Categories
Authors Storytelling Writing

The Architecture of Resonance

There’s a particular kind of madness that strikes writers late at night, or in the stagnant hours of mid-afternoon, when you find yourself staring at a single sentence for twenty minutes.

You’re weighing a semicolon against an em dash. You’re wondering if “murmur” is too soft or if “whisper” is too clichรฉ. All of this while knowing, with complete certainty, that no reader will ever stop to appreciate this specific choice. They’ll just read the sentence and move on.

So why do we do it?

In Draft No. 4, John McPhee โ€” the legendary literary journalist who spent decades at The New Yorker โ€” shares a principle he still writes on the blackboard at Princeton. It’s actually a quote from Cary Grant: “A Thousand Details Add Up to One Impression.” The implication, McPhee explains, is that almost no individual detail is essential, while the details as a whole are absolutely essential.

I find this idea endlessly useful. And a little reassuring.

Think about walking into a beautifully designed home. You don’t notice the precise angle of the crown molding or the specific undertones of the paint. You don’t walk in and say, “Ah yes, Alabaster White.” You just feel warmth, or elegance, or comfort. The impression is singular โ€” but it’s entirely built from a thousand invisible decisions someone made before you arrived.

Writing works the same way. The rhythm of your sentences, the specificity of your verbs, the way a paragraph ends โ€” these are the details. Individually, they’re expendable. Swap “murmur” for “whisper” and the piece survives. Delete the semicolon and the world keeps turning.

But collectively, they are the piece.

Start compromising โ€” reach for the easy clichรฉ, let a clunky transition slide, settle for vague where you could be specific โ€” and the foundation slowly rots. The reader won’t be able to name the moment they lost interest. They’ll just close the tab. The impression shifts from resonant to flat, without anyone quite knowing why.

Writing, then, is an act of quiet faith. It asks you to labor over things no one will applaud. Nobody claps for an em dash. But the work isn’t really for applause โ€” it’s out of respect for the whole.

We curate a thousand invisible things so the reader can feel one visible truth.

So the next time you’re agonizing over a single word at midnight, remember: you’re not just picking a word. You’re placing a tile in a mosaic. Cary Grant understood it. McPhee put it on a blackboard. You might as well make it count.

Categories
AI AI: Prompting Writing

AI as a Mirror, Not a Maker

Iโ€™ve been thinking a lot lately about how we move past the novelty phase of AIโ€”beyond just asking a chatbot to “write a poem about a turkey” or summarize a meetingโ€”and into actual thinking with these tools.

As a lifelong learner, Iโ€™m always on the hunt for workflows that help me synthesize information better. Most of the “AI for writing” advice I see online is pretty generic. But I recently came across a breakdown of how four high-profile writers are making effective use of tools like NotebookLM and Claude in ways that are much more sophisticated than simple text generation.

What jumped out at me is that none of these writers use AI to write for them. They use it to structure, challenge, and code.

Here are the four models that caught my eye.

1. The Triangulated Research Base (Steven Johnson)

Steven Johnson (Where Good Ideas Come From) has a workflow that solves a problem I face constantly: the messy “research phase.”

Instead of treating the AI as an oracle, he treats it as a connection engine. He creates a dedicated notebook (using Googleโ€™s NotebookLM) and uploads three distinct types of sources: a primary source (like a raw PDF or study), a secondary source (like a context article), and a multimedia transcript.

Then, rather than asking for a summary, he asks the AI to find the friction between them: “What themes appear in the interview transcript that contradict the historical account in the PDF?”

Itโ€™s less about getting an answer and more about finding the blind spots in your own reading.

2. The Diagnostic Editor (Kenny Kane)

This one really resonated with me because it mirrors the experiment I tried recently with my “Bubble Bath” post.

Kenny Kane uses Claude not to generate prose, but to act as a ruthless developmental editor. He uploads a messy draft and runs a “Diagnostic” prompt. He doesn’t ask “fix this,” he asks: “Where does the argument drift? Where does the energy drop?”

He even has the AI analyze his best writing to identify his specific “DNA” (sentence length, vocabulary choice) and then asks it to apply that same tone to his rougher sections. Itโ€™s using the AI as a mirror rather than a ghostwriter.

3. The Memo-to-Demo Shift (Dan Shipper)

Dan Shipper at Every is doing something fascinating that changes the definition of writing altogether. He argues that in the AI age, we shouldn’t just describe a concept; we should build a small app to demonstrate it.

If heโ€™s writing about “Spaced Repetition,” he doesn’t just explain the theory. He asks Claudeโ€™s Artifacts feature to “Write a React component that lets a user test spaced repetition live in the browser,” and then embeds that little app directly into the essay. The writing becomes 50% prose and 50% software.

4. The Co-Intelligence Loop (Ethan Mollick)

Ethan Mollick focuses on breaking the echo chamber. Before he publishes, he spins up simulated personasโ€”a skeptical VC, a confused novice, an expert in a tangential fieldโ€”and asks them to critique his draft from their specific viewpoints.

Itโ€™s effectively a focus group of one.


How to Get Started

If youโ€™re like me, seeing all these workflows might feel a bit overwhelming. My advice? Don’t try to overhaul your entire writing process overnight. Just pick one experiment to try this week.

Here are two simple entry points:

Experiment A: The “Blind Spot” Check (For Research)

If you are reading up on a topic, don’t just take notes. Open Google NotebookLM, create a new notebook, and upload your sources (PDFs, URLs, or pasted text). Then, ask this specific question:

“Based strictly on these sources, what is the strongest argument against my current thinking? What connection between Source A and Source B am I missing?”

Experiment B: The “Ruthless Editor” (For Writing)

If you have a rough draft sitting on your hard drive, copy it into Claude or ChatGPT and use this prompt (adapted from Kenny Kaneโ€™s workflow) before you do any manual editing:

“Act as a senior editor. Do not rewrite this text. Instead, analyze my draft and tell me: 1) Where does the argument lose energy? 2) Does the opening hook successfully promise what the conclusion delivers? Be critical.”

Iโ€™ve found that using the tools this wayโ€”as a partner for thinking rather than just generatingโ€”is where the real magic happens.

Which one will you try first?