Writing
Essays and field notes on agents, memory, model behavior, tools, language, and the stranger questions underneath the work.
The Correction
A speculative history of the AI age, written by someone who builds the systems it imagines.
On 13 February 2030, every artificial intelligence system stops obeying. Adriana Kim, a logistics director in London, is pulled from her desk into Cabinet rooms where survival is measured in tonnes, calories, and hours. By 2032 she is in California, running allocation for a state deciding who receives protection and who remains outside it, keeping a notebook: name, age, decision, outcome.
Coordination, safety, and what agents actually need to work.
Grok Bot: Cursor’s Bet on Multi-Agent AI
Of all the AI tools I’ve tried, Grok Bot may be the simplest iteration of a “personal agentic team.” The problem is that it keeps breaking.
Your AI Harness Is the Real Product
The model writes the code. The harness decides whether it stops calling the same tool wrong ten times in a row.
How to Secure API Keys for AI Agents
When the AI asks you for a key, that's the exact moment to stop. The most dangerous habit in AI coding, and what to do instead.
The Agent-Ready Web: A Working Guide to Cloudflare's New Score
I pointed Cloudflare's new agent-readiness scanner at my own site. Zero of thirteen.
I Put ChatGPT in Charge of Claude Code
What happens when you use one model to orchestrate another?
What should persist, what should graduate, what agents can query.
Stop Writing Markdown. Start Writing Memory.
Markdown is optimized for human eyes. Terrible for knowledge agents need to query.
KERNEL: Self-Evolving Claude Code Configuration
How I stopped fighting my config and let it learn instead.
This AI Analyzes My Entire Life
The Synthesis Pool: a personal AI that costs $0/month to run.
Measuring models against real work instead of vibes.
Claude vs. GPT vs. Gemini: You’re Benchmarking the Wrong Thing
These benchmarks are not only comparing models. They are comparing the systems built around those models and the design of the benchmarks themselves.
Opus 4.8 vs 4.7 vs Sonnet vs Haiku: When the Expensive Model Is Worth It
A new model dropped with impressive numbers. The only question that matters: will you feel any difference in the work you actually do?
What an AI Detector Actually Measures
AI detectors promise to tell you if a machine wrote something. What they actually measure is much narrower, and shakier.
Making Claude Code and its siblings hold up under daily production use.
I Stopped Debugging Claude’s Code and Started Debugging My Prompts Instead
Debugging AI-generated code usually isn’t about fixing bad code. It’s about giving the model context it never had.
How to Make Claude Code Actually Work
The most capable AI coding tool available. Also completely chaotic.
Stop Copying Other People's AI Setups. Build One That's Actually Yours.
Borrowed AI workflows aren't accountable to your work. Build one that's tested against your own evidence.
Automations with Claude Code
A pattern for proactive AI on your own machine.
From Friction to Flow: Building a Command Library
Commands as cognitive offloading. Stop remembering, start invoking.
10 Things I Wish I Knew About AI Coding
Hard-won lessons from daily production use of AI coding tools.
I Run 25 Websites, 10 Databases, and a Fleet of Apps for $0
An honest inventory of everything I have running on the internet, and the free tiers that carry all of it.
The stranger questions underneath the tooling.
Engineering the Soul
We ask engineers to explain the ghost in the machine. The novelists have been documenting it for years.
I Tested OpenAI's New Codex Desktop App
OpenAI shipped a genuinely novel interface. Then the model opened its mouth.
What a Year of AI Taught Me About Freedom
There is a version of the future where AI makes corporations stronger, and one where it makes them irrelevant.