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:

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 AI: Prompting Books Writing

How to Write a Book (The Voice-First AI Workflow)

We’ve all seen the “How to write a book in 24 hours with AI” tutorials. Usually, they involve a single prompt and result in a 200-page book of absolute “slop”—generic, robotic, and devoid of any human soul.

I recently came across a workflow on X that flips the script. Instead of asking AI to write for you, it uses AI as an editor, librarian, and investigative journalist to extract the book that’s already in your head.

I’ve adjusted this process a bit (with Gemini’s help) and built a revised “Toolkit” that makes it even more rigorous. This is a system you can use to write a book that actually sounds like you.

The Philosophy: Knowledge Extraction > Generation

The biggest mistake people make with AI is using it to generate ideas. The best books come from extracted knowledge. You already have the expertise in your head; the hard part is the “manual labor” of organizing, structuring, and filling gaps. We often overlook stuff that we should have included or we can’t quite resolve how stuff should be sequenced for the most reader impact.

This workflow uses voice dictation as the first step to capture your raw energy and then adds in AI to help handle the structural heavy lifting.

The 7-Step “Enhanced” Workflow

1. The Walking Braindump

Go for a walk and record a voice memo of everything you want to say about your topic. Don’t worry about structure, grammar, or “the right way” to say it. Just talk. Don’t worry about it. Movement usually activates parts of the brain that sitting at a desk shuts down. You’re just using the outdoors to open up your mind and bring fresh perspective.

2. The Transcription & “Essence” Extraction

Use a tool to convert your voice memo into text (something like the built-in tools in the iOS Voice Memos app on your iPhone or, if you prefer, a third-party app like MacWhisper or Wispr Flow. I find the built-in tools work quite well these days so give them a try before spending the money for a third-party app.

Once you have the transcript, don’t ask the AI to “write a chapter.” Instead, you want to ask it for help identifying the Core Thesis, the Target Audience, and the Unique Vocabulary you used. This creates a “North Star” for your project.

3. The Voice Mirror

This step is the secret sauce. To prevent the AI from making you sound like a corporate brochure, provide it with 3-5 pages of your best previous writing. Ask it to analyze your rhythm, sentence length, and diction. Tell it: “Clean up my transcripts, but keep my fingerprint.”

4. Recursive Brainstorming

Work on the outline with the AI. Iterate. Ask it what’s missing. How does it compare to the other best-selling books in your niche. Where are you being redundant? Where is your “original” angle?

5. Filling the Gaps via “Socratic Interview”

Once you have an outline, you’ll find “thin” areas. Instead of typing, flip things around and ask the AI to play the role of an investigative journalist. Have it interview you about the missing pieces. Dictate your answers. As with the first step, this pulls deep insights out of you that you might never have thought to type. Think like you’re talking to a friend and reacting to their reactions.

6. The “Devil’s Advocate” Pass

Before you get too far, ask the AI to “Red Team” your outline. Ask: “What would a skeptic say is the biggest leap of faith in my argument?” This forces you to add evidence where you were previously relying on “trust me.”

7. The Manual Polish

Finally, sit down and type. As the original author of this workflow noted, typing activates a different, more “painful” part of the brain that is essential for final quality. Use the AI-organized markdown files as your foundation, but always do the final “human” pass yourself.

Your “Project DNA”

If you’re going to try this, the key is consistency. Keep a file called Project_DNA.md. Every time you start a new session with AI, paste this file in first. It tells the AI exactly who you are, who you’re writing for, and what your voice sounds like.

Here’s the full toolkit with prompts that I’ve just described:

The AI Book Writing Toolkit: The Prompts

To help you get started, here are the exact prompts I use for each phase of this workflow.

Phase 1: The Essence Extractor

Use this on the transcript you’ve created after your first major walking braindump.

“I am providing a transcript of a raw ‘braindump’ for a book I am writing. Do not attempt to write the book yet. Instead, perform a deep thematic analysis to extract the ‘Essence’ of this project. Identify: The Core Thesis, The Target Audience, Unique Vocabulary (metaphors/phrases I use), and the Tone Map.”

Phase 2: The Voice Mirroring Protocol

Use this before organizing transcripts to ensure you don’t sound like a robot.

“Act as my Editor and Voice Stylist. I am providing 3–5 pages of what I consider to be my best writing. Analyze this writing for sentence rhythm, diction, and structure. Whenever you help me organize my voice transcripts, you must apply these stylistic ‘fingerprints.’ Clean up the grammar, but keep my rhythm.”

Phase 3: The Socratic Interviewer

Use this when a chapter feels thin or you hit a wall.

“Act as an investigative journalist interviewing me. Identify 3 areas where my current draft is fuzzy or surface-level. Ask me ONE question at a time. After I answer, challenge me: ‘That makes sense, but what about [Counter-argument]?’ Summarize our findings afterward.”

Phase 4: The Devil’s Advocate

Use this to stress-test your draft.

“I want you to ‘Red Team’ this rough copy of my book. Imagine you are a critical reviewer. Point out the ‘leaps of faith’ I am asking the reader to make. Identify where my arguments are ‘low-hanging fruit’ and tell me specifically where I am being too similar to existing books in this niche. Help me make it better.”

Final Thought

Your goal isn’t to use AI to work less; it’s to have it help you work deeper. By offloading the “clerk work” of organization and editing to AI, you free up your brain to do the actual “author work” of thinking, connecting, and writing.

Are you working on a book? I’d love to hear how you’re using (or avoiding) AI in your process. What prompts are you using? How have you adjusted them to fit your needs?