Adaptive Thinking Doesn't Change Quality. It Changes Variance.
I blind-tested Claude Code’s CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING setting with 20 headless sessions. Quality was identical. Variance was not.
Claude Code Memory: Progressive Discovery vs. Context Dumps
Most AI memory systems dump everything into context. Ours uses progressive discovery: a nightly dream cycle distills all learnings into ~2000 tokens.
Tell the Model What to Do, Not What to Avoid
Blind A/B tests on Go code generation showed positive framing in agent instructions consistently outperforms prohibition language. I built a linter to enforce it.
I Was Excited to See Someone Else Build a /do Router
Nine months of building in public with limited traction. Then someone posted a system with the same architecture and I felt something I wasn’t expecting.
The Handyman Principle: Why Your AI Forgets Everything
Context is a scarce resource, not a dumpster. Here’s how I stopped Claude from forgetting.
Everything That Can Be Deterministic, Should Be: My Claude Code Setup
The alien tool came with no manual. Here’s how I learned to hold it.
The /do Router: Keyword Matching for Specialist Selection
A 394-line routing system that loads domain specialists instead of letting Claude improvise. 33 agents, 57 skills, keyword matching. The mechanism and failure modes.