Stanford’s Meta-Harness paper argues that optimizing the code around the model matters more than optimizing the model itself. I applied it to my Claude Code setup and got the first real numbers: 3,723 tokens always in context, with no evidence they’re the right ones.
A Wharton paper gave a formal name to what I described three weeks ago: when AI thinks for you and you let it. The data is worse than I expected.
AI creates a demographic time bomb: it increases demand for senior talent while destroying the pipeline that produces it. What replaces corporate apprenticeship is something closer to Hollywood.
Keynes predicted 15-hour weeks by 2030. Gates says 2-day weeks within a decade. Meanwhile, Germany, Argentina, and Silicon Valley are legislating or normalizing 12-hour days. The paradox has a name, and it’s 161 years old.
Everyone says AI makes developers faster. My experience is the opposite: I arrive exhausted not because I wrote more code, but because I evaluated more decisions. The effort didn’t shrink. It transformed.
Three fractures in how we learn, hire, and distribute capability.
Three layers of knowledge integration between Obsidian and Claude Code: from write-only vault to a feedback loop that promotes patterns into skills.
Structured requirements, deviation rules, and the art of selective theft: five concepts borrowed from GSD, twenty rejected.
From token optimization to an orchestrated development workflow with Claude Code: teaching an AI your patterns is only part of the problem.
A personal project that started as “can I automate an RSS digest?” and became a full-stack monitoring platform with narrative memory, semantic search, and AI-generated editorial commentary.