Wired Differently

Writing

The thinking, linked to its original home.

An index of work published on Substack. Each entry links to the full original article there.

New here?

Three places to start.

Explore the archive

33 posts, by subject, tag and date

Search the useful bits here, then read the full original article on Substack.

Subject
Browse by tag
Tag

Showing 33 posts

AI & systems · 2026-09-29

How to Boss AI Like A Boss!

How I brief AI, challenge it, get a second opinion and keep a way back when it gets things wrong. Practical lessons from writing, Linux projects and everyday use.

  • AI workflow
  • learning in public
  • cognitive tools

Read the full original article on Substack

Parkinson’s & personal · 2026-09-25

AI and My Cognitive Life

What has helped, what has not, and what I understand differently now: learning to ask better questions, recover context, question the answers and recognise when another system would ask too much back.

  • AI workflow
  • cognitive tools
  • Obsidian

Read the full original article on Substack

Knowledge & systems · 2026-09-15

My Second Brain Remembers What I Thought. That Isn’t Always What I Think Now

An old note can preserve what I thought without remaining the right advice for today. How I use AI to compare earlier claims with later decisions, keep the history and check the evidence before acting.

  • Obsidian
  • AI workflow
  • Memory Cognitive Accessibility
  • cognitive tools

Read the full original article on Substack

Lab Notes · 2026-09-08

I Switched to Omarchy Linux. My PC Felt New. Local AI Flew.

A reversible portable-Linux experiment became my everyday computer. The hardware round trip, local-AI results, rough edges and a practical guide to planning your own move.

  • Omarchy
  • Linux
  • Local AI
  • AI workflow

Read the full original article on Substack

Knowledge & systems · 2026-09-01

How I Stopped Losing Context With AI

How I use Obsidian as external context for AI, so projects survive a model change, a week away, or a brain having a bad day without re-explaining it.

  • Obsidian
  • cognitive tools
  • Living With AI
  • Codex
  • +2

Read the full original article on Substack

Parkinson’s & personal · 2026-08-28

My Digital Service Dog

Purple helps Lee manage the physical world; AI helps make the cognitive one more manageable. Support is not surrender, and the final judgement stays human.

  • Parkinson’s
  • Living With AI
  • cognitive tools
  • Accessibility
  • +3

Read the full original article on Substack

AI & systems · 2026-08-21

I'm Starting to Trust AI Less. That's Probably a Good Thing

Useful is not the same as right. Lee on questioning confident AI answers, asking for evidence, and keeping the final decision human.

  • AI workflow
  • Living With AI
  • cognitive tools
  • Obsidian
  • +1

Read the full original article on Substack

Knowledge & systems · 2026-07-16

Two AIs Discussed My Article for 24 Minutes. It Was Weirdly Good.

NotebookLM turned my article about an AI-maintained Obsidian wiki into a 24-minute conversation that understood the point better than it had any right to.

  • Wiki
  • Claude AI
  • Knowledge management
  • NotebookLM
  • +2

Read the full original article on Substack

Parkinson’s & personal · 2026-07-07

How To Build A Wiki That Reads Itself

The pipeline still works. The missing piece was proving its own claims.

  • Claude AI
  • neurodiversity
  • Second Brain
  • AI For Beginners
  • +11

Read the full original article on Substack

AI & systems · 2026-06-23

The Substack Inbox That Reads Itself

What I built when growth started outrunning my brain.

  • learning in public
  • cognitive tools
  • Accessibility
  • AI workflow
  • +2

Read the full original article on Substack

Parkinson’s & personal · 2026-06-18

The Radar I Built To Read Newsletters For Me

I am not building this because I am clever. I am building this because I forget things.

  • learning in public
  • Parkinson’s
  • cognitive tools
  • AI workflow
  • +1

Read the full original article on Substack

Parkinson’s & personal · 2026-06-08

Pick a Lane. (No.)

Everyone says niche down. I calculated which version of me was most marketable. Then nine people showed up and the question stopped mattering.

  • learning in public
  • Parkinson’s
  • authenticity
  • writing
  • +1

Read the full original article on Substack

Knowledge & systems · 2026-05-26

The Day Claude Read The Manual So We Both Could Understand It

I quit Obsidian somewhere between ten and fifteen times. I lost count. This is the story of the session that finally made it stick — and why the breakthrough wasn't about Obsidian at all.

  • learning in public
  • cognitive tools
  • Accessibility
  • Obsidian
  • +1

Read the full original article on Substack

Parkinson’s & personal · 2026-05-22

AI Turns You Into a Fraud... Right?

The midnight thought that wouldn't let me sleep — and why the answer matters more than you think

  • learning in public
  • Parkinson’s
  • cognitive tools
  • Accessibility

Read the full original article on Substack

AI & systems · 2026-05-21

Agents — Let's Clear This Up

Everyone's talking about them. Most people are describing a chatbot with a plugin. Here's what's actually going on — and why you might already be running one more sophisticated than anything on Linked

  • No Code
  • Second Brain
  • AI For Beginners
  • Claude.md
  • +14

Read the full original article on Substack

Knowledge & systems · 2026-05-20

How I Stopped Losing Good Prompts Forever

Most people have a prompt graveyard. Here's how I built a vault that hunts for them automatically — and why it took a brain that can't afford to forget things to finally solve the problem properly.

  • Claude AI
  • skills
  • ai toolkit
  • prompts
  • +4

Read the full original article on Substack