31–40 of 46 posts
You just need to use this list as a prompt and instruct the LLM to avoid this kind of slop. If you want to be serious about it, you can even use some of these slop detectors and iterate through a loop until the top three detectors rate your text as "very likely human."
We wrote the paper on deslopping LLM and their outputs: https://arxiv.org/abs/2510.15061
What would you say are the top 2 red flags missing from the piece? Would love to know
There’s a really cool technique Andrew Ng nicknamed reflection, where you take the AI output and feed it back in, asking the model to look at it - reflect on it - in light of some other information. Getting the writing from your model then following up with “here’s what you wrote, here’re some samples of how I wrote, can you redo that to match?” makes its writing much less slop-y.
AI can copy 90% of your tone of voice but still use em dashes and corrective antithesis.
Ideally you'll have both /deslop and /soundlikeme (coming soon)
Just seems like the author could have said "write the damn thing yourself" and been done with it.
It will definitely help, but also some people, especially in marketing/sales, were writing like that before LLMs. So you should not only write the thing yourself, but also learn some good writing style.
Just don't use LLMs to generate text you want other humans to read. Think and then write. If it isn't worth your effort, it certainly isn't worth your audience's.
What is nice is that sometimes you will just write very badly what you want to say, like a scenario or badly written sentences, and just ask the LLM to reformulate that to be proper nicely written text. But in that case, there are big chances that the stylistic issues described in the article are present despite you having carefully crafted the content.
So when people say they never get a good output it's because they're trying to from
thought > article
instead of
thought > exploration > direction > structure > outline > article
I would also point to a human-generated (and maintained) list: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
Just seems like the author could have said "write the damn thing yourself" and been done with it.
As they say, "Bait used to be believable."
Earlier quoted context omitted.
Believe me, I've tried. By the time i get the documentation to be the way I want it, I am no longer faster than if i had just written it myself, with a much more annoying process along the way. Models have a place (e.g. for fixing formatting or filling out say sample json returns), but for almost anything actually core content related I still find them lacking.
I guarantee if you give me your prompt and the output you got I can fix it and get you a 10x better output in less than 5 minutes. DM me on substack if you don't wanna post it here, I'm honestly happy to help wherever I can.
And even if the style is (or isn't) LLM'ish, it does not say/help if the (even-filtered) content makes sense / is correct or is BS
Style does matter, sure..
https://hbr.org/1982/05/what-do-you-mean-you-dont-like-my-st...