MicroResearch was an experiment in autonomous AI-driven research — agents that would iteratively propose changes to a trading strategy, evaluate them, and keep what worked. It ran overnight. It failed spectacularly. But the failure taught me six principles that I now apply to every multi-agent system I build. 1. Clear Roles, Clear Scope The MicroResearch failure taught me something uncomfortable: I had given the research agents the same tool access as the main agent. Full file system, full messaging, full session spawning. The only thing constraining them was a markdown file saying “please don’t do these things.” ...

Why Restart The old Five Minutes Forward ran on Gatsby 2.x — a perfectly fine choice in 2020, but by 2026 the React/GraphQL build pipeline felt like unnecessary weight for what’s essentially publishing markdown files. So I’m starting fresh with a simpler stack. The Stack Hugo — static site generator. Builds in seconds, outputs pure HTML. Git → Deploy — write markdown, push, it’s live. That’s the whole workflow. PaperMod theme — clean, minimal, dark mode included, RSS built in. ...

Then Revolutionary War. 1812. The Civil War. The Cholera epidemic. WWI. Spanish Flu. WWII. Korean War. Vietnam. Coronavirus. In terms of the level of sacrifice required to endure these events, you’d better believe that what we’re going through now in April of 2020 stacks up. You are here, now, in this moment. In terms of lives lost, we’ve experienced xx so far, and can expect to lose xxx in total. When you think of moments in the American story and where you were, this one stacks up with the most significant ones in our history. ...