I had ChatGPT do the comparison for you! I am trying different styles. I usually write now when I get the feels — like I have something to communicate to a specific founder(s), or when there’s something really interesting happening in the world.
I think the ChatGPT critique is okay. This essay was too long. I told @GuptaRK22 whose writing I admire I thought it should have been half. Sermon-like? Youch. Taste in food is an obvious metaphor here. The idea that this is more “manifesto-like” is fair, but I have a stronger point of view on a lot of things than 5 years ago.
There were a few anecdotes I forgot to put in — like Ivan being friends with Dylan because he was a top, 14h/day type user. It’s not meant to be the same as a “what’s happening” piece, so I don’t think lots of citations/links make sense.
I still find trying to draft with AI extremely frustrating. It doesn’t have the coherence and voice, but maybe it’s my prompting technique, and I’m decidedly anal about writing. The way I do use AI is to have it repeatedly critique a draft, sometimes improve it based on that critique, and mostly just be annoyed.
I often say “I hate writing, because it’s almost as hard as thinking.”
Soon though, I’m sure!
https://t.co/xK67uiVygL
Quoted context
These are the quoted author’s words.
such an incredible essay from sarah.
as an aside -- i've been following @saranormous' writing for a while now. as i read through, the style appeared ai-aided and ofc, i am keen to see how people are using ai to write. so i went to grok to see if it'll venture a guess by comparing her earlier pre-ai era tweets vs a snippet from this essay.
fired up grok deep research to do this and tbh - the way it approached it was sorta weird. grok's main advantage is that it should have direct access to the advanced search algorithm and should be able to take a direct prompt like "compare sarah's writing style between 2022-2024 and this essay" and it should've made a beeline straight to the x search tool and put in advanced parameters like username, date etc.
instead, it took a bunch of keywords and puttered around 'mindlessly' searching across internet article, threaderapp, and so on, before it landed on searching & results natively from x
sometimes rules are useful. teaching https://t.co/ah6WKuQGx8 to use x properly is useful. not everything needs to be inferred from scratch🤷♂️
swami_rooted ↗