Claude is an excellent proofreader, but don't let a single word it generates hit your final copy. Use it to catch things and point things out, and for nothing more.
And even bigger-picture stuff, like "you might want to zoom in here" or "this section isn't paying off". I've only in the past few months started using it for proofreading, and it's pretty solid.
But if you take any of its words, you're infecting your writing with Claude's tone, and it will show.
It's super useful as a reader of your writing. It's a terrible collaborator, unless you're writing for an audience of middle managers.
Vocabulary is only part of it. LLM style is pretty recognizable, and most people don’t normally write like that. One reason is because they’re trained in a lot of marketing material, news articles, and the like. If it sounds like a self-unaware middle manager writing on LinkedIn, but it isn’t one, it’s probably an LLM.
This app flags "'s infrastructure" as a hallmark of AI-generated prose. Other markers of AI generation include "'s not just", "making it", "'t just" (33x more likely in AI!), and "ecosystem".
Pangram seems like a useful service for the world we are going to face. To me the semicolon-newline pair reminds of AI almost immediately. I am surprised that this service didn’t point that out. It could be just to me this pattern is bothering though.
It is not, but I have used Claude to edit it.
Claude is an excellent proofreader, but don't let a single word it generates hit your final copy. Use it to catch things and point things out, and for nothing more.
I’ll keep that in mind, thanks!
Why?
It's good at spotting stuff, like:
* Overusing verbs
* Poor structure
* Bad transitions between grafs
* Passive voice
And even bigger-picture stuff, like "you might want to zoom in here" or "this section isn't paying off". I've only in the past few months started using it for proofreading, and it's pretty solid.
But if you take any of its words, you're infecting your writing with Claude's tone, and it will show.
It's super useful as a reader of your writing. It's a terrible collaborator, unless you're writing for an audience of middle managers.
I’ve always had a sophisticated vocabulary, now people think my content is AI generated. Frown.
Vocabulary is only part of it. LLM style is pretty recognizable, and most people don’t normally write like that. One reason is because they’re trained in a lot of marketing material, news articles, and the like. If it sounds like a self-unaware middle manager writing on LinkedIn, but it isn’t one, it’s probably an LLM.
The guy you are responding to has "All comments Copyright © 2010, 2011, 2012, 2013, 2015, 2018, 2023, 2031 Thomas H. Ptacek, All Rights Reserved." in his HN profile....
Sounds like a hedge against Agentic bots.
Pangram itself looks like it was just generated by Google AI Studio.
This app flags "'s infrastructure" as a hallmark of AI-generated prose. Other markers of AI generation include "'s not just", "making it", "'t just" (33x more likely in AI!), and "ecosystem".
I don't think it's trustworthy.
Pangram seems like a useful service for the world we are going to face. To me the semicolon-newline pair reminds of AI almost immediately. I am surprised that this service didn’t point that out. It could be just to me this pattern is bothering though.
> His answer:
"Where X actually lives" is a new hallmark of AI writing. I've noticed it a lot lately.