The technical track — building in public. AI-driven trading systems, backtests, and the engineering experiments behind the writing. More code and charts than the main blog; read it if you like seeing the wiring.
Real-time NAV, positions, regime state, and the macro-gated backtest behind the strategy. Currently sitting in cash by design — see why. →
Two months ago I published a backtest claiming my crypto strategy returned +35%. This week I sat down with Opus 4.8 to pressure-test that claim — and the honest answer was more humbling, more robust, and a better story than the one I'd told.
A 9-sell AVAX trim cascade exposed what my weekend build was missing. Here's how a real backtest, a regime detector, and one honest critique session turned a shippable-but-flawed strategy into one that actually beats buy-and-hold.
I spent a Saturday afternoon connecting four AI data services into a single system that analyzes social sentiment, reads blockchain data, runs technical analysis, and executes real crypto trades on a paper account. No code. No API wrappers. Just Claude and a handful of MCP servers.