Tag: writing

Categories
AI Claude

Please Teach Me About AI

After reading Howard Marks’ latest essay about AI I wanted to try something similar to what he did so I asked Claude the following:

I’d like to experience what Howard marks did when he asked Claude to teach him about ai. Please reference by personal blog to learn about me and my interests: https://sjl.us


A man (me) wanted to understand an AI. So he asked the AI to explain itself to him. The AI, knowing who it was talking to, shaped its entire explanation around that specific person’s worldview. And it worked so well that the person felt like he’d received a letter from a thoughtful friend.

Claude came back and did what I asked. Pretty amazing stuff!

Scott — I’ve read your blog carefully. Not just the recent posts, but the pattern of what you reach for, what you return to, what lights you up. Now let me try to do what you wrote about: shape this explanation around you.

Continue reading “Please Teach Me About AI”
Categories
AI

The Student, The Teacher, and the Delightful Absurdity of It All

Howard Marks is one of the sharpest financial minds alive. The man has been thinking clearly about markets for fifty years, has written memos that get passed around Wall Street like sacred texts, and has outlasted more market cycles than most of us have had hot dinners. So when Howard Marks decides he needs to get educated about artificial intelligence to write a follow-up to his December memo, he does what any serious intellectual would do: he asks Claude.

And then Claude — the AI — teaches him about Claude.

I’ve been sitting with this for a few days and I’m still not entirely sure whether it’s profound or just very, very funny. Maybe both. Probably both.

Continue reading “The Student, The Teacher, and the Delightful Absurdity of It All”
Categories
Blogs/Weblogs Writing

Notes for a Distant Shore

I spend an embarrassing amount of time trying to control how people hear me. Most of us do. We want to be understood, neatly categorized, and told we make sense. But sitting down to actually write and sharing publicly requires dropping all of that. You just have to surrender.

Richard Rhodes nailed the feeling:

“To write is always to seal notes into bottles and cast them adrift at sea; you never know where your notes will drift and who will read them.”

You’re basically bottling up whatever is rattling around in your head on a Tuesday afternoon, tossing it into the digital ocean, and walking away. It’s vulnerable. Honestly, it’s a little reckless.

Once the bottle leaves your hand, you lose your voice. You can’t tap the reader on the shoulder to explain what a sentence really meant. The person who finds it brings their own weather to the shore. They might read a lifeline into a paragraph you barely thought about, or miss your main point entirely because they were distracted by the tide.

Forget about engagement metrics. The connections that actually matter rarely show up on a dashboard anyway. You write something, and it drifts. Maybe for years. Then someone stumbles over it exactly when they need it. You aren’t writing for a demographic; you’re writing for some random person walking the beach. True serendipity.

In the end, you just have to trust the water. Even if the bottle sinks, the act of throwing it is usually satisfying enough.

“Write as if you were dying. At the same time, assume you write for an audience consisting solely of terminal patients. That is, after all, the case. What would you begin writing if you knew you would die soon? What could you say to a dying person that would not enrage by its triviality?” (Annie Dillard, The Writing Life)

Categories
Biology Creativity Living

The Compost of the Soul

There is a pervasive pressure in modern life to curate our experiences like a museum curator arranges an exhibition. We want to catalog our memories, label our skills, and display only the pristine, unbroken artifacts of our history. We treat our minds like archives—dusty, organized, and static.

But Ann Patchett offers a different, earthier metaphor, one that feels infinitely more true to the messy reality of being human:

“I am a compost heap, and everything I interact with, every experience I’ve had, gets shoveled onto the heap where it eventually mulches down, is digested and excreted by worms, and rots. It’s from that rich, dark humus, the combination of what you encountered, what you know and what you’ve forgotten, that ideas start to grow.”

This imagery of the compost heap is liberating because it removes the burden of purity. In a compost heap, you don’t separate the eggshells from the coffee grounds or the dead leaves from the fruit rinds. It all goes in. The triumphs, the heartbreaks, the books we read halfway, the conversations we barely remember, and the failures we wish we could forget—they are all just organic matter.

The magic, as Patchett notes, is in the digestion. We are not static repositories of information; we are active, biological processors. Time acts as the earthworms, breaking down the sharp edges of raw experience until it loses its original form.

We often fear forgetting. We worry that if we don’t hold onto a memory with a white-knuckled grip, it loses its value. But in the logic of the compost heap, “what you’ve forgotten” is just as vital as what you remember. The forgotten things are simply the matter that has broken down completely, becoming the nutrient-dense soil that supports new growth.

If we view ourselves as compost heaps, we stop fearing the “rot.” We understand that the difficult periods of decomposition are necessary to create the humus required for the next season of growth. We are not built to be archives; we are built to be gardens.

Categories
Living Writing

The Loop and the Pixel

There is a distinct muscle memory associated with the 1950s classroom. It smells of chalk dust and floor wax, but mostly, it feels like the cramping of a small hand wrapped around a pencil. We didn’t just learn to write; we were initiated into the discipline of the loop. The Palmer Method or Zaner-Bloser weren’t suggestions—they were rigorous architectures of communication. We made endless rows of O’s and l’s, tilting the paper just so, learning that language required flow, connectivity, and a certain deliberate grace.

Then, the world sped up.

By the 1990s, the loops began to unravel. As keyboards clattered their way into dominance, the efficiency of the printed letter—and eventually the typed pixel—took precedence over the artistry of the connected script. By 2010, the erasure was formalized; cursive was dropped from federal education standards (Common Core) to make room for “electronic literacy.” We traded the unique signature for the standardized font. We gained speed, certainly, but I often wonder what we lost in the translation.

“New Jersey this week joined a list of more than 20 states slanting in favor of bringing cursive instruction back to classrooms. Lessons on the looping letters were dropped from federal education standards in 2010, part of a shift toward focusing on electronic literacy.” — The New York Times

It seems the pendulum is swinging back. Proponents argue for its utility—the ability to read historical texts or a grandmother’s birthday card—but I believe the resurgence touches on something deeper.

In an increasingly digital world, cursive is an act of resistance. Typing is percussion; it is staccato and disconnected. Cursive is string; it is continuous and fluid. When we write in cursive, we are physically connecting thoughts, linking one letter to the next without lifting the pen. It forces the brain to slow down and the hand to dance.

As we stare into screens that demand our instant reaction, perhaps we are realizing that we crave the friction of pen on paper. We are bringing the loops back not because they are faster, but because they are human.

Categories
AI AI: Prompting Writing

AI as a Mirror, Not a Maker

I’ve been thinking a lot lately about how we move past the novelty phase of AI—beyond just asking a chatbot to “write a poem about a turkey” or summarize a meeting—and into actual thinking with these tools.

As a lifelong learner, I’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 Google’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?”

It’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. It’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 he’s writing about “Spaced Repetition,” he doesn’t just explain the theory. He asks Claude’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 personas—a skeptical VC, a confused novice, an expert in a tangential field—and asks them to critique his draft from their specific viewpoints.

It’s effectively a focus group of one.

How to Get Started

If you’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 Kane’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.”

I’ve found that using the tools this way—as a partner for thinking rather than just generating—is where the real magic happens.

Which one will you try first?

Categories
AI

Research Prompts

I recently came across a prompt in a post on X which has proven to be quite useful in brainstorming.

Here’s the prompt, tailored in this example to research the area of AI super intelligence:

You are a professional ghostwriter. Generate 15 high-signal content ideas on how AI labs will reach artificial super intelligence.

For each idea:
- Give me a hook line (<= 15 words, curiosity-driven)
- Outline the structure in 3 parts (hook, point, action)
- Include an example or analogy that will resonate with an audience of college graduates. 

Make them practical, non-generic, and designed to spark discussion.

To see how it works, just copy it and put it into your favorite large language model. I think you’ll be surprised and pleased with what results you obtain.

After the first pass, you can try this next:

Pick the best one and draft it.

You’ll get back a draft article about the model’s choice for the best among the 15 it first produced.

You can then steer the model using a prompt like this:

Tune the draft for the vc/tech founder voice. Also speculate that Google is most likely the winner.

It’s fun to see how the article evolves further with that voice and more speculation about the possible winner.

You can then ask the model to redraft it further:

Sketch two spicy counterarguments to the main thesis.

And so on. It’s fun to do a deep dive on a topic using this approach. The wide range of the first fifteen results narrows and deepens as you ask the model to refine the draft it has produced.

I’ve lost track of time exploring a topic of interest to me as I got back and forth with the model evolving my understanding. Some models will even assist you in that process by suggesting next steps along the way.

Let me know of your experiences using this kind of approach!

Categories
Writing

Too Late

“Doesn’t it always happen that as soon as you’ve sent it, suddenly you notice something you want to change? You read your own work differently once you’ve shared it because you are—in that moment after you’ve hit the send button, or stuffed that envelope into the mail slot—rereading your work as the person to whom you’ve just sent it. The circle around your work suddenly grows wider. But now that you have a little more room in which to read it clearly, you’ve sent it out. It’s too late.” (Dani Shapiro, Still Writing)

Indeed.

Categories
Writing

Writing vs Speaking

“People often assume they know how to write because they know how to speak. There are deep and important connections between spoken and written language, but they’re not the same thing.” (Richard Rhodes, How to Write)

It’s always a clarifying experience for me to write. Fascinating how that works.

Speaking and writing operate in fundamentally different contexts, serve different purposes, and engage different cognitive processes. When we speak, we have immediate feedback from our audience. We can see confusion in someone’s eyes and clarify what we’re saying on the spot. We can use tone of voice, facial expressions, and gestures to add layers of meaning. We can pause, backtrack, and reformulate our thoughts in real-time.

Writing, by contrast, is a solitary act of communication across time and space. The writer must anticipate the reader’s needs, questions, and potential misunderstandings without any immediate feedback. Every word must carry its full weight because there’s no opportunity for clarification through tone or gesture.

Consider how we organize information differently in speech versus writing. In conversation, we might circle back to a point several times, approaching it from different angles as we gauge our listener’s understanding. In writing, this same approach would likely confuse readers who expect a more linear, structured presentation of ideas.

Speaking is largely automatic—we think and talk simultaneously, often discovering what we want to say in the process of saying it. Writing, however, requires us to think, plan, draft, revise, and refine. It’s a recursive process that demands we hold multiple considerations in mind: our overall purpose, our specific audience, the clarity of our current sentence, the flow from the previous paragraph, and the setup for what’s coming next.

There is one mode of writing that is very similar to speaking: free writing. In this mode, we discard the more formal steps of formal writing and just get words out of our brain on to the paper or into the computer.

A modification of free writing is brainstorming by speaking into an audio recording, perhaps while we’re on our morning walk. Another might be to use mind mapping tools to help us quickly capture and layout related ideas.

We can extend what we captured in a free writing exercise by sharing it with an LLM and asking for reactions, additional ideas, etc. Made possible by the introduction of chatbots a couple of years ago, these tools can be very helpful – just like interacting with a good friend or work colleague can help us refine our thoughts. Then we can be in a more developed position to more formally write.

Categories
Creativity Writing

Longhand

“If you’ve never tried it, see what happens if you write a draft of something longhand. Before long, you’ll be forced to x out whole sentences. You’ll draw circles and asterisks and arrows. You’ll change your mind about what you’ve crossed out, and write “stet” in the margin. It will look messy, because it is messy. It should be that: a beautiful, complicated mess. Who knows? Maybe only one sentence will remain. Maybe the whole order will be upended. You’ll be able to see a road map of your progress as you build the architecture of your story.” (Dani Shapiro, Still Writing)