When Opus 5 came out I felt myself struggling to follow along and at first was wondering if this is the moment the machine surpassed my ability to follow along and be useful. However over time it does appear it's all an artifact of the language choice Opus 5 is going with, along with the strange manner of speaking. Its engineering choices and solutions aren't "beyond my ability to follow along", just its wording...
Why does Opus 5 feel worse to work with?
591–600 of 915 posts
Re: Why does Opus 5 feel worse to work with?
#592Earlier 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.
Wikipedia's own "Signs of AI Writing" page distills it nicely:
- The subject becomes simultaneously less specific and more exaggerated.Re: Why does Opus 5 feel worse to work with?
#593Re: Why does Opus 5 feel worse to work with?
#594The 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…
There really needs to be a "terse mode" for Claude. It's WAY too loquacious. I'm hoping they aren't doing it on purpose to burn tokens.
Re: Why does Opus 5 feel worse to work with?
#595Because it is worse? It is optimized for token maxing, this time the output tokens are maximized.
Re: Why does Opus 5 feel worse to work with?
#596Because it’s worse. Occam's Razor.
Re: Why does Opus 5 feel worse to work with?
#597Earlier 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…
[dead]
Re: Why does Opus 5 feel worse to work with?
#598This custom prompt on claude.ai fixes it:
Use Simplified Technical English rather than being overly verbose.
Re: Why does Opus 5 feel worse to work with?
#599The 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…
I think the Opus 5 formula is to be the little professor treating your ideas like an essay for grading, or like a buyer analyzing merchandise for purchase.
Re: Why does Opus 5 feel worse to work with?
#600Earlier quoted context omitted.
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).
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 wear on their social circles, they will be getting small clues to stop saying those things. Agents don't get these social between-the-lines cues to stop a certain behavior, they endlessly repeat. 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.