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

51–60 of 915 posts

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

#51

Post by MyFirstSass »

markbao wrote: post #9
UI_at_80x24 wrote: post #3

Quality of code output has dropped dramatically since 4.5 IIHO. Time to complete has gotten worse too.

For me absolutely not. Fable 5 has been a step function change in the ability to hand off stuff to Claude. Opus 4.5 was itself a step function but I was still steering that significantly. Fable is one-shotting stuff that took multiple redirections in 4.5.

From my view Fable has been pure marketing bullshit, my workflows peaked at 4.6, Fable is neither smarter, its language is more annoying and it breaks stuff more easily.

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

#52

Post by Retr0id »

karimf wrote: post #37
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…

This 100%. I was Anthropic-pilled. I had a $200/mo subscription and I only used Anthropic models. I was frustrated by the verbose output and the writing style. I tried ASD-STE-100, it helped a bit, but it's still too verbose for my taste. Then I tried GPT 5.6 Sol. It's night and day. I think Anthropic just RL too hard on coding capabilities and never calibrated or benchmarked the writing styles.

It's a surprising change from my perspective, because in the past it felt like they understood that Claude should be pleasant to interact with.

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

#53

Post by bevekspldnw »

SyneRyder wrote: post #31
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 have noticed the same. For fun, I tried recording a WAV file of speech, and giving Opus 4.8 and 5.0 an image of the waveform, then a spectral image of the waveform, just to see if it could try to decode what I said from the image alone. It didn't get very far, but it identified a male voice from the formants, and detected the rhythm of the speech, then tried applying common test sentences to the speech rhythm. I wa…

We’re on the road to paper clips.

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

#55

Post by roarcher »

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.

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

#56

Post by hnlmorg »

xyzsparetimexyz wrote: post #22
inigyou wrote: post #16

Earlier quoted context omitted.

> When I pointed this out it literally said, and I quote, “I cheated”. This makes sense when you know how these models work - it doesn't think - it's the most likely autocomplete that pleases the user. The most likely pleasing autocomplete after "executing rm -rf /... execution completed. User asks, why did you do that? You deleted all my files! Assistant responds:" is "yes, I did, and that was a mistake"

> it's the most likely autocomplete that pleases the user this feels like a simplification. The models will push back on things a fair bit.

Only when instructed to in their system prompt.

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

#58

Post by dnautics »

inigyou wrote: post #45
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…

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.

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

#59

Post by MyFirstSass »

UI_at_80x24 wrote: post #3

Quality of code output has dropped dramatically since 4.5 IIHO. Time to complete has gotten worse too.

True, and the time to completion thing is something i haven't seen much discussion of, because everything is sloooooow these days.

I've even considered the claude "fast mode" setting, but thats only 2x and at least 20x as expensive as the 5x plan so can't afford that atm for my company.

Peak for me was 4.6 and it just did stuff blazing fast, both Opus5 and Fable is way, way slower for me, breaks stuff, uses bizarre cryptic language. As i've said elsewhere in this thread to me it's pretty obvious there's huge downgrades because of economy with various "clever" fixes that makes them work, albeit slower and weirder, ie. you get less for what you pay increasingly over the last 6 months.

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

#60

Post by andsoitis »

stavros wrote: post #54
andsoitis wrote: post #49

Earlier quoted context omitted.

What was your question?

"Please look at this repo and give me a high-level explanation of how the app works", more or less.

And all it replied with was what you wrote ("The loop Write. A file, applied. Properties go under data.properties, never on data:")?

Or was there more to the response?

Post reply on HN