Categories
Aging History Memories

Two-Stroke Memory

On April 29, 1986, a fire started in the Los Angeles Central Library and burned for hours. When it was over, hundreds of thousands of books were gone and hundreds of thousands more were soaked and scorched and bound for the freezers. Susan Orlean spent years trying to understand that fire, and somewhere in the middle of the work she wrote a sentence I haven’t been able to put down. Each of us, she says, carries a private library of a life lived, one no one else can entirely share, and it burns down and disappears when we die.

Then she turns the page. But if you take something out of that collection and hand it to someone, on the page or in a story recited, it takes on a life of its own.

I keep running the inventory on my own shelves, and it is a strange and unreliable catalog.

Categories
Authors Writing

Write Till You Drop

Annie Dillard died on Tuesday, September 15, at her home in South Wellfleet, Massachusetts. She was 81.

I have been reading her for years, and I keep returning to her because she makes writing feel both more serious and more alive. She was demanding without turning grim. She reminded you that the work is hard, then made you want to sit down and do it anyway.

Her essay “Write Till You Drop,” published in The New York Times in May 1989 and collected in The Writing Life, contains more useful advice about writing than many books on the subject. The line I remember first is this one: “You were made and set here to give voice to this, your own astonishment.” That seems to me the whole assignment. Pay attention to what stops you. Find the thing you cannot quite explain. Then try to give it a voice.

Dillard tells of a student asking a well-known writer, “Do you think I could be a writer?” The writer asks back, “Well, do you like sentences?” What a perfect answer. Writing begins thereโ€”not with wanting to be a writer, but with liking sentences enough to make them, take them apart, and make them again.

I have been blogging since 2001. Over that time I have written thousands of sentences, some better than others. The blog has been a way of noticing what I notice. It has also taught me that the only reliable way to keep writing is to write. Not to wait for a grand subject or a clear runway. Just begin with the thing at hand and see where the sentences lead.

Dillard is especially good on the danger of saving things. “Spend it all, shoot it, play it, lose it, all, right away, every time,” she writes. Do not hold back the best image, the sharpest thought, or the story you think belongs somewhere more important. Use it now. If you lock it away, she warns, you may open the safe later and find ashes.

That lands differently for me now. I recently started keeping a list of words and phrases I love, after reading that Susan Orlean has long done the same. I like the habit. It sharpens attention. But Dillard would probably lean over my shoulder and say: Good. Now spend them. A list is not the work. The words have to leave the safe.

The same is true of the book I am working on about Interstate 280. It is a long project, full of engineering, politics, landscape, memory, and side roads that keep turning into stories of their own. A smaller treatment might be easier. But Dillard has an answer for that, too: “It is no less difficult to write sentences in a recipe than sentences in Moby-Dick. So you might as well write Moby-Dick.”

She says a writer should play the edges of the field, like a tennis player who reaches for the shots that land at the lines. That feels right for the I-280 book. The highway is the center of the court, but much of the life is at the edges: a dam, a billboard that is not there, a ridge preserved from development, an engineer whose name has nearly disappeared. Those are the shots worth chasing.

Dillard closes with Michelangelo’s note to an apprentice: “Draw, Antonio, draw, Antonio, draw and do not waste time.” That is not complicated advice. Neither is her deeper promise: “No manipulation is possible in a work of art, but every miracle is.”

I keep a folder for the I-280 book. It is getting fat: a dam, a billboard that is not there anymore, a ridge somebody fought to preserve, an engineer whose name I have to look up every time. None of it is spent yet. Dillard would want to know what I am waiting for.

Categories
Aging San Francisco/California Street Photography

The Permission of Fridays

Doug always walked a half-step ahead, which meant he saw things first, which meant I was usually watching him see them โ€” the tilt of his head, the small pause before he brought the camera up โ€” before I ever turned to look myself. Market Street on a Friday morning has its own weather system, independent of the sky: the gray light fog gives even bright colors.

We would set out with no destination, which was the whole method โ€” what Jay Maisel, who died this summer at ninety-five, called going out empty. Leave the plan at home, he taught generations of photographers, so there’s room left in you to see something you didn’t already expect. You cannot plan to be astonished. You can only put yourself in the path of it and hope.

I have thought about those walks more than I expected to, now that they are gone. Not gone dramatically โ€” no falling-out, no single last Friday we knew was the last Friday. Covid arrived and shut the passes between people the way weather closes a mountain road, and by the time it reopened, the rhythm had broken. We still talk. We just don’t walk anymore, and I have never entirely worked out why something so simple didn’t start back up, the way you’d think a habit that good would insist on its own return. It just didnโ€™t come back.

Susan Orlean, in Joyride, writes about being a writer as a kind of permission โ€” an excuse to linger in places past the point a normal person would move along, and then to go back and report on what was seen. She’s citing Mary Oliver’s instructions for living a life: pay attention, be astonished, tell about it.

A camera grants the identical permission a notebook does. Nobody stops a man with a camera on Market Street and asks him what he’s doing there. The camera is its own credential โ€” I have a reason to be looking at you, at this doorway, at the light falling across these particular twenty feet of sidewalk, longer than is socially normal. Doug and I weren’t tourists and we weren’t reporters and we weren’t, most days, even talking about what we saw until afterward, over lunch. We were two men who had given ourselves formal license to pay attention to a city we loved, as if it might not be there next Friday.

It mostly was there next Friday. Until it wasn’t, in the way that most disruptions to a good practice aren’t dramatic so much as quietly permanent โ€” a scheduling gap that never gets rescheduled, a street that starts to feel unfamiliar again because you stopped walking it with intention. I still have the pictures. A woman waiting at a bus stop with an expression I never satisfactorily explained to myself. The chess player’s hands, mid-reset, waiting on the next stranger. Doug, once, caught by someone else’s lens, walking a half-step ahead of a man he didn’t know was photographing him photographing the city.

The third instruction is the one that survived when the walks didn’t. I don’t walk Market Street with Doug anymore, but I’m telling you about it now, on a blog nobody assigned me to keep for twenty-five years. The credential just changed instruments โ€” camera to keyboard. Orlean’s point, I think, is that the excuse and the obligation were always the same thing. You get to be there because you intend to come back and testify, and the testifying is the toll, due whether or not the place is still there when you go looking for it again.

Doug and I are not going to start walking on Fridays again. I’m too old for that kind of recommitment, and pretending otherwise would just be a nicer way of lying to myself. Plus physically itโ€™s just beyond me now. This essay is itself a kind of substitute โ€” the telling standing in for a habit of attending that got interrupted and never fully repaired.

Mary Oliver’s instructions don’t say what to do when the astonishment outlasts the practice that produced it. Maybe that’s the fourth instruction nobody wrote down: keep telling about it anyway, especially after you’ve stopped going. Or at least remembering.

Categories
AI Apple Google

The Library You Already Own

Sharon Park in the morning is not a dramatic place. There’s a duck pond, a stand of oaks that go gold too briefly in November, and a loop I’ve walked enough times that my legs know it better than my eyes do. It is, in other words, exactly the kind of place where a person starts talking to himself. Not out loud. In the productive, low-grade way โ€” turning a sentence over, arguing with an idea from the day before, checking a thought against something you believe about yourself.

I think in five years I’ll be doing that walk with something else along. Not a search engine. Not another chatbot trained to know a little about everything and a lot about nothing in particular. Something closer to a second set of eyes on my own life โ€” a reasoning engine, lean and mostly private, that has actually read the things I’ve written and doesn’t need me to explain who I am before it’s useful.

Here’s the distinction that matters, and it took me longer than it should have to see it clearly. The AI industry has spent years in an arms race over how much of the world a model can hold โ€” more facts, more languages, more of the internet compressed into weights. That race will keep going, and somebody else can have it. What I want is smaller and stranger: a model that knows comparatively little about the world and quite a lot about me. My core values document. The portfolio spreadsheets. Fifteen years of blog posts. The half-finished notes for the I-280 project, sitting in a folder, waiting for someone โ€” or something โ€” to ask the right question about them.

I spent a career in payments infrastructure, which means I spent a career thinking about a very specific kind of trust: the kind where a stranger’s system has to make a judgment call, in milliseconds, about whether to say yes. Fraud models don’t work because they know everything about commerce. They work because they know an enormous amount about one account, one pattern, one person’s ordinary Tuesday โ€” enough to notice when Tuesday stops being ordinary. That’s the architecture I keep picturing, aimed inward instead of outward. Not a system trying to know the world. A system trying to know me, well enough to notice when I’m drifting from what I said I cared about.

I can already feel the shape of the mornings this would change. Right now, when I sit down to look at RMD requirements against the tax picture, I’m doing the translation myself โ€” pulling numbers into a story I can actually feel the weight of. A reasoning engine grounded in my real holdings wouldn’t just run the scenario. It would know that I don’t want the scenario dressed up as a spreadsheet; I want it dressed up as a conversation, unhurried, the kind you’d have over lunch with someone who already knows the whole situation. And on the mornings when I sit down to write, instead of staring at a blinking cursor and a blank page that has no idea I exist, I’d be handing a draft to something that has actually read my last two hundred posts and knows the difference between the sentence I’d write and the sentence I’d cut.

None of this is especially exotic technology. Apple and Google are already building toward it โ€” Neural Engines fast enough to do real reasoning on-device, retrieval systems that can reach into your own files instead of the entire internet, fine-tuning that’s getting cheap enough to personalize rather than merely customize. The more interesting story here isn’t privacy, though privacy is real. It’s architectural: what happens when the expensive, impressive part of the system โ€” the part that knows everything โ€” becomes optional, and the cheap, personal part โ€” the part that knows you โ€” becomes the whole point.

What I don’t yet know is what this will cost me. A tool that reasons this well about my own life is also a tool I could lean on instead of doing the leaning myself, and there’s a version of this future where the walk around Sharon Park stops being mine and starts being a conversation with something that finishes my sentences a little too well. I’d want some way of knowing, plainly, what it’s drawing from and what it’s guessing at โ€” less a nutrition label than a kind of honesty I could check against, the way you’d check a fraud model’s confidence score before you trusted it with a yes.

But most mornings, I think I’d take the trade. Not because I want to think less. Because for thirty years I’ve been collecting the raw material โ€” the notebooks, the portfolios, the half-built essays โ€” and it would be something, finally, to walk beside a mind that had actually done the reading.

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 โ€” the way they moved, or failed to move, through a readerโ€™s mind โ€” simply wasnโ€™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 โ€” 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 canโ€™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 โ€” the rhythm and tone of the sentences. I began reading all my work out loud, listening for places that lagged and dragged, that didnโ€™t sparkle. I knew it was unlikely that anyone else was reading my stories out loud, but I was convinced that you do โ€œhearโ€ writing in your head as you read, and this pushes you (or stalls you) through the piece. I wanted the music โ€” that is, this subconscious tonal effect โ€” to match the subject.

I stopped. Read it again.

Because she was describing something real โ€” something I had been doing wrong for twenty-five years without knowing it was wrong. You donโ€™t know what you canโ€™t hear. Thatโ€™s the whole problem. The silence where the knowledge should be is itself silent.

I donโ€™t read my work out loud. Thereโ€™s something strange about it, something that breaks the spell โ€” 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. Orleanโ€™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 doesnโ€™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 โ€” a word, a rhythm, a single syllable landing wrong โ€” he stops and fixes it before moving forward. Never skips the trouble spot. Never tells himself heโ€™ll come back. His opening pages accumulate dozens of passes before he ever reaches the end. What heโ€™s really doing, underneath the technique, is training himself to feel the exact microsecond when a readerโ€™s attention would start to drift. To catch the loss before it happens.

Thatโ€™s not craft instruction. Thatโ€™s building a new sensitivity where there wasnโ€™t one before.

John McPhee works from the other direction entirely. His famous boxes โ€” index cards, sorted into piles, piles arranged into sequences, nothing drafted until the structure is known โ€” are about architecture before a single word is written. Heโ€™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 theyโ€™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 Iโ€™m still learning โ€” slowly, and late โ€” is that rhythm isnโ€™t decoration. It isnโ€™t the thing you tend to after the real work is done. Itโ€™s structural. A sentence moving at the wrong speed for what itโ€™s carrying fails the thought itself, not just the ear.

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

Iโ€™ve been experimenting with exactly that. An AI editor I call Clark. His job isnโ€™t correctness. Itโ€™s the sonic quality of prose โ€” the rhythm โ€” the same thing Orlean was describing, the same sensitivity Saunders spent years training. Clark finds whatโ€™s working as hard as what isnโ€™t. And when something fails, he explains what the readerโ€™s inner ear is hitting and why. Helpful.

I didnโ€™t know much about rhythm in writing when I was fifty. Didnโ€™t know it at sixty.

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

A lifetime of writing. Still learning how to listen.

Categories
AI Blogs/Weblogs Living Menlo Park

The Foothills

It was later in his illness. Someone had set up a folding table in the garage and Chris was sitting at it in a folding chair, working through a stack of photographs. Signing them, one by one, telling me the story inside each one as it came up โ€” where heโ€™d been, what was happening just outside the frame, what heโ€™d seen in the viewfinder that made him press the shutter at that exact moment and not a half second later. The garage was quiet. Outside, Menlo Park was doing whatever Menlo Park does on an ordinary afternoon. In here, a man was accounting for his life in pictures and I was standing there holding a camera, not quite sure what I was witnessing.

I made a photograph of him.

Itโ€™s at the top of his Wikipedia entry now. Thatโ€™s how the world knows his face โ€” a picture I made of him making sense of his pictures, in a folding chair, near the end. I donโ€™t know what to do with that except carry it.


Chris Gulker had been a photographer long before he was anything else. Staff photographer at the Los Angeles Herald-Examiner. Twice nominated for a Pulitzer. Published in Time, Newsweek, Rolling Stone. He had the eye first. Everything else โ€” the virtual newsrooms, the blogrolls, the hacked-together color systems that dragged newspapers into the digital age โ€” all of it came from the same instinct: look carefully, see whatโ€™s actually there, build toward what you see.

When I first met him he had just gotten a Leica M8. He talked about it the way he talked about everything he loved, which is to say with specificity and without apology.

He had driven an Audi TT. He had a Leica M8. He was not a man who made concessions to the ordinary.

He had glioblastoma. Diagnosed in 2006. Surgery, radiation, the whole negotiation with a disease that doesnโ€™t actually negotiate. He knew the terms and he kept going โ€” kept shooting, kept writing at gulker.com, kept thinking out loud about what was coming next, as if the tumor were an inconvenience and the future were the point.

He walked when he could walk. He talked when he could talk.

He died in October 2010. He was fifty-nine.


Twice a week in those last two years Iโ€™d put Lily in the car and drive over to his house. Lily was small and opinionated and she understood the trip as hers. Weโ€™d pick Chris up after breakfast, when the morning was still cool, and do the loop โ€” one mile, flat, because flat was what worked. Then weโ€™d come back to find Linda moving through the house, Chrisโ€™s wife of nearly thirty years, the still point of everything that was happening to them. Sometimes sheโ€™d join us and the conversation would open into something more alive, the kind of talk where someone says something offhand and suddenly everyone is leaning forward.

One of those mornings the three of us decided to start a local blog for Menlo Park. Linda would write and edit. Chris would shoot. We called it InMenlo.com.

When Linda wrote Chrisโ€™s obituary, thatโ€™s where she published it.

People talk about spending time with the dying as a kind of grace extended downward. It wasnโ€™t like that. Those mornings were a gift โ€” the ideas, the talk, the way Chris described what was coming as if he could already see it clearly from wherever he was standing. I left those visits more alive than I arrived. Thatโ€™s the debt I carry. Not grief exactly, though thereโ€™s grief. More like an obligation to keep paying attention to the future he spent his life building toward.


Last month a man named Demis Hassabis closed a two-hour technology showcase in Mountain View โ€” twenty minutes from where Chris and I used to walk โ€” and said seven words I havenโ€™t been able to put down since: We are at the foothills of the singularity. The audience applauded. Then everyone went home.

I keep thinking Chris would have had something to say about that.

Not the singularity part, necessarily โ€” that word carries a slightly rapturous charge, too certain of its own prophecy. But the foothills part. The careful humility of it. The acknowledgment that what we can see from here โ€” AI systems autonomously building operating systems, models that predicted a hurricaneโ€™s landfall and saved lives โ€” all of it is still just approach terrain. The mountain is what comes after.

Chris spent his whole career in the foothills of things. Slightly ahead of the moment, always building infrastructure for a future that hadnโ€™t arrived yet, always explaining to people who werenโ€™t sure they wanted to know. He pioneered the blogroll. Built one of the first online newspapers. Hacked color into the San Francisco Examiner with Macintoshes and ingenuity when the system said it couldnโ€™t be done. He was the wrong man for the present tense. He belonged to the next sentence.

He had the photographerโ€™s instinct underneath all of it โ€” the knowledge that you have to look carefully, that the light is always changing, that if you wait too long the moment is gone. He put the Leica to his eye and he saw. He put his hands on a keyboard and he built what he saw toward.


Lily is gone now too. She outlasted Chris, which felt right โ€” she was stubborn and she loved the route.

I still think about those mornings. The cool air, the flat mile, Lily pulling us both forward. The way the real conversation started when we got back. The way Linda might appear and the whole thing would open into something none of us had planned. The way Chris talked about what was coming โ€” not as speculation but as something he could already see, the way a photographer sees the shot before he raises the camera.

He always knew something was coming. He had a gift for the future tense Iโ€™ve never quite encountered in anyone else โ€” and a photographerโ€™s understanding that the future, like light, doesnโ€™t wait.

I wonder what heโ€™d make of the foothills. I think heโ€™d already have the Leica out. And I know weโ€™d still be talking about it.

Categories
Books Curiosity Living

Working the Seams

This book highlight popped up in my morning Readwise feed recently:

โ€œFishermen work seamsโ€”seams between slow water and fast, between deep water and shallow, between sunlight and shadow. The eddies around rocks, the bubble lines along banks. Thatโ€™s where the fish are.โ€

Neil King wrote it in American Ramble, his account of walking from Washington to New York. He was watching fishermen, not fishing himself, which maybe explains why it reads less like instruction and more like revelation. When youโ€™re the observer, you have room to notice what the practitioner is too busy doing to say.

The word seams is doing something I canโ€™t stop thinking about. A seam is a joining. Itโ€™s the place where two different things meet and, in meeting, create a third thing: the edge itself. Not slow water, not fast water, but the turbulent conversation between them. The fish arenโ€™t in the slow water. They arenโ€™t in the fast water. Theyโ€™re in the argument.


I think most of the interesting things in life happen at seams.

The best conversations arenโ€™t the ones where everyone agrees. Theyโ€™re the ones where two people with genuinely different orientations are standing at the same edge, looking at the same water. The friction between the views creates something neither would reach alone.

The best writing isnโ€™t the settled opinion, the fully-arrived-at conclusion. Itโ€™s the essay in the old sense โ€” the attempt โ€” where you can feel the writer at the seam of what they know and what theyโ€™re reaching toward. The bubble line between understanding and confusion. Thatโ€™s where the reader is, too, if theyโ€™re lucky.

I notice this on my own blog sometimes. The posts that feel most alive to me arenโ€™t the ones where I knew what I wanted to say before I started. Theyโ€™re the ones where I began at a seam โ€” between something Iโ€™d always believed and something that recently unsettled it โ€” and wrote my way along the edge, not knowing which bank Iโ€™d end up on.


Thereโ€™s a version of this that applies to attention itself.

I dwell on how I pay attention โ€” when Iโ€™m reading, when Iโ€™m walking, when Iโ€™m in conversation. And Iโ€™ve noticed that my attention goes flat in the middle of things. Flat terrain. Constant depth. Unchanging light. I have to work to stay present when nothing is in transition.

But put me at a seam โ€” a moment where the mood in a room is shifting, where a piece of music is about to resolve or refuse to resolve, where someone is on the verge of saying something theyโ€™ve been circling for an hour โ€” and Iโ€™m completely there. Attention is predatory, maybe. It goes where the tension is.

Which is what the fish are doing, of course. The seam isnโ€™t just a metaphor for where interesting things happen. Itโ€™s why interesting things happen there. The fast water sweeps food along; the slow water lets you hold your position; the seam between them is where you can eat without being eaten. The fish are solving a real problem. Theyโ€™re just also, accidentally, living beautifully.


I wonder sometimes if this is what makes a good editor, or a good friend who reads your drafts. They find the seams โ€” the places where youโ€™ve unconsciously papered over a tension, smoothed the fast water into the slow, given the reader no place to be a fish. โ€œSomethingโ€™s off here,โ€ they say, and what they mean is: you resolved this too quickly. Stay in the argument longer.

The eddies around rocks, the bubble lines along banks.

I want to be a better noticer of those. Not to resolve them. Just to work them.

Categories
AI Blogs/Weblogs

How to Refresh Dated Blog Articles

This afternoon I used the following prompt to help me assess posts I’d written a few years ago for updating:

I have a personal blog at https://sjl.us
Please review my blog posts that are between two and five years old and give me a prioritized list of which ones you think I should update.

I was curious how well it would do at this task. Turns out I was pleasantly surprised. Here’s the result:

Hereโ€™s my prioritized list of your blog posts (published roughly April 2021โ€“April 2024, i.e., 2โ€“5 years old as of April 2026) that I recommend updating, ranked from highest to lowest priority.

I reviewed the site structure, monthly archives, and indexed posts via searches. Your blog has dozens of posts in this window (mostly personal essays, photography, history, productivity/PKM, and heavy AI experimentation from the 2022โ€“early 2023 wave). I prioritized based on:

  • How much the topic has aged (AI/prompting/tech tools change fastest; photography, personal reflections, and history are more timeless).
  • Potential value of an update (adding 2026-era insights, new examples, current tool versions, or follow-up reflections makes the post fresher and more useful to readers).
  • Thematic clustering (your AI/PKM series from 2022โ€“2023 forms a natural arc that would benefit from a cohesive refresh).

I focused on the highest-impact ones rather than every post. Many others (e.g., pure street photography, freeway essays, family stories like the Tracy obituary, or 2021 COVID-era reflections) are still strong as-is and donโ€™t need updates unless you want to add new photos or minor notes.

Top Priority (Strongly recommend updating soon โ€” these are the most dated but highest-potential)

  1. Multi-step prompting for Claude (August 11, 2023)
    https://sjl.us/2023/08/11/multi-step-prompting-for-claude/
    Why update? Early Claude-specific prompting techniques; the entire field (Claude 3/4 families, GPT-4o-class models, Grok, etc.) has advanced dramatically. Easy win: expand with 2026 best practices, new multi-step examples, and comparisons.
  2. My Current PKM Stack as of September 2023 (September 20, 2023)
    https://sjl.us/2023/09/20/my-current-pkm-stack/
    Why update? Details your Obsidian/Instapaper/Feedly/Drafts workflow at the time. Tools and plugins have evolved a lot; readers love current โ€œstate of my stackโ€ posts. A 2026 version would be highly engaging.
  3. Using AI to Help Write (November 15, 2022)
    https://sjl.us/2022/11/15/using-ai-to-help-write/
    Why update? Pure GPT-3-era experimentation. Perfect opportunity to contrast 2022 capabilities with todayโ€™s multimodal models and show how your own AI-assisted writing process has matured.
  4. LLMs = Dream Machines (December 11, 2023)
    https://sjl.us/2023/12/11/llms-dream-machines/
    Why update? References to early hallucination discussions and Andrej Karpathyโ€™s tweet feel historic now. Update with current โ€œdream machineโ€ examples and how you use LLMs in 2026.
  5. Crafting Effective Prompts for Your AI Assistant (Claude, ChatGPT, Bard, etc.) (September 9, 2023)
    https://sjl.us/2023/09/09/crafting-effective-prompts-for-your-ai-assistant-claude-chatgpt-bard-etc/
    Why update? Another core prompting/PKM-adjacent piece from the explosion period. Pair it with the multi-step post for a nice โ€œ2023 vs 2026 Prompting Guideโ€ refresh.

High Priority (Worth updating โ€” clear value-add)

  1. An AI Thanksgiving (November 22, 2022)
    https://sjl.us/2022/11/22/an-ai-thanksgiving/
    Why update? Fun GPT-3 + DALLยทE experiment. Readers would love a 2026 โ€œthen and nowโ€ version with newer models/image generators.
  2. Hacking Creativity with AI (August 22, 2023)
    https://sjl.us/2023/08/22/hacking-creativity-with-ai/
    Why update? Early chatbot creativity techniques; the creative workflow space has exploded since then.
  3. On the Minimum Viable Environment (MVE) and Appleโ€™s Vision Pro (July 1, 2023)
    https://sjl.us/2023/07/01/on-the-minimum-viable-environment-mve-and-apples-vision-pro/
    Why update? Pre-launch speculation. Vision Pro shipped in 2024 โ€” you can now add real-world usage, ecosystem updates, and whether MVE thinking held up.
  4. Drafts โ€“ a tool for idea capture (April 16, 2022)
    https://sjl.us/2022/04/16/drafts-a-tool-for-idea-capture/
    Why update? The app was celebrating its 10th anniversary then; itโ€™s now 14+ years old with major feature/UI changes. Your long-term usage makes this a great โ€œthen vs nowโ€ post.

Medium Priority (Nice-to-have updates if you have time)

  1. Reading Books in 2022 (May 11, 2022)
    https://sjl.us/2022/05/11/how-im-reading-books/
    Why consider? Kindle/app habits and highlighting workflows have evolved; easy to refresh with current tools and your 2026 reading volume.

Other notable 2023 AI-adjacent posts (e.g., NotebookLM deep-dive from Dec 2023, Explorations of PKM from Oct 2023) would slot in here if you want to do a broader โ€œAI/PKM 2023 Retrospectiveโ€ series.

Lower Priority / Probably Leave As-Is

  • Photography series (e.g., โ€œCapturing the Art in Everyday Scenes,โ€ Paris posts, โ€œRedwood Circle,โ€ etc.) โ†’ Timeless and visual; they hold up well.
  • History/personal essays (e.g., โ€œOde to a Queen,โ€ โ€œThe Worldโ€™s Most Beautiful Freeway,โ€ โ€œRemembering Blue Chip Stamps,โ€ โ€œOld Man Walking,โ€ 2021 book recs, โ€œStuck in Neutralโ€) โ†’ Evergreen or emotionally resonant; updating could dilute their original voice unless you have new material.
  • Holiday/personal posts (e.g., Thanksgiving 2023, Merry Christmas 2021) โ†’ Fine as snapshots in time.

Quick recommendation on approach: Start with the top 5 (they form a nice cluster around AI prompting/PKM). Updating them together would create a strong โ€œ2023 AI Reflections โ€“ Revisited in 2026โ€ section or category on the blog. Many of these posts already reference each other, so cross-linking updated versions would be powerful.

If youโ€™d like me to pull full content from any specific post, draft sample update language, suggest new sections, or help with images/AI-assisted rewrites, just let me know! Your blog has a great reflective voice โ€” these updates would keep it feeling current without losing that personal touch.

Categories
Interstate 280 San Francisco/California San Jose

The Scenic Route Home

“In a world optimized for speed and engagement, 280 is a reminder that infrastructure can be art.”

It is a strange paradox that in the heart of Silicon Valleyโ€”a place defined by the ephemeral, the digital, and the instantaneousโ€”a cherished shared experience is a physical ribbon of highway that hasnโ€™t changed much in fifty years.

My post from last April, โ€œThe World’s Most Beautiful Freeway,โ€ has recently found a new wave of readers. Iโ€™ve been asking myself: Why? Why does a blog post about Interstate 280, written by a retiree exploring local history, resonate so deeply right now?

Perhaps itโ€™s because I-280 is more than just a commute. As I noted in the original piece, the ‘world’s most beautiful freeway’ tag has clung to 280 since the 1960s – a California Highways and Public Works article already quoted residents hoping the Junipero Serra Freeway would earn the title. It was a bold claim for a freeway, yet it stuck. While its sibling, US 101, is a clogged artery of billboard-choked utility, 280 feels like a deep breath. It is the “scenic route” we are lucky enough to take right in our own backyard.

There is a powerful nostalgia in that drive. We all remember the sign that used to sit in the median near Cupertinoโ€”the one that literally proclaimed it “The World’s Most Beautiful Freeway”โ€”before it vanished. We remember the way the fog rolls over the Santa Cruz Mountains, spilling into the crystal bowl of the reservoir.

But I think the recent interest goes deeper than pretty scenery. We are living in an era of rapid, often disorienting change. I used ChatGPT to help research the history of that road, a small testament to how AI is weaving into our daily inquiries. Yet, the road itself remains a constant. It was designed by engineers of the California Division of Highways, who chose the harder, more expensive route through the foothills rather than paving over El Camino Real. They chose beauty over pure efficiency.

That choice resonates today. In a world optimized for speed and engagement, 280 is a reminder that infrastructure can be art. It connects the headquarters of the companies building our future (Apple, Google, Meta) with the wild, golden hills of Californiaโ€™s past. It is a physical timeline of the Peninsula.

Maybe we are revisiting this post because we are craving that balance. We want to know that even as we rush toward the future at freeway speeds, we can still look out the window and see something timeless, something beautiful, something that reminds us where we are.

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?