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

461–470 of 915 posts

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

#461

Post by iFire »

swe_dima wrote: post #396
iFire wrote: post #224

Earlier quoted context omitted.

My prompt of asking it match the comment density of the last release of an exemplar project (Let's say sqlite) seems to work.

my prompt (doesn't help): > Go easy on the comments, only add comments if there's a big gotcha that is not clear from the code itself, or if something in another place is going to cause a side effect. Code should be self-documenting. When in doubt, don't add a comment at all. If you do have to add a comment, make it short and on point. Comments should show history of code changes or functionality, only comment on the…

Your prompt is so similar to my prompt.

> Go easy on the comments.

> If you do have to add a comment, make it short and on point.

I defined what easy meant numerically.

Match the comment density of FoundationDB, which is 12 to 14 percent of non-blank lines in `fdbserver`, `fdbclient` and `flow` at 7.3.

> only add comments if there's a big gotcha that is not clear from the code itself

Comment why the code does a thing, not what it does.

> Comments should show history of code changes or functionality, only comment on the current state (or not at all)

I call this the tenseless continuous-present voice.

Each sentence states what is currently true of the system.

This rules out past-tense edit narration, future or imperative planning, and aging temporal qualifiers such as “now” or “previously”.

A sentence that states a present truth stays correct as long as the code stays the same, and goes stale visibly the moment the code changes.

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

#462

Post by switz »

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…

4.6 was the last model that didn’t over-cook its writing in circular loops. I use it as a daily driver and drop into fable when I’m doing higher level architectural work. 4.6 is so much more efficient in its effort.

It became obvious to me very quickly that 4.7 and on were broken. I’m a little puzzled how others didn’t realize it, but maybe they don’t actually review model output (code) or have a strong process/workflow.

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

#464

Post by dannyw »

`/output_style new` can be used to tailor the output style to your preferences, e.g. make it more literal and task-execution focused, and feel free to return control to the user when unclear; can keep work going in the background.

The default behaviour is quite steerable.

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

#465

Post by kingleopold »

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.

no if prices were that high, millions of developers would switch to hand writing, open source LLM help and outsourcing at those levels, AI companies know this, you should too.

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

#466

Post by bcrosby95 »

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…

I wrote a harness for running tabletop RPGs. One of the key things to keep the LLM behaving correctly (such as not controlling the PCs) was being able to inject instructions with every new prompt, which I don't include in the history.

It seems like all harnesses could benefit from something like this.

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

#467

Post by UltraSane »

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…

Opus 5 sounds a bit like the dialog in Children of Dune where they talk like they are constantly trying to prove how smart they are and not actually communicate.

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

#468

Post by SubiculumCode »

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…

On the other hand, Opus 4.8 had an annoying habit of declaring a huge mistake was found, then two sentences later abruptly change its mind and say that it was in fact all okay. That's fine for chain of thought, but in the verbose output, it can lead to wrong impressions by the user.

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

#470

Post by chrisjj »

smallerfish wrote: post #344

I really wish these agents attem[pted less personality and were more mechanical. I find Opus 5 to be incredibly annoying. It's also significantly slower - repetitive tasks that used to take 10-15 mins now take around 40 mins. And, its writing is much worse, as stated elsewhere in the thread.

> I really wish these agents attem[pted less personality and were more mechanical.

Which will sooner convince the gullible of "AGI"?

Post reply on HN