The Pragmatic AI Podcast is sponsored by Tighten. T-I-G-H-T-E-N. We will take your AI ideas, prototypes or even vibe-coded apps, and we'll take them to production. Scalable and secure. Check us out at tighten.com.

In this episode, Matt Stauffer sits down with John O'Nolan, founder of Ghost, the open-source publishing platform he runs as a nonprofit that's deliberately capped at 50 people and can never be bought or sold. It's an unusual perch from which to be one of the most AI-optimistic builders in tech.

They get practical fast: John's Codex Desktop setup across two Macs, why "goal mode" is the biggest workflow shift of the year, running adversarial red-team sub-agents mid-task, and the risk-based rule for when to ship AI code versus pump the brakes. Matt shares his own turning point building a Laracon puzzle in hundreds of thousands of lines of code between meetings.

The conversation widens into where this all goes — a future long tail of small, niche businesses competing with giants, why "you're bad at prompting" is a more useful frame than "the AI is bad," and John's "made in China" theory for why today's slop era gives way to quality.

• Matt Stauffer on X - https://x.com/mattstauffer
• Tighten Website - https://tighten.com/
• John O’Nolan on X - http://x.com/johnonolan
• Ghost Website - ghost.org
• Incorruptible by Eric Ries - http://bit.ly/4pqxmbD

-----

Editing and transcription sponsored by Tighten - https://tighten.com/