#research · 15

2026

October

30 — Unasked, Not Unwritable: What Polanyi's Tacit Knowledge Says About Debugging With an LLM 30 — Fluency Is Not Understanding: What the Illusion of Explanatory Depth Says About Learning With an LLM 26 — The Hard Parts Get Harder: Do Bainbridge's Ironies of Automation Apply When an LLM Does the Typing? 11 — Microtasks Jump the Queue: Reading Promise, await and setTimeout Order

September

22 — Jev, and Why Detection Is Not Generation 11 — Should I Use ultrastorage? the Answer Was in My Repo, Not Its README 05 — Pick the Layer, Not the Tool: the Git TUI Comparison Everyone Runs Is One Level Too High

August

18 — Agents Are Mostly Plumbing: Reading DeepSeek's Open-Source Harness

July

14 — Curation Beats Collection: What 230 Free AI Agents Added to My Setup 10 — Studying Hany Rambod: What a 25x Olympia Coach Actually Does

June

30 — Network Effects: Why the Biggest Network Beats the Best Product 29 — Build or Buy: the Crossover Hiding Under a Business-School Checklist 29 — Why the Average Is a Lie: Ergodicity and the Game That Bankrupts Everyone 29 — Why the Hundredth Cake Costs Less: Marginal Cost, Scale, and Sunk Cost 12 — Kelly Criterion: How Much to Bet When You Think You Have an Edge