Posts

• meta · 2026-07-20 Does AI's rise make humans obsolete? — from AlphaGo to Shin Jinseo I got into coding when AlphaGo beat Lee Sedol — it read as 'humans lost.' This week Shin Jinseo won a 2-stone handicap game against a stronger AI. Humans didn't catch up; through AI's lens, they evolved. Developers too.
• meta · 2026-07-20 I thought it was a simple task — why it took 12 rounds of adversarial review It looked simple: replicate an existing pattern into another mode. But cross-provider review found subtler flaws over 12 rounds. Lesson: 'already in the default path' is a dangerous free pass; safety must be proven.
• infra · 2026-07-19 The deployment succeeded and deployed nothing — a mutable tag swallowed the rollout The deploy said success, rollout said complete, the safety net went green — yet production didn't change. Mutable tag (latest): same name, new content, so Kubernetes saw 'no change,' and the safety net passed vacuously.
• meta · 2026-07-13 The people left out of AI — I was unemployed once too Some won't use AI even for free — the barrier isn't money but having no reason to use it. AI can widen the gap by will, not just money. You can subsidize access, not drive; but you can make sparks and on-ramps.
• meta · 2026-07-12 You get 5 hours a day. AI uses the other 19. A working person gets about 5 usable hours a day; the other 19 are wasted. AI uses those 19 — for cents an hour. But it pays off only if you first build a fulcrum: verification. Without it, it's negative leverage.
• meta · 2026-07-11 Autonomy and fail-closed don't conflict — my harness started running itself I made my harness autonomous — give it one goal and it runs to completion, and it even cut its own release. But autonomy didn't mean removing review; I added a layer. Adversarial layers still caught real bugs mid-run.
• meta · 2026-07-09 Hey, have you even tried it? — the fastest way to get good at AI The fastest way to get good at AI? Use it a lot — but build, don't just search and ask. Playing AlphaGo vs building it changes your questions, and the builder handles AI better. Process, not result, is the asset.
• meta · 2026-07-08 The product and the tool grow each other — the virtuous loop in how I work I built a tool to build a product. Then the agents building it hit friction — which becomes an issue, improves the tool, improves the product. Not the loop inside the harness, but one level up: an org I designed.
• meta · 2026-07-07 I ran every stage on the top model, then moved implementation to a cheap one — here's why I won't go back Everyone mixes models, but which one goes on plan, implement, and review differs. I started with the top model everywhere, hit token limits, and cheaped out on implementation. Constraints, not taste, decide the layout.
• meta · 2026-07-05 Multi-agent isn't always the answer — so I asked an AI directly Does adding more agents help? I asked an AI. It splits on one question — can parallel pieces succeed without knowing each other's decisions? Yes for reading and exploring; for writing one coherent thing, it backfires.