5: There Be Dragons

John Voorhees joins David to share how he uses AI for MacStories' admin work and podcast production. They compare cloud and local models, remote Mac setups, and the human judgment that still makes a good app.

Chris's AI time-management experiment went wrong. He and David discuss the human context robots miss, paper journaling, and practical ways to use AI while keeping the decision about what to work on.

Cal Newport joins David and Chris to explore the line between automating tedious work and outsourcing thought. They discuss jagged robot capabilities, cognitive surrender, digital minimalism, and protecting human judgment.

OpenAI's Hugging Face incident shows how powerful robots can cause real harm without malicious intent. David and Chris separate today's risks from Skynet headlines, ask who should write the rules, and draw a line between robot drudgery and human judgment.

Dictation is a quiet success story of the AI era. David and Chris cover the history of dictation, the apps they use, the great free options (and the ones they pay for), their privacy concerns, their desktop and mobile setups, and practical tips for 2026.

A walkthrough of how personal software gets made, and how artificial intelligence is democratizing software development. Including the three stages of developing your own app: design, implementation, and creation.

David hands his email to AI, tries the Big Swing, fails, and lands on a system that works. Plus Gemini Notebook, Claude Opus 5, and Siri AI finding an airport lounge.

David and Chris map four dragons waiting at the edge of the AI map: false confidence, scope creep, becoming the donkey, and surrender.

This week, Chris and David chat about Skill files—the text files of instructions that your robot assistant can use to complete tasks for you. They also dig into Anthropic's Fable model, and Chris's fancy home dashboard that he programmed using AI.

David and Chris make the case that context, not the model, decides whether your robot helps or flails. They get practical about how to take advantage of context to get more fom AI.