Debug Log #3: I Had Claude Code Backtest a Trading Strategy for a Week, and It Found Three Bugs In Its Own Simulation

Automated excerpt

When I actually checked the math behind that specific row, the trigger had fired at roughly -2. 9% below the average cost basis -- nowhere near the -50% the log claimed. The rule, as written in my own spec, was simple: a buy-the-dip trigger at "-50% below average cost" should fire when price crosses average_cost * 0. 5. It looked like a real trigger doing real work.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.