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

671–680 of 915 posts

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

#671

Post by oezi »

antonvs wrote: post #586
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…

It’s the repetitiveness of style, the attempt to make everything seem as impactful as possible, the use of short sentences (too much Hemingway in the training data?), and obvious patterns like “it’s not this, it’s that” and several others. Real human writing doesn’t follow such strict rules. When the same small set of rules is applied over and over throughout a text, it becomes obviously strange and machine-like.

I blame RLHF entirely for this. Nobody used to talk like AI speech before.

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

#674

Post by zmmmmm »

I'm with the author and others in this comment thread, speculating that effectively the balance has tipped to where humans are no longer the target audience of post training - other agents are. Whether it's through the reasoning / CoT, or whether it's in handing off to subagents etc, the focus has moved to agents communicating in "agent-speak" to themselves or other agents. And human niceties are just kind of, noise in the way of getting work done.

This will probably bring us to a cross roads where the folks that want to remain in oversight and control of the AI work will bifurcate from those that want to skate straight to the future where nobody looks at anything and outcomes are evaluated purely empirically.

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

#675

Post by mcmcmc »

agaj-nimm wrote: post #560
JacobAsmuth wrote: post #440

Earlier quoted context omitted.

Literally nothing indicates we've hit a peak, but I guess I'm discussing this with someone who thinks every iteration since Opus 4.6 had zero ROI so there's probably not much common ground here.

Four years ago LLMs were sometimes amazing, sometimes wrong, sometimes a huge time sink when it's almost there and you try to herd the tokens but it's like herding cats. Just today I had the exact same experience. Every single testimonial is the same as I described above, just emphasizing a different bit to defend or attack LLMs or to make a case for nuance. The two differences have been: (1) the 1.5 trillion dollar…

They will always be wrong sometimes, but it’s becoming less wrong and wrong less often. Everyone will have their own opinion on “good enough”, but if you expect perfection you are bound for disappointment. No need for that when random chance and Murphy’s law will bring enough anyway.

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

#676

Post by fluoridation »

oezi wrote: post #669
fluoridation wrote: post #646

Earlier quoted context omitted.

>Perhaps between model version releases, frontier labs can harvest the web and ask "What Claudisms do people mention negatively?" but I don't think they do that yet. That won't happen. People can't phrase their objections in a succinct-enough way. When they do, the objection is superficial ("too many em dashes") and doesn't strike at the core of what makes LLM output bad.

Don't talk about other people in such a way. If we had a way in Claude to mark a word/token and downvote/reduce it logits then it wouldn't be to hard to send loadbearing to token valhalla. In the future, I hope we get a way to randomize the language idiosyncrasies and/or personalities better.

I didn't mean it as a criticism, just a statement of fact. I can't do it either. It's difficult to say what about a writing style is bad beyond vague descriptions.

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

#677

Post by karthikiyengar »

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 having pretty decent results by configuring an output style that forces it to write for simplicity and scannability. The cognitive burden of reading through dense outputs compounds really quickly.

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

#678

Post by jsLavaGoat »

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…

Claude in particular seems to try and use its internal thesaurus but not exactly align the senses. It constantly uses "address" for place or location and "grammar" for structure, meaning, etc.

This is kind of a nitpick, but it seems like with prose writing there are still some things to learn.

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

#679

Post by karthikiyengar »

nmwp wrote: post #219
madradavid wrote: post #183

Earlier quoted context omitted.

"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." This. Thank you for expressing this so eloquently. I've tried to put a finger on this and you've done that for me. I wonder what the solution could be , Ask Claude to "Du…

I’ve asked it to use plain English, avoid jargon, explain terms before introducing them. Its first response was to make memory, it forgot after 5 prompts, then it suggested claude.md. Looked good at the start of a session, forgot after 6 interactions. Then it continued suggesting other locations, sometimes correcting its own corrections. Same effect, so today I got annoyed again. And then it suggested a new thing: ad…

Setting an output style (https://code.claude.com/docs/en/output-styles) definitely yields way better results than just relying on memory or Claude.md
Post reply on HN