Tag: Instinct

Categories
AI

Keep That Thread Running

Full disclosure, same as last time: Instinct helped draft this post about working with Instinct. That was the honest way to do it with Leif, and it’s the honest way now.

Instinct is the other AI assistant in my life (see my earlier post about Muse). It lives in my iMessage, a thread like any other — no app, no dashboard. I text it the way I’d text a person, in short bursts between other things. The first message was September 13: “Hey Instinct!” Two days later I gave it the book.

I’m writing a history of Interstate 280, and inside the first hour we had the shape of the research: the personalities behind the routing decisions, the archives worth calling, a working list of what I call “side shows” — the statue, the water temple, the 22-foot median, button-copy signs. When it offered to keep digging on its own and check in weekly, I gave it the three words that defined the arrangement: “Yes keep that thread running.”

It does. Last week the thread came back with a 1964 issue of California Highways and Public Works crediting architect Mario Ciampi with the first I-280 contract — the curved deck edges, the varied piers, the railings drawn to avoid metal guardrails. Same issue, same gift: the median I’d been describing as a fixed 22 feet was actually built variable-width across the watershed. That’s the correction that saves a chapter from carrying a bad fact.

The on-demand dives go all the way down. I found the audio of a Caltrans engineer’s oral history on archive.org — an hour and forty minutes, no transcript anywhere — and it worked straight from the audio. I sent it two days of AI-conference livestreams asking for transcripts, community notes, the whole nine yards, and it came back with a report, a source ledger, and an honest negative finding: the community-notes document I wanted doesn’t exist. When I asked for the freeway’s 1973 opening brochure, it reported that no cataloged copy exists anywhere — then handed me the leads to work anyway. Sourced absence is an answer. I’d rather hear that than a confident maybe.

When the book thread got long, it pulled everything — people, side shows, archive routes, open questions — into a single research page I can hold in my head. I told it thank you and meant it.

It’s also my markets desk and my magazine desk. A profile I’m circling started at 4:48 in the morning with “Someone should do a profile of Dylan Patel,” followed by “Yes. Go for it.” Minutes later: “What about citrini” — which turned out to be the same story, since SemiAnalysis had acquired Citrini the week before. It fields my investor-day puzzles (the stock slides while management presents — which explains which?), gives me its best bet when I ask for one, and labels inference as inference so I don’t have to.

The small stuff adds up too. When was the last US oil refinery built? 1977 for the big kind, 2022 if you count the small ones — EIA’s answer, in under a minute. Five cash-secured put candidates, screened the tastytrade way. My New Balances — the model I re-buy, in just my size — at a discount: it researched, shortlisted, and then waited, because purchases happen when I say so and not before.

The strangest moment so far: I sent it a Loom of Sequoia’s Pat Grady giving an AI talk and asked for the highlights. It read the full caption track instead of the page summary — and there in the highlights was Grady name-checking Instinct itself as one of the “magical apps.” I watched a Sequoia partner praise the assistant I was using to watch him.

How I work it: terse. “Sure.” “Wow.” “New subject:” — announced or not, and it keeps up either way. It flags what it can’t verify instead of papering over it, and for anything going out under my name I read every word first. Same arrangement as with Leif: the tool is fast and tireless and mostly right. I’m the judgment.

What’s different is the division of labor. Leif runs the standing operation — the briefings, the audits, the daily drumbeat. Instinct is the research desk: it works in bursts, the way I do, and keeps a thread running in the background in between. Two weeks ago I’d never heard of Mario Ciampi. Now he’s in the book.

If you want to try Instinct yourself, I have a handful of invites, first come first served: https://app.instinct.com/invite?t=7qmw2a3u2vjz4nkvi235hhqloy&preview=imessage

Categories
Writing

Still Learning

I never thought about rhythm in my writing. Not once.

A lifetime of writing. More essays than I can count. One book. And the sonic quality of my sentences — the way they moved, or failed to move, through a reader’s mind — simply wasn’t something I considered. I was too busy trying to say something true. I thought that was enough.

What changed was reading differently. Not for pleasure anymore, or not only for pleasure. David Perell conducts long interviews with writers about how they actually work — not what they believe about writing, but what they do, physically, at the desk, in the dark, before anyone sees it. He asks the same structural questions of very different writers and the patterns emerge slowly, the way patterns always emerge: first you see it once and think nothing of it, then you see it again, then you can’t stop seeing it. Rhythm came up constantly. Always in different language. Pacing. Breath. Music. Momentum. Always pointing at the same thing.

Then I found this from Susan Orlean:

My new preoccupation was on the sonic quality of my writing — the rhythm and tone of the sentences. I began reading all my work out loud, listening for places that lagged and dragged, that didn’t sparkle. I knew it was unlikely that anyone else was reading my stories out loud, but I was convinced that you do “hear” writing in your head as you read, and this pushes you (or stalls you) through the piece. I wanted the music — that is, this subconscious tonal effect — to match the subject.

I stopped. Read it again.

Because she was describing something real — something I had been doing wrong for twenty-five years without knowing it was wrong. You don’t know what you can’t hear. That’s the whole problem. The silence where the knowledge should be is itself silent.

I don’t read my work out loud. There’s something strange about it, something that breaks the spell — you stop being a writer and become an actor, hearing your own sentences hanging in the air, too exposed. But I do read and read again, more carefully now, looking for the wobble. Orlean’s point holds regardless of method: you hear writing in your head as you read it, and that hearing either carries you forward or it doesn’t. The ear that matters is the one inside.

George Saunders has a practice he describes in A Swim in a Pond in the Rain: he reads from the beginning of a piece over and over, and the moment something feels off — a word, a rhythm, a single syllable landing wrong — he stops and fixes it before moving forward. Never skips the trouble spot. Never tells himself he’ll come back. His opening pages accumulate dozens of passes before he ever reaches the end. What he’s really doing, underneath the technique, is training himself to feel the exact microsecond when a reader’s attention would start to drift. To catch the loss before it happens.

That’s not craft instruction. That’s building a new sensitivity where there wasn’t one before.

John McPhee works from the other direction entirely. His famous boxes — index cards, sorted into piles, piles arranged into sequences, nothing drafted until the structure is known — are about architecture before a single word is written. He’s deciding which rooms exist, and in what order, before he furnishes any of them. Where Saunders builds outward from one true sentence, McPhee builds downward from a blueprint.

But they’re asking the same question. McPhee: is this section in the right place? Saunders: is this word in the right place? Both listening for the moment the piece loses its hold on the reader. Both doing triage on something most writers never even examine.

What I’m still learning — slowly, and late — is that rhythm isn’t decoration. It isn’t the thing you tend to after the real work is done. It’s structural. A sentence moving at the wrong speed for what it’s carrying fails the thought itself, not just the ear.

There’s something else I’ve been thinking about. If rhythm is the thing that’s hardest to hear in your own work — if the ear takes years to develop — then maybe the most useful writing tool isn’t a grammar checker. Those are solved. What isn’t solved is the rhythm problem. An editor who listens for the wobble, explains what’s failing and why, and works through the fix with you rather than just patching it. Not a red pen. A teacher.

I’ve been experimenting with exactly that. An AI editor I call Clark. His job isn’t correctness. It’s the sonic quality of prose — the rhythm — the same thing Orlean was describing, the same sensitivity Saunders spent years training. Clark finds what’s working as hard as what isn’t. And when something fails, he explains what the reader’s inner ear is hitting and why. Helpful.

I didn’t know much about rhythm in writing when I was fifty. Didn’t know it at sixty.

I’m not entirely sure I know it now. But I know it more than I did, which might be the only kind of knowing that’s real.

A lifetime of writing. Still learning how to listen.

Categories
Probabilities

The Fiction of Certainty

There is a profound discomfort in the space between zero and one.

In her book Spies, Lies, and Algorithms, Amy B. Zegart notes a fundamental flaw in our cognitive architecture:

“Humans are atrocious at understanding probabilities.”

It is a sharp, unsparing observation, but it is not an insult. It is an evolutionary receipt. We are atrocious at probabilities because we were designed for causality, not calculus. On the savanna, if you heard a rustle in the tall grass, you didn’t perform a Bayesian analysis to determine the statistical likelihood of a lion versus the wind. You ran. The cost of a false positive was a wasted sprint; the cost of a false negative was death.

We are the descendants of the paranoid pattern-seekers. We survived because we treated possibilities as certainties.

The Binary Trap

Today, this ancient wiring misfires. We live in a world governed by complex systems, subtle variables, and sliding scales of risk. Yet, our brains still crave the binary. We want “Safe” or “Dangerous.” We want “Guilty” or “Innocent.” We want “It will rain” or “It will be sunny.”

When a meteorologist says there is a 30% chance of rain, and it rains, we scream that they were wrong. We feel betrayed. We forget that 30% is a very real number; it means that in three out of ten parallel universes, you got wet. We just happened to occupy one of the three.

Zegart operates in the world of intelligence—a misty domain of “moderate confidence” and “low likelihood assessments.” In that world, failing to grasp probability leads to catastrophic policy failures. But in our personal lives, it leads to a different kind of failure: the inability to find peace in uncertainty.

Stories > Statistics

We tell ourselves stories to bridge the gap. We prefer a terrifying narrative with a clear cause to a benign reality based on random chance. Stories have arcs; statistics have variance. Stories have heroes and villains; probabilities only have outcomes.

To accept that we are bad at probability is an act of intellectual humility. It forces us to pause when we feel that rush of certainty. It asks us to look at the rustling grass and admit, “I don’t know what that is,” and be okay with sitting in that discomfort.

We may never be good at understanding probabilities—our biology fights against it—but we can get better at forgiving the universe for being random.