Learn
Serious AI work starts with better inputs.
Guides, research, and tool verdicts for professionals who want AI that reflects how they think and work.
Start here
New here? Start with these.
Understand what structured context changes about professional AI.
Essay11 min read
Should We Ask Codex? Why AI Threat Prompts Work
AI threat prompts do not scare models. They work when pressure clarifies standards, and fail when the missing ingredient is capability, not motivation.
EssayMay 5, 2026
The Super-User Paradox
The AI productivity paradox: super-users are getting faster, but most companies still do not turn AI gains into revenue, cost, or operating performance.
EssayApril 29, 2026
How to Read an AI Benchmark
Why the labs keep retiring their own headline tests, and how working professionals should actually read frontier-AI launch numbers in 2026.
Build NoteApril 22, 2026
Shipping a Multiplayer Game in 4 Days: A Spec-First Build Log
A non-engineer shipped a production multiplayer game in four days using spec-first thinking and Claude Code. Here's the full build log.
Browse
The full index.
Topics
Should We Ask Codex? Why AI Threat Prompts Work
AI threat prompts do not scare models. They work when pressure clarifies standards, and fail when the missing ingredient is capability, not motivation.
The Super-User Paradox
The AI productivity paradox: super-users are getting faster, but most companies still do not turn AI gains into revenue, cost, or operating performance.
How to Read an AI Benchmark
Why the labs keep retiring their own headline tests, and how working professionals should actually read frontier-AI launch numbers in 2026.
Shipping a Multiplayer Game in 4 Days: A Spec-First Build Log
A non-engineer shipped a production multiplayer game in four days using spec-first thinking and Claude Code. Here's the full build log.
I Built a Paul Graham AI Profile
What happens when you load 1,875 tokens of structured context into Claude? A first-person experiment in context engineering with a Paul Graham AI profile.
The Multiplier, Not the Equaliser
Ben Horowitz says AI equalises opportunity. The economics of data, power, and capital suggest a harsher truth: AI multiplies existing advantage.
Why I Manage My AI's Memory
ChatGPT's memory knows your name. It doesn't know how you think. The Two-Layer Context Model explains why, and what to do about it.
I Spent Days Trying to Master AI Image Generation. Here's What Actually Works.
A five-step AI image generation prompt engineering framework built through real editorial illustration work. ChatGPT vs Gemini, tested and compared.
The Working Professional's Guide to Claude
From Chat to Code: you don't need to be technical to use the most capable AI tool on the market. How to start with Chat, graduate to Cowork, and decide whether Code is worth the leap.