Posts
All the articles I've posted.
On Input: The Allowlist
Published: at 06:21 PMInformation is infinite, attention isn't. Four inputs worth taking: what you love, what serves your data, what sits outside your cognition, and health — where no amount of planning beats action.
Self-Evolution Is a Data Problem
Published: at 03:10 AMEveryone wants agents that improve themselves. The blocker isn't intelligence — it's data. Observability first, a centralized fleet second, the agent last.
FDE: The Job Is the Gaps
Published: at 02:47 AMConfirm the requirement, build on the product, deliver. Accurate and useless — the real work is extracting specs nobody can state, winning access, and shipping evidence instead of demos.
Agent Harness Turns Development into Executable Patterns
Published: at 03:25 AMAgent harnesses are not just multi-agent wrappers. They route context, package workflow skills, expose project-specific tools, and use traces as the feedback surface for improvement.
Game theory as a learning lens, not an arithmetic class
Published: at 01:50 PMA learning-oriented distillation of game theory resources: Schelling, Yale, Model Thinking, Game Theory 101, and evolutionary games. The point is not memorizing formulas, but learning to see constraints, commitments, types, and feedback.
Minimum Viable tmux
Published: at 01:00 PMThe tmux man page is 4,000 lines. The part you need is about six — four commands and one prefix key — plus the payoff I didn't expect: coding agents read your panes too.
The Memory Stack
Published: at 12:14 PMAgent memory isn't a switch you flip. It's a four-layer stack: a provider, a policy MCP, the laws you write, the router you fork.