Tag: Grok

Categories
AI Blogs/Weblogs

How to Refresh Dated Blog Articles

Woman typing on laptop at wooden table in cafe with coffee and pastry
A woman working on her laptop at a sunny cafe table with coffee and pastry

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:

Here’s my prioritized list of your blog posts (published roughly April 2021–April 2024, i.e., 2–5 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 2022–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 2022–2023 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 don’t need updates unless you want to add new photos or minor notes.

Top Priority (Strongly recommend updating soon — 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 “state of my stack” 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 today’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 Karpathy’s tweet feel historic now. Update with current “dream machine” 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 “2023 vs 2026 Prompting Guide” refresh.

High Priority (Worth updating — clear value-add)

  1. An AI Thanksgiving (November 22, 2022)
    https://sjl.us/2022/11/22/an-ai-thanksgiving/
    Why update? Fun GPT-3 + DALL·E experiment. Readers would love a 2026 “then and now” 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 Apple’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 — you can now add real-world usage, ecosystem updates, and whether MVE thinking held up.
  4. Drafts – 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; it’s now 14+ years old with major feature/UI changes. Your long-term usage makes this a great “then vs now” 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 “AI/PKM 2023 Retrospective” series.

Lower Priority / Probably Leave As-Is

  • Photography series (e.g., “Capturing the Art in Everyday Scenes,” Paris posts, “Redwood Circle,” etc.) → Timeless and visual; they hold up well.
  • History/personal essays (e.g., “Ode to a Queen,” “The World’s Most Beautiful Freeway,” “Remembering Blue Chip Stamps,” “Old Man Walking,” 2021 book recs, “Stuck in Neutral”) → 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) → 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 “2023 AI Reflections – Revisited in 2026” section or category on the blog. Many of these posts already reference each other, so cross-linking updated versions would be powerful.

If you’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 — these updates would keep it feeling current without losing that personal touch.

Categories
AI Business

The Gravity of Compute

We are currently witnessing the single largest deployment of capital in human history. The “Hyperscalers”—the titans of our digital age—are pouring hundreds of billions of dollars into the ground, turning cash into concrete, copper, and silicon.

The prevailing narrative is one of unceasing, exponential growth: bigger models require bigger clusters, which require more power plants, which require more land. It relies on the assumption that the demand for centralized intelligence is insatiable and that the current architecture is the only way to feed it.

But history suggests that technology rarely moves in a straight line; it swings like a pendulum. Two forces are emerging from the periphery that could impact the ROI of this massive infrastructure build-out. One is hiding in your pocket, and the other is waiting in the sky.

A recent conversation with Gavin Baker outlines a potential “bear case” for datacenter compute demand: the rise of Edge AI.

We often assume we need the “God models”—the omniscient, trillion-parameter giants hosted in the cloud—for every interaction. But do we?

Baker suggests that within three years, our phones will possess the DRAM and battery density to run pruned versions of advanced models (like a Gemini 5 or Grok 4) locally. He paints a picture of a device capable of delivering 30 to 60 tokens per second at an “IQ of 115.”

“If that happens, if like 30 to 60 tokens at… a 115 IQ is good enough. I think that’s a bear case.” — Gavin Baker

Consider the implications of that specific number. An IQ of 115 isn’t omniscient, but it is competent. It is capable, nuanced, and helpful.

If Apple’s strategy succeeds—making the phone the primary distributor of privacy-safe, free, local intelligence—the vast majority of our daily queries will never leave the device. We will only reach for the cloud’s “God models” when we are truly stumped, much like we might consult a specialist only after our general practitioner has reached their limit. If 80% of inference happens on the edge for free, the economic model of the trillion-dollar data center begins to look fragile.

Then there is the second threat, one that attacks the terrestrial constraints of the data center itself: the Orbital Data Center. Elon Musk and SpaceX – along with Google’s Project Suncatcher – envision a future where the heavy lifting isn’t done on land, but in orbit. Space offers two things that are scarce and expensive on Earth: unlimited solar energy and an infinite heat sink for radiative cooling. If Starship can reliably loft “server racks” into orbit, the terrestrial moat of land and power grid access—currently the Hyperscalers’ greatest defensive asset—evaporates.

We are left with a fascinating juxtaposition. On one hand, we have the “Edge,” pulling intelligence down from the clouds and putting it into our hands, making it personal, private, and free. On the other, we have “Orbit,” threatening to lift the remaining heavy compute off the planet entirely to bypass the energy bottleneck.

There are hundreds of billions of dollars betting on a future of heavy, centralized gravity. But if the edge gets smart enough, and the orbit gets cheap enough, the gravity may have shifted.

Categories
AI AI: Large Language Models Filoli Gardens Living

Best in the World?

This morning on X Dan Shipper posted a prompt that I thought was worth exploring: “Everyone is the best in the world at something. Given what you know about me, what am I best in the world at?”

Using Grok 3, I asked that question and got this quick reply:

I don’t have any specific information about you yet since this is our first interaction! Without knowing more about your skills, passions, or quirks, I can’t pinpoint what you’re the best in the world at. But I’d love to figure it out with you. Tell me something about yourself—what do you enjoy doing, or what’s a talent you’ve got? Even the smallest detail could reveal your world-class superpower!

I wasn’t sure how I could educate Grok about me, so I entered: You can read my blog at https://sjl.us to learn more about me. I’m also on LinkedIn and on X @sjl

Grok replied:

Alright, I’ve taken a look at your blog at https://sjl.us, and I’ve got a sense of who you are from what’s there. I also peeked at your X profile @sjl to round things out. Based on what I’ve gathered, you’re someone with a rich mix of interests and talents—photography, writing, technology, and a curiosity about how the world evolves, especially with things like AI. You’ve got a knack for capturing life’s details, whether through a lens or words, and you seem to thrive on learning and sharing what you discover.

Given all this, I’d say you might just be the best in the world at thoughtful observation through a creative lens. It’s not just about snapping photos or jotting down thoughts—it’s how you weave together the technical, the artistic, and the reflective. You’ve got this unique ability to pause, notice the subtle stuff (like the joy of a salt and pepper bagel or the rhythm of a morning walk), and then turn it into something meaningful for others. Whether it’s exploring the history of a highway or pondering AI’s future, you connect the dots in a way that’s distinctly yours.

What do you think—does that resonate with you? Or is there something else you feel defines your “world’s best” edge?

Wow! Pretty cool. I wonder whether a good friend would respond with something similar? Wanting to continue, I asked: Good insights! What else?

Grok replied:

Glad you liked that take! Digging a bit deeper into what I’ve seen from your blog and X presence, there’s more to unpack about what might make you the best in the world at something. Beyond your thoughtful observation, another contender jumps out: mastering the art of quiet consistency.

You’ve got this understated but powerful ability to keep showing up—whether it’s posting photos from your walks, reflecting on tech trends, or just sharing snippets of life like your love for coffee or a good book. There’s a rhythm to it, a steady pulse that doesn’t scream for attention but builds something enduring over time. Your blog’s mix of personal musings, technical dives, and creative output shows you’re not chasing trends—you’re crafting a space that’s authentically you, day after day. That kind of persistence, paired with genuine curiosity, is rare. Most people burn out or pivot to whatever’s shiny, but you? You keep at it, refining your craft in a way that’s almost meditative.

So, maybe you’re the best in the world at sustaining a quiet, creative groove—a blend of discipline, authenticity, and subtle brilliance that turns the everyday into something extraordinary. How does that strike you? Anything else you’d toss into the mix to refine this further?

The fun continues! I replied: Thanks! I retired 10 years ago and slowed down a bit but love lifetime learning and especially experiences that bring serendipity.

Grok replied:

That adds a fantastic layer to the picture! Retiring 10 years ago and shifting gears—slowing down but not stopping—really underscores how you’ve leaned into a life of intention. Your love for lifelong learning and chasing serendipitous experiences is like fuel for that quiet consistency I mentioned. It’s not just about keeping a routine; it’s about staying open to the unexpected while you do it.

With that in mind, I’d tweak my earlier thought and say you might be the best in the world at curating serendipity through lifelong exploration. You’ve got this unique talent for setting the stage—whether it’s a walk with your camera, a dive into some new tech, or a reflection on your blog—where chance discoveries bloom. Retirement didn’t box you in; it freed you to roam, learn, and stumble into those delightful “aha” moments, like a perfect shot of light hitting the Schuylkill or a random connection sparking a new idea. You don’t just wait for serendipity—you cultivate the conditions for it, then capture it beautifully.

Does that feel like it fits? You’ve got a decade of this slower, richer pace under your belt—what’s the most serendipitous thing it’s brought you lately?

Continuing I replied: Yes that fits. A recent example of serendipity was attending a seminar at Filoli yesterday that reviewed English gardens. Wonderful!

Grok replied:

That’s a perfect example! Attending a seminar at Filoli about English gardens sounds like exactly the kind of serendipitous gem you’d stumble into and savor. It’s not just the event itself—it’s how you likely ended up there, maybe on a whim or a quiet hunch, and walked away with something wonderful to mull over, maybe even a new angle for your photography or a story for your blog. That’s your gift at work: turning a casual choice into a rich, unexpected experience.

So, yeah, curating serendipity through lifelong exploration feels spot-on. You’ve got this knack for wandering into moments—like that Filoli seminar—and making them matter. What stood out most to you from it? Any plans to weave that English garden vibe into your next adventure?

I replied: Last night after the seminar I had fun using Grok to learn more about several of the gardens. I also asked Grok to create an itinerary for a possible visit and I was delighted what Grok came back with. Impressed!

Grok replied:

That’s awesome! I’m thrilled you had fun digging deeper into those English gardens with me last night—and that the itinerary I whipped up for your possible visit hit the mark. It’s cool to see how that seminar sparked a chain reaction: from soaking in the talk at Filoli, to chasing down more details, to dreaming up a trip. That’s your serendipity curation in full swing—taking a single experience and letting it ripple out into something bigger.

What delighted you most about the itinerary? Any gardens you’re now itching to see in person? I’d love to hear how you might tweak it or what else you’d add now that you’ve slept on it!

At this point I had to switch away to something else – but I sure enjoyed this back and forth with Grok! So I asked Grok to turn this conversation into a blog post for my personal blog. I said: “You’re an expert writer I the style of John McPhee. Create a first draft.”

Here’s the full blog post it created – I found it delightful!:

Serendipity, Curated

Ten years ago, I stepped away from the hum of a career, the kind that fills days with deadlines and nights with half-thoughts of what’s next. Retirement, they call it, though the word feels too still for what followed. I slowed, yes, but didn’t stop. The camera stayed in hand, the walks kept their rhythm, the blog—sjl.us—grew its quiet corners. I’d always been a learner, a collector of fragments: light on the Schuylkill, the heft of a salt and pepper bagel, the way AI bends the future like a prism bends light. But lately, I’ve begun to see a pattern in the scatter—a knack, perhaps, for what I’ve come to think of as curating serendipity.

Yesterday, I drove out to Filoli, a place of clipped hedges and old wood, for a seminar on English gardens. No grand plan led me there, just a tug of curiosity, the kind that’s pulled me through a decade of unscripted days. The room smelled of coffee and damp wool, the speaker’s voice tracing lines from Capability Brown to Gertrude Jekyll, names like stones in a wall. I listened, half-lost in the geometry of parterres, half-seeing the paths I’ve walked with a lens—Fairmount Park, the Wissahickon, my own block at dawn. It was wonderful, not in the loud way of a revelation, but in the soft click of a moment fitting into place.

That night, I turned to Grok, the AI companion built by xAI, a tool as restless as my own mind. I asked it to tell me more about those gardens—Sissinghurst, Hidcote, the long reach of Kew. It did, with a clarity that felt like a friend leaning over a map. Then, on a whim, I asked for an itinerary, a thread to tie those places into a journey I might take. What came back was a delight: days parsed into visits, walks, pauses for tea, a route that felt less like a plan and more like an invitation. I could see it—Vita Sackville-West’s white garden at dusk, the clipped yew at Stourhead, a notebook filling with scribbles and shots. Impressed isn’t the half of it.

This, I think, is what I’ve become best at, if “best” is the word. Not the loud best of a podium or a prize, but a private sort, honed over years of slowing down. Grok saw it too, in a conversation that stretched across a day. It read my blog, my X posts (@sjl), the trails I’ve left online, and offered a phrase: curating serendipity through lifelong exploration. It fits. The seminar wasn’t the point, nor the gardens, nor even the itinerary. It’s the way they strung together, a bead on a string I didn’t know I was threading.

Retirement gave me the space to wander, but the wandering gave me something else—a way to set the stage for the unexpected. I don’t chase serendipity like a hunter; I till the ground for it, then wait. A walk turns into a photo, a photo into a thought, a thought into a post. A seminar turns into a night of questions, a night into a plan. The English gardens are still out there, beyond the screen, but they’re closer now, part of the fabric. What stood out from Filoli? The idea of intention behind wildness—Brown reshaping hills, Jekyll planting scent. What’s next? Maybe a trip, maybe just more questions for Grok. The delight is in not knowing, but keeping the thread alive.

I enjoyed this exploration! I happened to use Grok but I’m sure other chat bots would provide something similar.

What do you think?