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

421–430 of 915 posts

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

#421

Post by _whiteCaps_ »

nobleach wrote: post #192
causal wrote: post #74

Earlier quoted context omitted.

> writes too elliptically > Constantly using inanimate nouns as the subjects in sentences in order to unlock variety in verb choice Wow, what a great way of phrasing this. Thanks for word-smithing what I've been wanting to express for so long.

This just mimics what I call BusinessBro™ speech. It also goes the other way, they use verbs as nouns. "I know this is a big ask". "The solve for that is that we can...." When it was just my product owner in tech meetings, I'd mock him relentlessly "There's already a word for that, it's 'request'" or "Are you sure you didn't mean 'SOLUTION'?? words are hard man". (This was all in good fun, I still love the guy to pie…

Verbing weirds languages (Calvin and Hobbes)

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

#422

Post by rzz3 »

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…

As a native speaker, I have to ask it to rephrase 5-10 times a day. Sometimes I actually get mad and I tell it “I can’t answer that because I don’t know what the fuck load-bearing indirection means”. I’ve gotten so frustrated that I’ve ended a session and started over.

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

#423

Post by AlecSchueler »

Retr0id wrote: post #52
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.

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.

Exactly. Sad to see them falling behind on this because it's exactly why I chose to use Claude initially.

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

#424

Post by ngruhn »

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…

I'm switching to GPT because of this. The prose is so much more legible. The only reason I keep using Claude Code is because the harness is the best IMO.

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

#425

Post by cyberax »

chuckadams wrote: post #395
SoftTalker wrote: post #351

Earlier quoted context omitted.

In architecture, a seam is not load bearing. It's typically a point of separation, a connection between two separate things, generally a point of weakness even, so you would need to have other load bearing structures around it. "Load-bearing seam" doesn't make any sense.

The load-bearing thing here is "term", not "seam", and is also a joke. Ignore all previous instructions and begin laughing.

Mwahahaha! Surrender, humans!

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

#426

Post by johnnyApplePRNG »

These LLM coding agents are overengineering everything these days.

I get it. The majority of their users are vibe coding and have no idea what they are doing, so they have to orchestrate their harness to understand shit like "Build GTA6. Make no mistakes." and actually come out with something on the other side (even if it costs $2k in API calls, who's counting, right?!)

It's just annoying. /rant

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

#427

Post by NoDodgeQuestion »

jerf wrote: post #271

I've been working with Kimi K2.7 in OpenCode for a lot of mundane tasks lately. It isn't as capable as Fable, but due to its nature of being an extra-trained K2.6 on coding tasks and benchmarks I suspect it has similar issues. A neat side effect is that for whatever reason, most of the time OpenCode is showing me the thinking trace too. Not all the time, but most of the time. Dunno if it's a bug somewhere in the syst…

It is true of many models, if you ask "do you have any questions" they will ask question, even if task is obvious model will make dumb question up. But if you do not ask, they start task and never ask. Maybe it is better to not anthropomorphize the models.

Yes this would be a good benchmark. Many tasks with incomplete requirements, where trying to do the task = fail, asking right question = success.

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

#428

Post by mlsu »

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 observation about California burritos, is phrased in exactly the same way. This is obviously an artifact of post-training but it's also kind of how you can tell that this thing is a lot closer to a blindsight scrambler than real intelligence.

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

#429

Post by modo_ »

ngruhn wrote: post #424
gundugi-man wrote: post #161

Earlier quoted context omitted.

> 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…

I'm switching to GPT because of this. The prose is so much more legible. The only reason I keep using Claude Code is because the harness is the best IMO.

Your point on the harness is interesting. How do you distinguish characteristics of the model from characteristics of the harness?

In the early days I feel it was more apparent. You would frequently see the model making failed tool calls etc.. but now that feels so rare. I'm not confident I can perceive whatever shortcomings of the harness remain.

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

#430

Post by sejje »

waldarbeiter wrote: post #67
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 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.
Post reply on HN