AI
Authorization Isn't Safety
A Field Note on agentic money — and the layer we skipped.
field-notes
AI
Adversarial Dynamical Systems and the Ceiling on AI Trading
Field notes on what actually works — and on the limits nobody selling you a signal wants named.
AI
Harness vs. Model: Why I Built My Own
The thing that kept failing was never the model. It was the scaffolding around it — the prompts, the tools, the memory, the dispatch. That part I can own.
AI
The Expected Outcome Reframe: How I Get Unstuck
Reframing "I want to build X" as "the expected outcome is Y, verified by A, B, C" — and the different methods that got me unstuck.
AI
You cloned the harness. Now what goes in it?
DeepSeek Harness passed 160,000 stars in days. If the runtime is free, the interesting question isn't the code — it's what goes in the slots, and that's the layer a clone can't hand you.
AI
Right-Sizing the Machine: The Discipline and the Measure
My always-on instruction context was 13,891 tokens a turn. I cut it 62.8% — and found the layer had drifted off its own purpose while I wasn't weighing it.
AI
The Persistent Memory Bundle
How I keep Claude coherent across model swaps, session death, and long gaps — three layers, and the discipline that makes them work.