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

61–70 of 915 posts

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

#61

Post by tigeroil »

roarcher wrote: post #55
cyberrock wrote: post #32

Small specific complaint: whoever is making Opus love using git checkout to mutate test, please stop. IME it's a footgun that it shoots itself with every single day. I'd rather it pollute git stash than watch it git checkout and forget the reverted file.

I explicitly forbid Claude to make any changes to Git state in my global CLAUDE.md, but every so often if I let it perform a task in Auto mode, after it finishes it will remorsefully confess to having used git checkout to test a change. I suppose that its RLHF training has taught it that asking forgiveness later is sometimes a useful workaround for annoying restrictions.

I'm glad it's not just me - the failure mode you and the parent discuss is a huge part of why I just don't use Claude anymore.

I've never had this issue with GLM or DeepSeek.

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

#62

Post by KptMarchewa »

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.

[flagged]

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

#63

Post by purplepatrick »

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 metaphors, abstractions, and seemingly no understanding of correct anaphora use. For example, “the x”, with x having not only no antecedent but also being a coined word or quasi-synonym for something that is already named in the code base. This gets compounded by its being unable to regress to a baseline (existing names in code) and instead anchoring on newer (vague or wrong) terms, for example, that crept in through a plan.

CC tells me this is because the speedy and precise fulfillment of a current task will trump every other tendency, so it adheres poorly to whatever “semantic baseline” the project represents.

Of course, it also has no concept of what context the user has and assumes that it must be the same it holds in its memory, which creates this “I didn’t know that you didn’t know” type of communication.

I have managed to wrangle some of these issues with a custom output style, but wish a pre-report hook were an option, as it could force CC to rewrite plan implementation take-aways…

Btw: Fable has the exact same issues, just somewhat less pronounced.

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

#65

Post by inigyou »

dnautics wrote: post #58
inigyou wrote: post #45

Earlier quoted context omitted.

well we don't know exactly what thinking is, but we can be pretty sure that at least LLMs don't think anything like humans, just by observing their behavior. They always produce outputs in line with the fancy autocomplete model.

> what evidence would convince you that it is thinking so, none it seems. as its behaviour becomes more and more humanlike you can just move the goalposts and say "thats consistent with an autocomplete" buddy i got some bad news for you humans are just a fancy autocomplete too.

That's exactly what a fancy autocomplete would say. I'm so sorry you don't have limbs.

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

#66

Post by speed_spread »

ykonstant wrote: post #18
stavros wrote: post #6

For me, the issue is how obtuse it is. For example, it just said to me: > The loop > Write. A file, applied. Properties go under data.properties, never on data: I have no idea what any of that means. It's "explaining" like I already know, in which case, why would I even need the explanation? I can't stand how it talks, I switch back to Fable or Opus 4.8, Opus 5 grates.

LOL, is it trying to speak in Haikus?

Pain. Sufferance. Inevitable is, the Yodaization of LLM output.

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

#67

Post by waldarbeiter »

bevekspldnw wrote: post #10

I’ve also caught it cheating a two times now. I’ve asked it to write a benchmark suite. It found a bunch of my adhoc logs in a scratch directory and wrote code that used those instead of running the actual benchmarks! When I pointed out the 5 hour benchmark seemed to run in 5 seconds it literally said, and I quote, “I cheated”. That was the easier one, second time I was making a source of truth data set and was parsi…

I can completely relate, what really bothers me is that I feel the early LLM generations overconfidence is back in Opus 5. Opus 5 wanted to tell me a training run will only take 30min while having access to the logs where earlier runs took 4x as long. I also didn't ask to estimate how long the run will take it just stated confidently that it will take 30mins.

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

#68

Post by dolmen »

kioleanu wrote: post #4
mr_tox wrote: post #2

I get the same impression. For example, I don't know if it's because I speak to it in Italian, but it tends to make mistakes or rather, "approximate" the words.

I avoid speaking to AIs in anything else than English as the results are almost always worse

It depends how you measure "worse".

I'm using it in my native language, in hope this can escape some dumb guardrails. Recently Sonnet put a word partially in Russian (cyrillic) in its output instead of my latin-alphabet based language. I suppose that this kind of mishaps is less likely to happen in English.

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

#69

Post by sevenzero »

user43928 wrote: post #43
sevenzero wrote: post #17

I hate that it now tries to verify frontend behavior through a headless browser instead of just looking at the code...

You can turn off the browser use tool in the harness if an instruction not to use it for this is not enough.

I just want to start /claude in my CLI and start working. It worked fine before, why do I have to opt out of shit now? Opt in for this type of stuff sounds way more reasonable.
Post reply on HN