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

631–640 of 916 posts

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

#631

Post by indemnity »

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 canceled my personal Max 20x subscription because since the 5 series models I simply cannot understand what the LLM is saying without a lot of reading and re-reading, and no amount of CLAUDE.md exhortations to speak plainly seemed to fix it. I don’t have the energy to spend twice as long to understand its plans, and pay Anthropic prices for the privilege. GPT seems not to have been infected by this yet, whatever it is, and Grok is quite refreshing for how normally it speaks.

I wonder if everyone at Anthropic talks like this.

If it’s watermarking, lol, good luck with that, it’s enough negative value to make me switch providers and I’m in a position to make this decision at a company level as well (we spend millions a month on Anthropic).

They need to fix it.

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

#632

Post by laurels-marts »

artdigital wrote: post #324
ryanschaefer wrote: post #230

Earlier quoted context omitted.

I had this debate with my coworker who prefers anthropic models to open ai ones. I ended up settling into the idea that gpt 5.6 is better used as a tool and opus 5 is a companion. GPT 5.6 takes you literally whereas opus 5 tends to take more liberties to try to get to the “spirit” of what you want. It comes down to preference, and I don’t want a companion.

That’s how I see it too. Claude is more “fun” to use, like a coworker I have to talk to now and then to steer it, while gpt-5.6 is a task machine: I give it a task and it is very consistent, reliable and predictable in its execution. I don’t have to interrupt it, it gets the task done exactly how I wanted it, but it’s “boring” and feels more sterile

Sol is an absolute machine. I stopped doing parallel worktrees just because the cost of context switch outweighs the cost of waiting Sol to just finish the task it’s working on which is usually anywhere from 1-10mins.

I also like Codex CLI more than the Codex App bc it’s more scriptable and displays all the tool calls and reasoning whereas in the App it’s kind of folded away/obscured. This way as soon as I see a tool call fail (eg it tries to use jq assuming it’s available but it wasn’t so I take a note to set it up as it’s obviously useful for the agent to wrangle json).

I think its amazing what OpenAI have been able to squeeze out from a model like Sol thats much smaller in size than Fable.

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

#633

Post by billbrown »

adamcharnock wrote: post #232

My latest trick (literally from yesterday) is to just ask it to write according to ISO 24495-1, the standard for plain language: > [This standard is] for anybody who creates or helps create documents. The widest use of plain language is for documents that are intended for the general public. However, it is also applicable, for example, to technical writing, legislative drafting or using controlled languages. You don'…

You could create an output style to make this prevalent.

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

#634

Post by semiquaver »

silverwind wrote: post #328
martinald wrote: post #323

Earlier quoted context omitted.

Keep in mind all this kind of stuff can make the model less capable. If it has to think in "plain" English, it may well be squashing quality of code etc output. I'm not sure how true this is, but when using "forced" json output it def had a big drop off in quality - https://arxiv.org/html/2408.02442v3 . I think you're better not fighting it with hacks like this and find a different model.

Changing output style shouldn't affect thinking at all.

Tell that to all the CLAUDE.md lines across dozens of repos I have to write to get them to understand that git commit standards and PR description standards are different.

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

#635

Post by indemnity »

oefrha wrote: post #197
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.

They did release an Opus 5 prompting guide saying you need to explicitly prompt it to be concise or it will be very verbose. YMMV but it got better for me to some extent. https://platform.claude.com/docs/en/build-with-claude/prompt...

And where would we put this? I don’t want to write that out every prompt. CLAUDE.md is a joke, it has little to no effect.

Basically, I’ve gone from supporting them to hoping someone else wipes the floor with them.

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

#636

Post by sibeliuss »

saaaaaam wrote: post #531
paimapi wrote: post #452

Earlier quoted context omitted.

there's a wide array of assessments when it comes to reading comprehension. the one you refer to, the GRA, sets the 'sixth grade level' as whether or not a reader understands the author's main points, is able to answer conceptual questions related to the text, and then apply those to relevant situations. beyond this level is the ability to essentially be skeptical of a text and to know how to critically analyze it. s…

I’m inherently skeptical of big walls of text like this these days. (So here’s a big wall of text of my own!) However, a lot of what is written here makes sense. And particularly “if your comprehension level stops [here] you get 'big words in complex sentence structure sounds smart and right so it is smart and right' even if the reasoning and process is poor” This is exactly the problem. And another point you make: >…

You are fighting a good fight! Props.

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

#637

Post by user43928 »

ryanschaefer wrote: post #230
D13Fd wrote: post #120

I’ve been doing some heavy work on a personal project lately. I burned through the limits on Claude, the plus a few hundred dollars in credits, and ultimately decided to move to an OpenAI account just so I can keep going. I was surprised to find that OpenAI Sol is much much nicer to work with than Opus 5 or Fable at the moment. Especially on Opus 5, the way it communicates is just exhausting. It keeps “being honest”…

I had this debate with my coworker who prefers anthropic models to open ai ones. I ended up settling into the idea that gpt 5.6 is better used as a tool and opus 5 is a companion. GPT 5.6 takes you literally whereas opus 5 tends to take more liberties to try to get to the “spirit” of what you want. It comes down to preference, and I don’t want a companion.

I doubt there is such a clear difference.

One week it feels better to work with Fable and Opus 5, the other I work more with GPT 5.6 Sol. Either takes its liberties, and neither communicates like a companion.

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

#638

Post by beezlewax »

mlsu wrote: post #428
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…

Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…

And this is infuriating. I don't want to read all this gibberish anymore. It's making me hate what software engineering has become.

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

#639

Post by semiquaver »

sejje wrote: post #430
waldarbeiter wrote: post #67

Earlier quoted context omitted.

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.

I never ask for time estimates, but all the models will sometimes give me them. It'll sometimes estimate 1-2 weeks for something that is ~ one more prompt and 10 minutes of waiting for the model to churn.

This (feature estimates assuming human scale performance) happens all the time to me. Models are trained on a view of the world where software takes a long time to write. Gonna be a while before the models fully absorb their own impact on reality.

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

#640

Post by buu700 »

boomlinde wrote: post #496
mlsu wrote: post #428

Earlier quoted context omitted.

Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…

I've noticed that ChatGPT (whatever model the free version uses by default) likes to phrase answers as though it's correcting me, even when my question doesn't contain any assumptions.

Interestingly, I've been noticing almost the opposite issue. 5.6 Sol frequently starts its responses with "Yes" even when my prompt doesn't contain a yes-or-no question.
Post reply on HN