I've never wanted to get in a physical fist fight with an LLM before Opus 5.
i would definitely punch it in the face
Why does Opus 5 feel worse to work with?
661–670 of 916 posts
Re: Why does Opus 5 feel worse to work with?
#662Opus 5 is SLOOOOW. Opus 4.8, compared to 5, was 3-5 times faster 3 months ago. I am waiting for 30-45 minutes for basic tasks that took 5-6 minutes in the past. Everything is extremely slow.
Re: Why does Opus 5 feel worse to work with?
#663The unsolvable dilemma still is scope opus 5 especially giving a simple directed task it would find ways to distract you from the the given task
Re: Why does Opus 5 feel worse to work with?
#664A gem Opus 5 gifted to me today: "A devastating pair of findings, and the first is beautiful in a way worth naming: the anti-vacuity floor is what blinds the gate to a vacuous case."
I get these kind of superfluous sentences all the time; drives me nuts.
Re: Why does Opus 5 feel worse to work with?
#665The 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…
My biggest pet pieve isn’t the LLM-isms themselves, but people who aren’t aware of them releasing documentation that’s clearly AI generated and being indignant when I ask “is this AI generated”
Re: Why does Opus 5 feel worse to work with?
#666My biggest problem with Claude is that anything I mention it won't shut up about. Then it gets saved in memory and it will keep repeating it to me forever with weird random exposition.
Re: Why does Opus 5 feel worse to work with?
#667Earlier quoted context omitted.
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.
The best trick I have after asking it nicely in all sort of ways is: 1. Have it build a scoring script that penalizes words outside a simple English list and approved jargon. Penalize sentences over 15 words as well. Add whatever else. 2. Run it in a loop to reduce the score while preserving intention This works much better than other ways I’ve tried. Of course it costs more. And I would apply it only to the output t…
After scoring, how do you tell the harness / model to only influence it's user-visible output tokens? Is there a deterministic way to specify this or is it a plain-text instruction in a hook or skill?
Re: Why does Opus 5 feel worse to work with?
#668Earlier 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…
You're right, and the load-bearing part of the argument is not what you think it is. Two ambiguities worth resolving before moving on: whether what you wrote also applies to ChatGPT, and whether you have custom instructions set up. Failure mode worth flagging explicitly: I didn't read TFA. (I'm becoming allergic to how these things write).
forgot the, "my original claim was overstated"
Re: Why does Opus 5 feel worse to work with?
#669Earlier quoted context omitted.
> 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…
>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.
Re: Why does Opus 5 feel worse to work with?
#670Earlier quoted context omitted.
I haven't had time to complain on here because I spend all my time trying to work out wtf Opus 5 is talking about and googling words I've never seen or heard in 40 years as a native English speaker.
I’m either out of touch with contemporary terminology but Opus 5 dropped “pre-mortem” on me today. Figured I’d just figure it out with more context.
It's project management jargon: https://en.wikipedia.org/wiki/Pre-mortem