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

141–150 of 915 posts

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

#141

Post by speerer »

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…

Genuine question - are you copying the Claude phraseology for effect (in which case you captured it brilliantly), or is there a more mundane explanation?

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

#142

Post by swe_dima »

My feeling that as it becomes a better coder it becomes a worse communicater. It's overfitting for coding benchmarks, while communication style is harder to quantify during training.

And no matter how often I tell it to stop adding comments it just can't help itself.

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

#143

Post by sscaryterry »

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.

This is 100% my experience.

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

#144

Post by cl3misch »

fuglede_ wrote: post #93
demibabs wrote: post #44

Earlier quoted context omitted.

I wouldn’t exactly put it like that. It’s moreso the model sometimes outputting non-optimal tokens in a way that’s detectable if you know the algorithm. It seems possible for that to make the response “drift” far from what it would’ve been, because it’s constant entropy that adds up after time. (However, according to Anthropic and Google, it doesn’t really impact the quality of responses. I find that a bit hard to be…

One way to watermark (assuming temperature is otherwise positive) would be to output the most likely (or optimal) token every so often.

But wouldn't you have to know the exact context before this token in order to verify the watermark? I.e. a paragraph wouldn't be sufficient; you would need the system prompt, previous prompts, and even hidden thinking?

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

#145

Post by algoth1 »

demibabs wrote: post #44
algoth1 wrote: post #28

Earlier quoted context omitted.

From the little i understand that wouldnt be an issue because the model is ‘just’ using interchangeable words in a mathematical non-random way. Like using the same number of adjectives and the exct same words, but in a order that wouldn’t be mathematically plausible unless it was the watermark

I wouldn’t exactly put it like that. It’s moreso the model sometimes outputting non-optimal tokens in a way that’s detectable if you know the algorithm. It seems possible for that to make the response “drift” far from what it would’ve been, because it’s constant entropy that adds up after time. (However, according to Anthropic and Google, it doesn’t really impact the quality of responses. I find that a bit hard to be…

Yeah, it’s hard to believe, specially when you are coding and there’s only one best way to do things, unless it plays with variable naming, or comments

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

#146

Post by skarz »

edg5000 wrote: post #104
Root_Access wrote: post #101

Claude models have seriously digressed since 4.6 and in some of the most meaningful ways to pro and vibe coders alike. I'm holding onto 4.6 until the bitter end.

You're right. I just re-checked. 4.8 and 5 gave a blatantly wrong answer to a simple question, 4.6, Quen, GLM, Sol gave the right answer. They messed up somehow, not sure what they did.

What was the question?

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

#147

Post by stasomatic »

hmokiguess wrote: post #88

The harness as well, Claude Code has started to disappoint me when I go play with the others out there. Codex got a lot better, pi is delightful to use, and there has been a lot of innovation out there.

Plus you can use OAI monthly subscription with pi/omp etc, but it's tokens with Anthropic. I need a hard $ cap, I can wait for the usage window to reset. Going to get flip back to Codex, and then back again to CC* when it leapfrogs again.

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

#148

Post by taspeotis »

My completely unfounded pet theory is that it’s been ruined by the masses.

Claude Code in the hands of normies spamming “3” and “y” to send their transcripts to Anthropic.

Rated “3” simply because they are not software developers and are just amazed at what Claude has built visually, not technically.

And thus the training has been poisoned.

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

#149

Post by intrasight »

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…

Tell it to write like an engineer and comment like a programmer;)

But for the life of me, I don't get why anyone would care about the comments. All code is "machine language" now. The only document you should be reading is your spec.

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

#150

Post by conception »

causal wrote: post #79
karimf wrote: post #37

Earlier quoted context omitted.

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.

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
Post reply on HN