The Archive · 2013 — Now
Notes from the practice.
Write to figure out what you actually think. The post is the second draft of a thought you had earlier in the day.
565 essays in the archive · 13 languages · 45 categories
6 Months, 3 Game Projects, 0 Shipped
I spent 6 months trying to become a game developer while keeping my day job. I built three projects, wrote 684 commits, and shipped exactly zero games. Here is what happened, what I learned, and why nothing shipped.
Read the analysis
How to measure AI marketing impact
Measure decisions changed and cycle time, not output volume. Output is a vanity metric once the model makes it cheap. The signals that matter are how fast work moves, how much review it takes, how often the AI-assisted work is actually better, and what business outcome followed.
I Rolled Back 2,724 Lines After One AI Audio Change Broke Production
I pushed what should have been an upgrade to my podcast platform's voice system. Six days and several commits later, I deleted 2,724 lines of code and rolled back to what worked. Here is what happened and what it taught me about testing production AI changes.
The Full Index
Earlier entries
Sort: Newest
Which marketing tasks to automate (workflow audit)
No. 05Paid MediaAI creative production for paid media
No. 06AII'm Using Claude Code for Everything Else But Coding
No. 07AIAI campaign localization
No. 08AITwo years after my 7 Andrew Ng courses: the 2026 path I'd actually take
No. 09AIThe Code Was the Easy Part of Shipping Prova
No. 10AIWhat Agencies Actually Need From AI Is Not More Content
No. 11AIBuilding a client-memory data moat
No. 12AII Tried to Clip My Course into a YouTube Video. Here's Why I Rebuilt It Instead.
Subscribe
Get the next useful note when there is something to say
I write about AI, work, expat life, and building products. Pick the topics you care about, and I'll send the next one when it's worth your time.