Guest Appearance on the Ditching Hourly Podcast
By Dave Mabe
Jonathan Stark recently invited me on his Ditching Hourly podcast to discuss AI and trading.
We discussed a wide range of topics related to AI and trading, including how I started using Claude and how to get AI out of its own way.
Here are the show notes:
We cover systematic versus discretionary trading, automated trade execution, backtesting, Claude Code workflows, unit testing, AI-generated strategy ideas, the danger of building complex financial software without domain expertise, and how to turn expert judgment into useful guardrails and questions instead of pretending AI can supply one perfect answer.
00:01 — Systematic Trading Basics
04:57 — How AI Entered Dave's Workflow
07:45 — Unit Tests and AI-Assisted Development
12:00 — From Manual Approval to Auto Mode
13:34 — Auto Mode and the Trade Client
18:39 — The Strategy Cruncher and Backtesting
22:10 — Trading Versus Investing
26:22 — Turning Market Patterns into Strategies
29:03 — AI's Dangerous Overconfidence
33:45 — The Backtesting Software Trap
37:14 — Operational AI Inside MabeKit
40:40 — Encoding Expert Judgment
44:38 — Guidance Instead of Perfect Answers
50:10 — AI Adoption in Trading
54:33 — Experts, AI, and the Road Ahead
Thanks for having me on the show, Jonathan!
-Dave
P.S. "The process of becoming a more systematic trader honestly mirrors the journey of becoming a trader at all—lots of ups and downs, frustration, second-guessing, and moments where you want to quit. And then every once in a while, there’s a real moment of clarity and forward progress. Using the AFL code generator in MabeKit feels like one of those moments." - Mike A. Get Instant Access to MabeKit