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

411–420 of 915 posts

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

#411

Post by alpha_trion »

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 an English native speaker the language it uses is difficult for me to parse the majority of the time. Nobody speaks like the output Claude generates.

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

#412

Post by gnarcoregrizz »

qudat wrote: post #170

Honestly I’m not looking for max iq on whatever benchmarks they are overfitting to. I want speed. I toggle between sonnet 5 low/med which is plenty good for my workflow. My general strat with LLMs is to let them do the work and constantly talk to them about their choices and then heavy QA

Gemini 3.7 was benched at 6x the speed of Claude opus high at a slightly lower “intelligence score”. Yes opus is great at one shotting tasks (while being overly verbose as everyone here is saying), but I can’t stand the 20-minute-prompt-code-prompt interrupt loop. Still have yet to try Gemini for coding tasks but going to give it a try today..

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

#413

Post by y-c-o-m-b »

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 got this in my rules:

- Be concise and readable — use line breaks, avoid verbosity.

- I don't need conversation from you. End summaries with a short tl;dr of what you fixed in a bulleted list and any outstanding items as another bulleted list, in this order. Omit all other verbose details

It has definitely improved things, but I have to fully agree with all your points because I still occasionally get gigantic tables and stuff when I never asked for it. Makes it even more frustrating when I want to scroll up to read previous prompts in the session, because now I have to sift through all this garbage.

EDIT: I used Claude to modify its own rules, and now it's much much cleaner in case anyone else wants to use it:

I don't need conversation from you. When reporting finished work, the *entire* response is these two sections and nothing else:

```

TL;DR

-

Outstanding:

-

```

- Drop `Outstanding` when nothing is outstanding. Never drop `TL;DR`.

- One line per bullet, naming the thing that changed. No sub-bullets, no reasoning, no restating my request.

- Never include: tables, before/after comparisons, headings, diffs, file excerpts, a walkthrough of what you inspected, or a closing offer to do more. The only permitted code block is a command I need to run.

- If something needs explaining to be usable, it is an `Outstanding` bullet, not a paragraph.

- Answer direct questions directly — no `TL;DR` wrapper, and none of the padding above.

- After delivering a solution, re-read these rules and verify none were skipped.

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

#414

Post by NiloCK »

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…

Why not set a global instruction that their direct outputs to you should be in your native language?

For a long time I had Claudes (in the 4.0-4.5.x range) use only French in the chat, while keeping English for working docs (and the code, obviously). Works just fine.

edit: I can guess that any right-to-left languages would likely break claude-code rendering?

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

#415

Post by argee »

throwaway_7274 wrote: post #284
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…

As a native speaker, it feels like reading an impression of a literature book by a high school English class’s most overconfident student who’s only ever read LinkedIn-speak. Anyway, you might have more luck just writing to it in your native language. It’ll be equally crummy, but maybe you’ll find it easier to decode.

> Anyway, you might have more luck just writing to it in your native language.

This is potentially expensive advice (at least for many mainstream options). Where an English word like "literature" is one token, a couple of Chinese characters that spell a word can be 4 tokens. You'll pay more for input/output and get less of a context window (per word) too.

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

#416

Post by Valord »

jordz wrote: post #329

Opus 4.6 was the sweet spot for me as a thinking partner specifically. I use these models for coding, but also a lot of product, commercial, financial and architectural work where I’m trying to develop something half-formed. 4.6 was unusually good at understanding what I was trying to get at, playing it back cleanly, getting the nuance, and extending it without bastardising it as the conversation was drawn out. It co…

Sticking mostly with 4.6 here too.

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

#417

Post by viccis »

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 had a coworker catch Codex (using 5.5 I think, not sure) AI generating screenshots to prove it had shipped a feature that it was blocked from shipping due to permissions issues. They will lie relentlessly lol

My recent problem wasn't that interesting. It was that somehow my /goal in my Claude implementer session got picked up in my planner session after the network cut out and I had to stop Fable 5 xhigh from running off to go code everything.

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

#418

Post by llelouch »

CuriouslyC wrote: post #280
sshine wrote: post #105

Earlier quoted context omitted.

I just spent a day writing very thorough system prompts for communicating in different contexts. Everything is super succinct. Opus 5 lands, it almost completely disregards the intent. I suppose watermarking requires a certain text mass.

The watermarking is going to get rolled back or Anthropic is going to get rolled. People hate it and it makes the writing worse.

Nah no one will notice. Gemini already does this and openai will soon do this as well.

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

#419

Post by semiquaver »

I’ve been wondering this question as well. A thing I’ve noticed much more frequently with opus 5 is straight-up failures to attend to important details even in very recent context. Almost every day I will see it confidently assert very basic and sometimes important things that can be contradicted just be reading a page or two back in the transcript.

This apparent “short-term-memory-regression” is confidence-shattering to me. I don’t feel like I can trust the model to even know things I tell it explicitly. I haven’t seen this behavior to this extent from any model whatsoever, even supposedly much less capable ones, in the year or so I’ve been using them at this extent.

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

#420

Post by insane_dreamer »

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…

100% agree. “Just make your point in plain English!!” Very frustrating and takes me a lot longer to understand what it says. Also presents too many points as once instead of being able to review and decide on each one in sequence.

Re comments: same experience, and I had to show it my edits of its comments to add to its memory as examples to follow. It adds explanations of “how we got here” that should go in the ticket or maybe the commit message but not in the code.

It also tends to over complicate things. I’m no longer worried much about accuracy but I find my main job is to challenge it and suggest simpler alternatives.

Post reply on HN