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

251–260 of 915 posts

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

#251

Post by D13Fd »

conception wrote: post #150
causal wrote: post #79

Earlier quoted context omitted.

Yeah I don't know that any of the benchmarks index on "understandability". I'm amazed at how Claude can produce a page of text describing what it did and it can take me a full five minutes to decipher it, often just to find it's something I could have expressed in a simple sentence.

Have you tried asking it for a lay explanation of what it did? That’s usually all it takes for me. Sends garbage -> request -> sends something readable

Yeah but Sol shows it is possible to just send the readable explanation in the first instance. And I don't want to spend tokens and time on asking for a better version of each response.

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

#252

Post by barrkel »

MyFirstSass wrote: post #24

I've gone back to 4.8. 5 would constantly veer of in random directions if not working from 100% strict and narrow instructions. I find it weird there's not more discussion here on HN on how the most used model now has clearly degraded in quality and it seems we've hit a peak and are on a downslope - because the model is clearly smaller or more economical for Anthropic no doubt about it, and the benchmaxxing they do i…

I have a chunky bit of functionality in my hobby app using babylon.js to render 3D worlds using things like portals and LoD rendering to manage the visual load. I built it out with a combo of Fable and Opus 5.

I too got fed up with the prose of Opus in particular, and tried going back. Unfortunately, the previous models were less able to hack it. The prose was better but progress was worse.

It wasn't just conversation and comments. Some of the function names were wild. Like it instead of something like "isSolidWall(x)" it would write something like "weightyNotEphemeral(x)" or something - that's not quite it, but it really did embed overwrought antithesis into the identifier instead of a straightforward positive predicate.

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

#253

Post by an0malous »

blks wrote: post #157

Nth post about another model suddenly feeling “worse” or “off”. Seems like active users of these models can only judge it based on a vibe and a feel.

If they were all about OpenAI or Anthropic, I’d guess it’s a real effect from enshittification to prepare for IPOs

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

#255

Post by waldarbeiter »

yorwba wrote: post #198
waldarbeiter wrote: post #171

Earlier quoted context omitted.

Thank you, my dict.cc search history contains exactly some of these words. I felt like my english got much worse but when Claude kept talking about "hunk" over and over I felt like the problem is maybe not on my end.

"hunk" is git terminology. When you use `git add --patch` (which you probably should, if you use `git add` at all) you get prompted "Stage this hunk [y,n,q,a,d,e,?]?" which is self-explanatory (?) and the hunk refers to whatever change git is highlighting at the moment.

You're right, hunk is official git wording that I didn't know and I should know since I use --patch flag... It's just that I never heard a human (including online) reason about hunks. While at the same time (from my observation) people say things like code chunk, code snippet etc. a lot.

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

#256

Post by nailer »

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…

> I think the issue is that what works well for code (succinctness) doesn’t work well in prosaic English.

Hrm, I would have said the oposite. Succint language communicates without unnecessary clutter that could be a barrier to communication.

> Biggest issues: dense sentences, constant metaphors, abstractions, and seemingly no understanding of correct anaphora use.

And maybe you also agree? I'm confused about your preferred style of language.

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

#257

Post by tempest_ »

openasocket wrote: post #122
jodacola wrote: post #94

Earlier quoted context omitted.

Yes. I’m not particularly dense but lately the walls of text I get back turn my brain in knots. When I start feeling my brain knot, I know I need to say something along the lines of “I need you to explain this very simply, with examples.” Only then can I parse the results without all the mental weightlifting. On more than one occasion my mind has wandered into “is this purposeful to get me to spend more tokens?” terr…

I know exactly what you mean. Something about those AI explanations just make my eyes glaze over. Dozens of new terms and metaphors and analogies conjured out of the ether to explain even the simplest thing. And when I try making it explain with examples, or show me the code it is proposing, often it seems unrelated or even in tension with whatever it tried to say before. I’ve given up trying to assign any meaning to…

I have gotten to the point that when it throws a wall of text at me I demand a diagram heavy primer from "first principles". This helps a bit but is a token burner for sure since CC seems to (and literally) be paid by the word.

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

#259

Post by KronisLV »

I'd say being exposed to the slop tone too much: https://blog.kronis.dev/blog/ai-slop-is-a-self-inflicted-tra... because the technical capabilities of the model and the harness (at least nowadays) are all fine.

There's precisely no technical reason for things to have to be this way (though technical reasons in regards to training etc. explain how we did end up here) and reading too much of Claude's output just makes me irrationally angry, especially when coupled with otherwise already frustrating situations.

That's why I'm personally looking more in the direction of Kimi K3 and GLM 5.3 (they both have decent coding subscriptions, though K3 is on the slower side), except all of the models that have seen enough of Claude's output and have done distillation etc. are already infected by some of that slop as well, even though to a slightly lesser and more tolerable degree (for now).

Though tbh I've used Opus 5 plenty and didn't find it much worse than the previous iterations at doing work and instruction following - though maybe that's because I have plenty of CLAUDE.md instructions and memory (which I'd like to purge or decrease in size like 10x tbh, bitrot).

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

#260

Post by user43928 »

thevinter wrote: post #215
user43928 wrote: post #43

Earlier quoted context omitted.

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

I did. He just went ahead and built a script to run headless chrome and take screenshots anyways.

Wow.

I hope that in the future they can differentiate better when something is constrained intentionally, rather than persistently working around every blocker it encounters.

Post reply on HN