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

201–210 of 915 posts

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

#201

Post by basch »

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

Brilliant way to get people to waste tokens.

Maybe just don’t generate garbage in the first place?

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

#202

Post by cmiles8 »

The mainstay benchmarks are becoming a farce and not partially relevant to what customers actually care about.

Metrics like price per million tokens are meaningless when the models are wildly inconsistent and unpredictable on how many tokens they use to complete a task.

The labs all need to move to variable pricing so they don’t go bankrupt, but customers won’t accept a world where nobody can predict what things will cost. It’s becoming an unavoidable problem.

At times it also feels like the labs actually encourage these models to burn useless tokens as they are incredibly verbose unless you really push them to not be. If you just ask something simple that could get a 5 word response you get a whole useless essay.

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

#205

Post by crab_galaxy »

altern8 wrote: post #180

I feel like it works A LOT better than Opus 4.8 + Sonnet. I now use it exclusively at high effort for planning and low effort for writing the code (instead of Opus 4.8/Sonnet). However, it's absolutely exhausting to use because of the way it communicates. All the jargon and its weird, over complicated way to phrase simple things makes it almost impossible for me to understand what the hell it's trying to even say hal…

I have to preface all my prompts with, “in simple, plain English…” because it doesn’t respect my rules on this stuff.

I’m glad to read I’m not the only one getting these unintelligible responses from Claude lately

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

#206

Post by vachina »

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…

yeah I feel the same way with Opus 5 too. If I ask it to do something, it would go ahead and rewrite unrelated things and then in a less performant version of it.

I’ve instead moved to GLM, at least it has the courtesy to ask some steps of the way what I wanted exactly and only work on what I asked.

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

#207

Post by inferniac »

gundugi-man wrote: post #161
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…

the tip that was floating around on x was to tell it to use "ASD-STE100 Simplified Technical English"

cladue desktop has an instructions sections under general options, you can put something like

"try to stick to ASD-STE100 Simplified Technical English, keep answers short and to the point"

funnily enough the placeholder they suggest when its empty is "keep answers short and to the point"

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

#208

Post by Aurornis »

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…

> Sentences that orbit a point, then jump to it like it's a revealed insight.

That’s accurate in my experience, except some times the point isn’t even revealed. I use LLMs for a lot of codebase exploration where I ask it to map out how something works. It will come back with a wall of text that says everything except the specific key things that I need to know.

This leads to extra turns where I have to prompt it to finish the explanation and complete the thoughts. At first I thought I was doing too much skimming and missing the insights, but even after re-reading output it’s often just not there. It talks about the insight and things related to it, but it forgets to actually include it in the output until I specifically ask again.

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

#209

Post by inferniac »

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.

I think anthropic is very far up their own ass and it shows up in the model output

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

#210

Post by nathanyz »

slaser79 wrote: post #188

A lot of the issues have been already noted here..Two "regressions" for me: 1. Communication ability. It basically now speaks almost in riddles I am asking OPUS 5 for tldrs all the time now (should skillify it now!) 2. Overengineers for edge cases. I get it. With all the benchmarking and RLing, but now tasks that would have been completed relatively quick take much longer as it overengineers all the edge cases, and s…

Your #2 is spot on. I have in fact said the same exact words to Opus about missing the forest for the trees.

I have it work on some code for an inhouse ClaudeCode plugin, and it starts coding as if it will be attacked by hackers who will try all sorts of variations to break it. I can appreciate that in cases of software that is public facing or accessible, but for a simple helper plugin it is overkill.

It will even admit that it is doing this when confronted, and then keep on getting lost in edge case verifications on the next turn. I feel like Opus is the person who does something a way you don't want, you tell them how you actually want it, they apologize, and then just continue doing it their way as if your input meant nothing to them.

Post reply on HN