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

691–700 of 915 posts

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

#691

Post by eli_gottlieb »

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…

> and it’s a real challenge.

What model did you use to write this?

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

#692

Post by dr_dshiv »

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…

“It is not sharing anything, because it is not capable of sharing, because it does not have a soul”

soul.md though, just saying

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

#694

Post by peddling-brink »

sshine wrote: post #600
IgorPartola wrote: post #540

Earlier quoted context omitted.

I am curious why LLM writing has such an uncanny valley feel to it. Like if I was talking to a person who constantly used a phrase they liked I would notice it and it is possible I might get irritated by it, but I wouldn’t necessarily. In high school I had a teacher that would say “that type of thing” a lot. One time my friend and I counted it during one class period and he averaged to use the phrase every 48 seconds…

> if I was talking to a person who constantly used a phrase they liked I would notice it and it is possible I might get irritated by it There are sociological reasons why this happens less with humans: 1. You cycle your dumb repetitive jokes with everyone you meet, so nobody hears it twice 2. Those who know you well will notice when you're just repeating ("dad jokes") 3. As a person's idiosyncrasies are beginning to…

This is conjecture, but why couldn't they hire the writing equivalent of a voice actor?

Honestly I don't think it would take much. Doing it ethically would take a little more money, but not much, for them.

Hire a prolific author with the writing equivalent of the "midwestern accent". I have a terrible writing accent, so it couldn't be me, but these people are out there. Pay them a bunch of dollars to ingest their entire corpus, and to produce more as needed. Use an LLM to match the writing style of this author during the post-training RL, and get a brand new Claude voice out of it.

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

#695

Post by xivzgrev »

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…

Yes! Ive started getting a feel for AI writing on blogs. It feels slightly verbose and involves "reveals"

"It's not the naked man on your lawn waving a chainsaw that's scaring you. It's the burrito you ate for lunch: it went down easy, but now it's coming for you"

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

#696

Post by ethin »

bonesss wrote: post #480
ethin wrote: post #387

Earlier quoted context omitted.

I primarily use Claude Web, so my experience differs from cc users, but on Claude web you can no longer completely turn off memory. So what ends up happening (and it honestly is kinda sad) is that I'll start a new conversation with it, start talking about something completely different, and then it will just drop in random things from past conversations, and they aren't even things I wrote but things I asked it to pr…

The constant memory wouldn’t be so bad if it weren’t dumb, wrong, and forced. I hit the wall with it several times today trying to refine some text for a job application. The fact I considered doing babies first Rust project last fall lead to constant non-productive interjections and digressions about my supposed Rust skills and the Rust ecosystem. Trying to create an unrelated spreadsheet to model an investment resu…

Agreed. I wish I could turn it off completely but they no longer let you do that (because, you know, that would be too much to ask for...). The most hilarious thing is that I've had it refer to code it's generated for prototyping ideas I've had as mine! As an example, a few weeks back I was musing about Ada and how I wish there was another compiler in the OSS ecosystem for it, and now it will randomly throw in "You wrote an Ada 2022 compiler" when talking about my skills or where I'm at and I'm like.... Yeaaaaa okay then.

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

#697

Post by smoe »

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.

Something I've noticed quite a bit on the paid plans as well is that it starts its answers with "I mostly agree..." or "almost correct...," then goes through the list of points I made without actually disagreeing with any of them.

I assumed this is a system prompt or RL that nudges it to be always skeptical but then it still has like all the models the urge to appease the user.

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

#699

Post by aetherspawn »

rsalus wrote: post #630
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…

Yeah, +1 on the comment verbosity. Left alone it's actually insane. I've had to setup enforcement + templates (use ASD-STE100) to keep the cruft down. I'm worried this may impact the quality of outputs though - haven't measured it.

I also use the ASD-STE100 trick and it works pretty great, but the places that it decides to put huge comments are really weird and a lot of the time I just ask OpenAI sol “rewrite the comments in this file without slop” and it does a much better job for comments.

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

#700

Post by eluusive »

I can't quite put my finger on it. It doesn't write as well as Sonnet. Also, I feel like it follows instructions much more poorly. I do a lot of iteration on my projects and telling it to follow the same process I just had it do, and it'll deviate or invent something totally different.

I find myself having to check the work much more. It takes quite a few liberties with procedures I wanted it to follow.

Post reply on HN