Writing Examples

Write for people

Make it shorter.

Writing With and Beyond AI: Fieldnotes from Computer-Mediated Poetry

Apr 10, 2026, 12:15 pm - Large language models can make writing mind-numbingly efficient — but the point of writing with AI should be to write what we couldn’t have written alone (without generating bland, derivative “slop”).

I knew my writing students were using AI. Their confessions led to a powerful teaching moment | Micah Nathan

The problem wasn’t just the perfectly polished, yet mediocre prose. It’s what’s lost when we surrender the struggle to translate thought into words

Writing Is Thinking

When you write about your work, it makes all of us smarter for the effort, including you. Done well, this kind of sharing means you’re contributing signal, instead of noise. But writers are made, n…

On Writing #3

Periodically I like to gather various observations about writing, and share my perspective.

How to write well with AI

Why people who pledge never to write with AI are telling on themselves

Hi, I'm David Perell.

I write, host a podcast, and run a writing school called Write of Passage.

The great shift of English prose

It's not because of shorter sentences.

Do LLMs write like humans? Variation in grammatical and rhetorical styles

As large language models (LLMs) have grown in power and become more widely available, research has focused on their ability to complete various tasks and the biases they exhibit when doing so. In this study, we instead examine their writing style in detail. We show that instruction-tuned models, which are trained to answer questions and solve problems, have a distinct noun-heavy, informationally dense writing style, even when prompted to match the style of informal speech and writing. These findings suggest that instruction-tuned models generate text that does not align with genre conventions familiar to human audiences, and demonstrate the value of linguistic variables in evaluating the output of LLMs., Large language models (LLMs) are capable of writing grammatical text that follows instructions, answers questions, and solves problems. As they have advanced, it has become difficult to distinguish their output from human-written text. While past research has found some differences in features such as word choice and punctuation and developed classifiers to detect LLM output, none has studied the rhetorical styles of LLMs. Using several variants of Llama 3 and GPT-4o, we construct two parallel corpora of human- and LLM-written texts from common prompts. Using Douglas Biber’s set of lexical, grammatical, and rhetorical features, we identify systematic differences between LLMs and humans and between different LLMs. These differences persist when moving from smaller models to larger ones and are larger for instruction-tuned models than base models. This observation of differences demonstrates that despite their advanced abilities, LLMs struggle to match human stylistic variation. Attention to more advanced linguistic features can hence detect patterns in their behavior not previously recognized.

Paragraph

Where writers share, grow, and get paid — one post at a time.

Wherein I Find Myself Writing About Writing

Most everyone finds writing to be challenging (especially those who say they enjoy it). This is because writing is an intentional, thoughtful act. This is as it should be, but “AI” has recently exacerbated the misbelief that writing is simply an output. In fact, it's a creative process that has merit in and of itself.

An open letter to Grammarly and other plagiarists, thieves and slop merchants

To everyone at Grammarly, I am writing a book right now, a really challenging endeavor that no doubt someone in Silicon Valley will think it’s fine to steal the day it’s published. I’ve been a professional writer for decades, even though the number of ways to make

The Human Skill That Eludes AI

Why can’t language models write well?

The language of generalization.