The Archive · 2013 — Now
AI archive.
135 posts in this category
135 essays in the archive · 13 languages · 45 categories
Codex with GPT-5.4 vs Claude Code with Opus 4.6 — Why I Used Both (March 2026)
In March 2026, after using Claude Code with Opus 4.6 daily for almost a year, I spent a week with Codex and GPT-5.4. My verdict then: neither tool won outright — the combination of cross-model review, complementary strengths and operational resilience beat either alone. (I have since moved to a single model; see the updates below.)
Read the analysis
AI for media planning
AI for media planning works best on the repetitive, data-bound steps before a plan exists — audience pulls, channel sizing, budget scenarios — while the judgement stays human. This is a practical guide to what the model is and is not good at, and where a team should start.
The App Store Said Yes
Two weeks ago I wrote "Still building. Still not done." Today DIALØGUE is live on the App Store. Here's what the last 40% actually looked like.
The Full Index
Earlier entries
Sort: Newest
Marketing AI policy and governance
No. 05AII Translated 3.9 Million Words in 4 Days with Parallel AI Agents
No. 06AIHow to pilot AI in a marketing org
No. 07AINobody Tells You: The Real Work Starts After the AI Says 'Done'
No. 08Paid MediaAI and brand safety in paid media
No. 09AIWhat Happens After You Migrate: 8 Days of Compounding Returns
No. 10AIHow I Rebuilt My Blog Backend in 4 Days with Claude Code
No. 11AIAI for agency new business
No. 12AIMeasuring marketing incrementality with AI
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.