Essays on systems, execution, AI, and the operating problems underneath them.
Ideas is where I write from real operating problems.
Most pieces start with something concrete that is not working, then trace the system around it: what the incentives are doing, where judgment is being crowded out, how AI changes leverage, and what a simpler operating model might make possible.
How I use OpenClaw for investment reviews, forms, and upcoming commitments, and how the architecture has changed since June.
As models improve, the next AI productivity gain may come from removing yesterday's prompts, plugins, and orchestration while keeping the controls that protect judgment.
The open-source OpenClaw runtime gives me the substrate. The real work was designing the operating layer on top: routing, memory, capabilities, state, lanes, and context discipline.
AI changes leverage, not the logic of judgment. Chinese-first post with a separate English companion version.
A systems essay on how centralisation can narrow local judgment while preserving state capacity.
The real power in AI is not the model. It is the harness around it.