top of page

014

Vibe Coding That Works

16/07/2025

Pete Winn, Andy David

Pete and Andy introduce "slow code," their methodology for coding with AI that prioritizes intentionality over the quick-but-messy "vibe coding" approach, combining human planning with AI execution through a three-phase process of ideation, planning, and implementation.

The conversation explores their tool stack, how multi-agent conversations avoid single-model bias, and how this methodology parallels creative frameworks like "write drunk, edit sober."

Description

In this episode, the hosts discuss their development of "slow code," a more intentional approach to coding with AI that contrasts with "vibe coding." 


They explore how this methodology creates a structured workflow combining human planning with AI execution, resulting in higher quality code while maintaining the speed benefits of AI assistance.  


Key Themes: *Understanding Vibe Coding* (00:02:20 - 00:08:00)

  • Vibe coding involves speaking instructions to AI and ignoring the underlying code

  • Democratizes coding by allowing anyone to build in natural language

  • Major downside: potential security issues and poor code quality

*Evolution to Slow Code* (00:08:00 - 00:19:40)

  • Hosts developed methodologies through experimentation with AI tools

  • Initial frustrations with existing AI coding tools led to refinement

  • Slow code combines intentional planning with AI execution

*Three-Phase Methodology* (00:19:40 - 00:25:30)

  • Ideation: Using Claude Desktop for exploration and brainstorming

  • Planning: Converting ideas to structured documents and roadmaps in Obsidian

  • Execution: Having AI implement based on detailed specifications

*Tools and Implementation* (00:25:30 - 00:40:00)

  • Using Obsidian for planning and documentation

  • Connecting to AI tools via MCP (Model Context Protocol)

  • Root Code for implementation with orchestration capabilities

  • Benefits of separating environments for different phases

*Multi-Agent Conversations* (00:40:00 - 00:51:00)

  • Creating pipelines where multiple AI agents discuss ideas

  • Using different models (Claude, Grok) to avoid single-model biases

  • Value in seeing how ideas develop through agent conversations

*Benefits of Slow Code* (00:51:00 - 01:01:30)

  • Creates reusable, higher quality code versus one-shot vibe coding

  • Maintains human intentionality and design control

  • Still much faster than traditional development

  • Parallels the "write drunk, edit sober" approach to creative work

*Future Applications* (01:01:30 - 01:15:00)

  • Integration with Goose for continuous development and scheduling

  • Creating dedicated AI development environments

  • Applications beyond coding (writing, research, analysis)

  • Plans to share methodology through tutorials and community

*Contrasts with No-Code Tools* (01:15:00 - 01:26:00)

  • Visual no-code tools add unnecessary complexity

  • Slow code leverages AI's strengths while maintaining human oversight

  • More flexible than constrained visual interfaces

Check out more episodes

The Good Stuff is a low-fi dialogue with Pete Winn and Andy David.

 

Each week, we share our everyday experiences working with artificial intelligence and how it's fundamentally changing the rules of work and business, the economy, entrepreneurship, and human potential. We explore the ripple effects, unintended consequences, and emerging opportunities as AI transforms how we work and create, diving into the tools and technology we're using each week.

Expect a mix of chats out of the back of a van at the beach, walking interviews and general use of dialectic and discussion with insightful guests that lift the lid on complex topics. Chilled out, minimal jargon, authentic.

 

Connect With Us:

Email: info@otherstuff.studio

Pete: https://x.com/Pete_Winn

Andy: https://x.com/andymdavid

Transcript

Add paragraph text. Click “Edit Text” to update the font, size and more. To change and reuse text themes, go to Site Styles.

bottom of page