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

511–520 of 915 posts

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

#511

Post by zamalek »

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…

Yesterday I told it "don't use std mutex, use parking_lot" for its plan. It ignored that sole instruction (i.e. nothing else in my message), making zero changes to the plan, three freaking times in a row.

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

#512

Post by skipants »

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.

Which written language has the most history of terse, succinct writing? If Claude doesn't improve I'm ready to learn a new language just to avoid its prose. I'm only half-joking.

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

#514

Post by FeepingCreature »

edg5000 wrote: post #106
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…

We can use OpenRouter pricing to get an idea about what competitive inference pricing is like without R&D or other costs, and indeed we'd be screwed if we had to pay those rates. We'd go from 100-200 USD to 2000-4000 USD/m.

Not sure what you're talking about here. Kimi K3 is frontier scale and sells competitively at $2.80 input, $14 output per 1M tokens.

edit: oh you mean month? Sure, but then it fully depends on your usecase. I agree that subscriptions are heavily subsidized though.

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

#515

Post by xyzzy_plugh »

mlsu wrote: post #497
phickey wrote: post #444

Earlier quoted context omitted.

In your reading, what is the distinction between blindsight’s scrambler and real intelligence? My reading is that it’s just as real, and draws out the disadvantages a sense of self constrains intelligence with

Sure. I should have been more precise about what is 'real intelligence' here. What I mean is that blindsight's scramblers are aliens that cannot share human values. Their structure is completely different to ours, their qualia (or whether they even have it) is impossible for us to understand. In short, they do not have a soul. When Claude does this "slowly revealing a dramatic insight" thing that it does, it does tha…

I think I understand what you are trying to convey but I fear you've made the same mistake again, this time with "soul" instead of "intelligence."

I think what you are getting at is that they are deterministic automata. They are machines. We have introduced randomness to add variation but it is an artificial randomness that simply perturbs the path traversed.

When we choose words it isn't because of a token distribution, nor because we rolled a die. We choose words because we feel a certain way, the external world, our body and senses are all connected as one system. These machines don't experience moods or get tired or feel better after a good night's sleep. They don't know their audience, we're all the same to them. We have no personal relationship nor can we establish one, as presenting some arbitrary background is not the same thing as a fluid, evolving relationship that accumulates through experience over time. There are no scars or fond memories.

If these things can truly be intelligent, to abuse your use of the word, then at least we are quite far from holding them correctly.

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

#516

Post by bborud »

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.

Doesn’t just mean the model has picked up on what happens when two graybeards who still wear cargo shorts meet and one utters a declarative sentence? :-)

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

#517

Post by renegade-otter »

pennomi wrote: post #450
deskamess wrote: post #83

Earlier quoted context omitted.

Its a little too much.... I have to ask it to explain some of the terms in the context they are used and I am getting tired of it. 'Seam', 'overload', 'spine'.... having to mentally 'reinterpret/flatten' the sentence is tedious. When asked to re-explain it starts with some half apology. Then, on the next query it does it all over again.

What’s killing me is that the vernacular is creeping into my coworkers’ speech patterns too.

"SAY LOAD-BEARING ONE MORE TIME!"

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

#519

Post by bwfan123 »

stefan_ wrote: post #222
inferniac wrote: post #207

Earlier quoted context omitted.

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"

CLAUDE.md is mostly powerless against the reinforcement learned crap. I'm up to three separate instructions telling it to cut out the hyper verbose, retelling history comments and it still writes them every time.

> CLAUDE.md is mostly powerless against the reinforcement learned crap.

When you dont know the cause, you dont have a fix. Thats the biggest issue i have with all of AI is that we dont know how it works, and yet we think it will be great ! This is more like a religious belief than a scientific one. There is no causal model of how it works, there is no theory. And the temerity to call it intelligence is annoying.

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

#520

Post by jmstfv »

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've switched to Codex a few months ago when Claude's weekly limits were getting pretty stiff, and I haven't looked back. Both GPT 5.5 and 5.6 are quite capable, especially compared to nerfed Opus 4.7 (haven't tried 5).

Also, the Codex guy regularly resets weekly limits for everyone, which is a nice bonus (I know it's a temporary gimmick to attract more users, but I might as well use it while it lasts.)

Post reply on HN