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

711–720 of 916 posts

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

#711

Post by SupremumLimit »

mlsu wrote: post #546
xyzzy_plugh wrote: post #515

Earlier quoted context omitted.

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 distribut…

Fair. What I am trying to get at is when people talk about "intelligence," beyond academic debates such as this one that mentions qualia, they are talking primarily about value. How intelligent the thing is is how valuable it is (often directly, in an economic sense). My argument is that value is a relational thing that must involves human feeling, intelligence actually has very little to do with it. When a child slo…

I think you're conflating intelligence with consciousness. The point of Blindsight is to lead us to the idea that intelligence doesn't require consciousness (and further, that consciousness might even act as a limiter on intelligence).

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

#712

Post by NamlchakKhandro »

billbrown wrote: post #633
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.

which is just the same as having it in your AGENTS.md and also having a agent_settled hook that reminds it on how to talk

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

#714

Post by saaaaaam »

sibeliuss wrote: post #636
saaaaaam wrote: post #531

Earlier quoted context omitted.

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.

Good fight / entirely thankless fight maybe.

I can’t help feeling like this is the last gasp of the old internet. Those tiny corners of expertise can so easily be eliminated through a few months of “AI! SHINY!” and there’s no coming back. I’ve seen a couple of other communities decimated by AI. The participants start posting AI slop and then remarkably quickly everyone else just stops commenting. It’s awful.

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

#716

Post by crooked-v »

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…

> “the x”, with x having not only no antecedent but also being a coined word or quasi-synonym for something that is already named in the code base

It does the same thing if you try to get it to do analysis of text or turn data into summaries. It will invent cryptic hyphenated compound words to describe things instead of using plain language or preexisting terms.

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

#717

Post by JohnBooty »

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…

    Will Claude will act as a therapist or produce 
    value or produce a work of art? No. It cannot, 
    because it does not have a soul.
I tentatively agree, although I'm only tentative because I don't think it's an interesting question.

Here's what I do think is interesting. You!

I mean... yes, you, too but not you specifically. The plural "you" that the english language lacks.

And so here's what I think is the actual interesting question. Might AI help you create art? Or be a therapist? Or something else interesting and worthwhile?

Maybe AI won't write the next great guitar solo. I'm pretty sure it won't. But might it help you learn to play guitar? Help you fix your broken guitar amp? Help you understand some tricky parts of guitar playing? Help you work through some tricky tabulature where you can't tell if you're playing it wrong or if the tab is just bad?

I don't know. But that's my angle for finding any of this interesting.

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

#718

Post by gigatexal »

I’ve become disillusioned with Anthropic and their models. Sonnet 5 was fantastic. It’s slow and dumber now. Of course this is anecdotal but it’s true. I had one to fable to get anything decent and then my employer is paying Fable costs. Yikes.

For my personal projects I’m using Claude code in the terminal with Kimi and Deepseek models. I find the Chinese models cheaper, just as good if not better, and the real value add from Anthropic being the harness: Claude code.

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

#719

Post by therein »

app13 wrote: post #571
Valord wrote: post #416

Earlier quoted context omitted.

Sticking mostly with 4.6 here too.

Last model from Anthropic that I can use as a security researcher. 4.8+ won't even look at my git repos Granted they contain robot dog malware, but still.

The moment it sees shellcode, it runs for the hills.

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

#720

Post by timpera »

buu700 wrote: post #640
boomlinde wrote: post #496

Earlier quoted context omitted.

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.

I've been noticing the same thing since 5.4- it starts with "Yes" yet I haven't asked a question. I think it might be related to the reasoning, like it's answering its own questions?
Post reply on HN