Comment by qalmakka
4 hours ago
> Run Android apps natively on Apple Silicon Macs. No emulator, no virtual machine, no Linux underneath.
God damnit Dario fix Claude already so that it stops using this sentence structure once and for all. Opus is so annoyingly recognisable that it has started to irk me badly lately
Why does it matter if it's easy to recognise? I prefer to know when I'm reading AI writing.
It's just overused and cliche now
I think you meant to say:
It's not just overused — it's a cliche now.
I've recently asked claude to be concise in writing documents. It's brilliant for me. You get things like:
No faffing around.
[delayed]
Hey, at least it didn't call it "beautiful" or "elegant".
Too late, people already talking like this too
You're absolutely right!
[dead]
It's not a bug, it's PR!
Some call it a triple construction.
Feature, not bug
[dead]
How would you prefer it. Does it not get the point across? Why does it even matter to you?
"Why does it matter to you?" Many Claudisms are grating to many people. Annoying is enough of a justification.
> Many Claudisms are grating to many people.
Would they be grating to them in the pre-LLM days?
5 replies →
For one, say what it does instead of what it doesn't do
"Run Android apps natively on Apple Silicon Macs."
1 reply →
"Run Android apps natively on Apple Silicon Macs. Uses translation instead of emulation."
No, slop generally doesn't get the point across efficiently.
It's hard to parse, it's grating, and in addition to the strange language you have to apply additional skepticism due to gross inaccuracy being more likely than in human-written text.
Variety is the Spice of Life
Cliches annoyed people before LLMs. There is a whole microgenre of essay ranting about the proliferation of various annoying cliches, bits of jargon, etc. the proliferation of Claude prose is simply rendering certain turns of phrase into annoying cliches, which people are reacting to in the normal way. Cliches also get the point across but nonetheless lots of people find them grating.
If you run a readability analysis on slop it scores very poorly. LLMs generally continue to be mediocre with the veneer of quality without context to guide them.