I feel like with the rise of AI something that anonymizes writing styles should exist. For example it could look for differences in American versus British spelling like color versus colour or contextual things like soccer versus football and make edits accordingly. ChatGPT could be fed a prompt that says “Rewrite the following paragraphs as if they were written by an Australian” but I don’t know if it would have a good enough grasp on the objective or if it would start shoehorning in references to koalas and fairy floss.
I tried searching online to see if something like this existed and found a few articles from around the 2010s such as Software Helps Identify Anonymous Writers or Helps Them Stay That Way by the New York Times. It talks about stylometry and Anonymouth but it seems like Anonymouth hasn’t been updated in years. All recent articles seem to be about plagiarism and AI.
For context what got me thinking about the topic was remembering JK Rowling being revealed to be the author of a mystery novel called The Cuckoo’s Calling. Smithsonian wrote an article about it called How Did Computers Uncover J.K. Rowling’s Pseudonym?. I thought it could make for a neat post here.
This doesn’t differentiate different types of English but I will post it any just in case it is useful to you.
https://goblin.tools/Formalizer
Not even bad. The text is not a jab at OP, just a random thing that was in my head lol
This seems like an extremely potent tool for sealioning people. Thanks, I hate it.
I had to look up what sealioning is
https://en.wikipedia.org/wiki/Sealioning
That’s absolutely hilarious. I love it.
Love this tool!
original:
more passionate:
What happens when you take the output and make it the new input with “more passionate”?
E.g. how far can you push it? Or even the other way.
I didn’t try feeding the output back in but note you can click on the 3 peppers and move an intensity slider. That sample I posted was just middle intensity. When I max it out to 5 peppers, it grows to 4 paragraphs:
Less emotional (×3) is boring:
I did it with the sarcastic option elsewhere in the comment thread and it seems to plateau around the third time.
Hmm. But like there’s stuff in there that isn’t even part of the substance of what you said. Like the call to action at the end. That’s the type of thing you’d want to be pretty sure you really wanted to do in some circumstance where you want to communicate on a matter in plain sight but obscure your identity, as such a matter would presumably be pretty important and high stakes.
Indeed this bot could lead a mob of nutters into an insurrection attempt like that seen on jan.6. I guess the idea is to get ideas for rewording rather than use the output verbatim.
Not bad, though I think it missed a nuance with 16.7%.
alt-text
(Two screenshots side-by-side showing a text converter with the following input, settings, output + new settings and new output)
For sale: baby shoes, never worn.
Make my text:
More professional
Available for purchase: a pair of infant footwear, never utilized.
Make my text:
More sociable (waffle)
Hey there! So I’ve got these super cute baby shoes up for grabs. Unfortunately, they’ve never been worn. But that just means they’re brand spanking new and ready for a little one to rock them! Let me know if you’re interested in giving these adorable kicks a new home. #forsale #babystyle #neverworn
I like it so far
This looked fun so I took a section from a Hackaday article about the last Morse code station in America and ran it through.
The original
More sarcastic:
More sarcastic x2:
More sarcastic x3:
After that it kind of plateaus. It seems like in short bursts it could do alright depending on what modifier is chosen, other options seem to alter what the original prompt is trying to convey pretty drastically.
Thanks for linking it.
I’d like to interject for a moment
More passionate 🌶️🌶️🌶️🌶️🌶️
Backend of this is OpenAI / LLM; so my guess is if OP knows what they want, they can prompt such models or chatbots in such a manner to achieve the desired styles.
vs
I turned up the peppers to 5 and… Oh boy. Sociable at 3 is all “friendly” and “positive” and polite—it removes most of the dark stuff—and then Sociable at 5 loops around to… This:
Thanks for sharing 🙃