificity and in my experience it just... fundamentally doesn't get it. Presumably using a different model for it would help. My theory is that Claude's learned approach to comments is to treat them as a sort of persistent in-band thinking trace, or a "memory" tied to an in-code location, which is a little at odds with the way humans use comments (huma…

I also suspect comments are very much tied to how Claude reasons because not only are they bad comments, I can't get rid of them. Commenting is the one area in which I've been unable to get Claude to respect any rules. It can follow code conventions I prefer, it can do other things, but it can't keep the comment volume down. My CLAUDE.md has rules about not including any redundant comments in the code that are obviou…

> But worse, many comments include in the moment reasoning like "added parameter bar because we can no longer use the frob to automatically derive bar". That's stuff for a commit message, or just a mental note, and absolutely not for comments.

I've noticed this a lot, and before your remark I couldn't put my finger on what was wrong. Now I know: Claude is writing its thought processes and maybe parts of the conversation it had with you as comments in the code!

I always end up manually trimming those comments, which is cumbersome.

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

#163

Post by ambicapter »

purplepatrick wrote: post #63
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…

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…

> being a coined word or quasi-synonym for something that is already named in the code base.

This annoys me with a lot of LLM code. They rename things for the hell of it all the time.

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

#165

Post by dnautics »

openasocket wrote: post #156
dnautics wrote: post #36

Earlier quoted context omitted.

> t doesn't think in humans the exact same behaviour (cheating) is slmost always the result of a chain of complex series of choices and environment-driven rationalization. if the llm doesn't cheat, you say "its just producing the most straightforward answer -- not thinking'. if it cheats, you say "weaseling out of hard thinking". damned if it cheats, damned if it doesn't. what evidence would convunce you that it is t…

Whether something is “thinking” or not is really more of a philosophical question. It really depends on which of the many, often contradictory, definitions of “thinking” you choose. Sometimes we use “thinking” to describe advanced calculation or analysis, which would cover LLMs along with chess engines and many other algorithms. Other times we use “thinking” to describe what conscious beings (which is ALSO a philosop…

> to conclude if it is thinking or not I would want to look inside its head

https://arxiv.org/abs/2607.03502

a non-thinking token model (just "completion") can answer one-step questions but generally not multistep questions. however, if you append [n] of a single token (e.g. period, space), it is able to use the activations in the higher layers of the blank tokens as a "scratchpad" to seemingly work through the complex question through "causal token time" and deliver a correct answer

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

#166

Post by docheinestages »

Claude has essentially become useless for agentic development or research. Doesn't matter what model you use. A few rounds and bam, you've burned through your quota. Doesn't matter how "intelligent" their models are, if you can't use them. That, and the quality of AI responses are, in my opinion, significantly worse than competitors like OpenAI. At this pace, I foresee Anthropic becoming the next Nokia.

If you would've asked me this a year ago, I would've said the exact opposite.

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

#168

Post by thedougd »

rio517 wrote: post #75
fny wrote: post #71

Just like with people you need to tweak your approach when switch models--especially with a major version bump. 4.8 was the intern who lacked confidence who requires clarification. 5 is the know it all intern who fills in your spec. As such, you need to be upfront about what you need in your system prompt or CLAUDE.me and you need to discuss your spec more up front (e.g "is there anything unclear?") You also need to…

I literally just did this a few moments ago. haha. I said "maybe think for a while on ideas and then give me a few options? " and Opus 5 still just did the thing, while 4.8 gave me options. Same exact prompt and context.

I added a system prompt paragraph explaining that a question is just a question, whether or not I’m in plan mode.

It still just takes the question as a directive and jumps to action when I’m looking for clarification.

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

#169

Post by dnautics »

elgertam wrote: post #127
dnautics wrote: post #36

Earlier quoted context omitted.

> t doesn't think in humans the exact same behaviour (cheating) is slmost always the result of a chain of complex series of choices and environment-driven rationalization. if the llm doesn't cheat, you say "its just producing the most straightforward answer -- not thinking'. if it cheats, you say "weaseling out of hard thinking". damned if it cheats, damned if it doesn't. what evidence would convunce you that it is t…

If I could give it a novel task outside of its explicit training and see it actually improve just through accreting context, I'd be convinced it was thinking. The opposite happens in practice. I test new models with two tasks: iteratively generating SVGs based on a text description with rendered rasters for feedback; and generating "Before and After" clues like on Jeopardy, where the response has two overlapping phra…

see sibling comment,

> see it actually improve just through accreting context

this actually happens and has been tested.

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

#170

Post by qudat »

Honestly I’m not looking for max iq on whatever benchmarks they are overfitting to. I want speed. I toggle between sonnet 5 low/med which is plenty good for my workflow.

My general strat with LLMs is to let them do the work and constantly talk to them about their choices and then heavy QA

Post reply on HN