Episode 14: Vibe Coding that works!

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

Episode 13 - Creativity and Summoning AI like a Shaman

Hosts: Andy and Pete Guest: Gav Fielding (Digital Marketing & Brand Specialist, Artist) Exploring AI's creative potential, the art of prompt engineering as digital shamanism, and how traditional creative processes translate to the age of artificial intelligence. AI Development Evolution (00:00-08:22) Cursor IDE billing changes and the shift from "slow coding" to "vibe coding" Return to "super fast waterfall" development with AI agents Context window limitations: quality vs quantity

Human vs AI Context (08:22-15:55) The challenge of replicating human contextual understanding in AI Multi-personality aspects of identity and AI agent development "Things you know" vs "things you are" in AI persona creation Vision and sensory data as the next AI frontier

Learning Transformation (15:55-24:12) Khan Academy's personalized AI math tutoring Tailoring communication styles to individual learning preferences ChatGPT's tutor mode: guided discovery vs direct answers Voice interface challenges in natural conversation

Creativity as Process (24:12-35:20) Creativity as a "volumes game" generating many ideas to find exceptional ones AI raises both floor and ceiling of creative output The "doorman fallacy" - losing tacit knowledge through naive automation Personal AI tools outperform organisational implementations

Purpose in an Abundant World (35:20-46:48) When everything is automated, purpose becomes the key differentiator Brand strategy increasingly important with commoditized intelligence- Balancing automation benefits against loss of meaning David Graeber's "bullshit jobs" in AI context

Creative Problem-Solving (46:48-55:06) Engineering vs creative solutions (Rory Sutherland's elevator mirror example) Market research challenges: people can't articulate true needs The difference between mechanical and psychological solutions

Decentralization & Community (55:06-58:14) AI enabling hyper-localisation and community based solutions Shift from centralised to localised innovation Evolution toward gig economy with community co-working hubs

Shamanic Prompt Engineering (58:14-1:18:43) Prompt engineering as modern "shamanism" summoning digital entities "Set and setting" for AI interactions, borrowed from psychedelic methodology Multi-agent conversations for enhanced ideation Tools like Mind Hive for collaborative AI workshops

Creative Methodology (1:18:43-1:27:54) Hemingway's "write drunk, edit sober" framework Separating ideation from judgment in creative processes Underwater brainstorming for forced creative breakthroughs Divergent vs convergent thinking states

Digital Summoning (1:27:54-1:39:34) AI requiring careful "birthing" and context setting Traditional shamanic practices informing modern AI interaction The art of "enchanting" AI with proper incantations

Standout Quotes "Creativity is just a volumes game. You have more ideas. Some of them are good, some of them are bad, and you filter them all out." "It's almost like layering in pre-modern medicine... the clash between those applied to AI now versus current life versus future AI life." "We're all shamaning this thing. And we're just giving it a bad trip." "There probably is like a way of... maybe it's all in occult books around summoning demons. It's actually just got mis-translated over the years. And it was actually all about context engineering."

Good Stuff 12 - In The Future Work Will Look Like Play

https://blob.satellite.earth/bcfdfff33944f01b89509e4013e419c51119de8fcf9bf3a53c6fffebc02666d2

In Episode 12, Pete and Andy explore common AI myths and misconceptions, diving deep into interface design, the productivity vs creativity paradigm, and how work might evolve to resemble play in an AI-enabled future.

Key Discussion Points: Reflections on Guest Episodes (00:00-03:20) - Dynamic of having guests vs. just the two hosts - Preference for discussion format over structured interviews - Organic conversation flow versus scripted content The "I Trained the Model" Myth (03:20-10:30) - Misconception between fine-tuning vs. adding context/documents - Most "training" is actually just attaching PDFs or system prompts - LLMs should handle interface, not factual recall - Context engineering as the superior approach over model training Small vs. Large Language Models (10:30-16:30) - The "Ferrari for grocery shopping" mentality - overusing frontier models - Small language models as the better choice for repetitive commercial workflows - Cost and speed advantages of smaller models for specific tasks - Modular approach: using right-sized models for different pipeline steps Interface Design Myths (16:30-27:30) - Chat as the default AI interface limiting potential - Need for adaptive interfaces suited to different working styles - Microservices architecture finally becoming economically viable with AI - Moving beyond monolithic "big model for everything" approach Flow State and Adaptive Interfaces (27:30-39:00) - Spreadsheets as example of adaptive, durable tools - Visual vs. text-based collaboration preferences - The ramp-up/ramp-down challenge when returning to complex projects - Multiple input/output modalities for different contexts Human Collaboration Patterns (39:00-48:00) - Engineers gravitating to whiteboards for collaboration - The canvas as shared workspace vs. individual thinking space - Voice, visual, and collaborative interfaces serving different needs - Balancing real-time interaction with persistent documentation Creativity vs. Productivity Paradigm (48:00-58:00) - AI as creative enabler rather than just productivity booster - The scary prospect of agency - having to decide what to work on - Embodied human experience as irreplaceable for insight generation - Examples from Rory Sutherland: mirrors in elevators, train comfort over speed The Future of Work as Play (58:00-1:08:00) - Moving from medieval peasant schedules to office work and back to leisure - Work resembling exploration and experimentation - The role of craft and embodied skills in an AI world - Victorian gentlemen as preview of future leisure class Error Tolerance Double Standards (1:08:00-1:14:00) - Unrealistic expectations for AI accuracy vs. human error rates - Need for same systems and processes, just faster iteration cycles - Human mistakes tolerated due to context; AI mistakes seen as fundamental flaws Key Insights: "It's not the job of the model to know stuff... the best way to get good factual core from these things is context engineering." "Why are you in a hurry? Take your time. Be really comfortable. We'll get rid of the plebs." - On reframing problems "The future's here, it's just not evenly distributed" - Applied to leisure and creative work Bottom Line: AI myths persist because people experience AI through limited interfaces and apply unrealistic error expectations. The real opportunity lies in modular, adaptive systems that enable work to become more play-like, with humans focusing on embodied creativity and meaning-making while AI handles decomposed tasks.

Good Stuff 11 - Tastemakers and Zeitgeists

Summary In Episode 11 of The Good Stuff podcast, hosts Pete and Andy welcome their inaugural guest, Joel Pember, brand director and co-founder of Juicebox. The conversation explores Joel's journey from photography to digital marketing, diving into philosophical discussions about AI's impact on creative industries, the evolving nature of brand and taste in an AI-driven world, and the future of agencies in a rapidly changing digital landscape. Key Themes Introduction and Beach Recording (00:00-02:00)- The hosts discuss recording at the beach and their unstructured approach to the podcast- They introduce their first-ever guest, Joel Pemba, brand director of Juicebox Joel's Background in Photography (02:50-06:30)- Joel discusses his start as a photographer and the philosophical aspects of photo media- Explanation of Magnum Photographers and the artistic side of photography beyond technical skills AI's Impact on Photography and Creative Industries (06:30-11:00)- Discussion about how AI might affect artistic expression and photographic storytelling- Reflection on the difference between AI-generated images versus images with lived experience AI Ethics and Leadership (11:00-18:30)- Sam Altman's open letter and the weight of responsibility on AI leaders- Debate about governance versus innovation in AI development- The need for more philosophical and ethical conversations around AI Government Regulation vs. Organic Development (18:30-25:00)- Discussion about regulation of technology (social media bans for children)- Debate about centralized control versus free markets and bottom-up solutions- How younger generations will adapt to and potentially circumvent restrictions Economic Pressure and Social Considerations (25:00-30:40)- How economic pressures limit people's ability to engage with bigger questions- Discussion about inflation, debt, and the impact on younger generations- The need to question existing systems and consider alternatives Brand Value in an AI World (30:40-40:00)- The evolution of social media platforms from connection to algorithmic discovery- How brand value might increase in an era of AI-driven abundance- The role of brands as shortcuts for trust and quality The Nature of Taste and AI as Taste-maker (40:00-50:00)- Discussion about how taste is formed and whether AI can develop authentic taste- The role of lived experience in developing taste versus algorithmic recommendations- Cultural waves and how brands ride the zeitgeist The Future of Agencies and Customer Experience (50:00-01:02:00)- Joel explains how digital agencies have moved from the fringe to the center of brand strategy- How customer experience and technology are replacing traditional advertising- The role of AI in transforming how brands connect with customers Agency-to-Agency Interactions (01:02:00-01:15:30)- Exploring how AI agents might interact with each other on behalf of humans- Discussion about hyper-localization and the shift away from global monoculture- Joel's vision for Juicebox as designing meaningful connections between brands, people, and intelligent systems Conclusion (01:15:30-01:17:00)- Reflection on the conversation and plans for future episodes- Joking about making all future guests use the "Joel sprite" in their visualization

The Good Stuff 10 - Death of the sunk cost falacy

In this tenth episode of The Good Stuff, hosts Pete and Andy discuss how AI is transforming product development, business creation, and work. We explore how the falling cost of creation enables faster product-market fit testing, the future of venture capital, and the rise of multi-agent AI systems.

(00:56-07:13) The hosts celebrate reaching episode 10 Shout-outs to podcast supporters including Crispy, BundabergHodl, and BTCShellingPoint. Mention of Bethans upcoming book "The Human Edge" about critical thinking and human skills in an AI world AI and the Changing Nature of Business Creation (07:13-15:17) Discussion of the Presidio Bitcoin podcast (PBJ)How AI is making engineering less important than product-market fit The ability to rapidly test multiple ideas with minimal cost Product Market Fit and Personal Alignment (15:17-27:53) The importance of "product-founder fit" and choosing problems you genuinely care aboutReduced sunk cost bias when experimenting has lower costsHow energy and interest in a problem are better guides than purely tactical decisionsScott Adams' skill stacking concept applied to the AI era Hyper-Localization and the Future of Business (27:53-40:00)- The rise of hyper-local solutions built by people who understand specific markets"Proof of punch in the mouth" the trust advantage of local businessesPotential "death of B2B SaaS" as local solutions become more viableHow AI might transform interfaces between humans and business services Bitcoin, Capital, and Long-term Value Preservation (40:00-55:43) Discussion of how Bitcoin fits into business strategy in an AI worldThe "up, up, down" methodology (margin up, capital up, risk down)How Bitcoin provides a way to preserve value in an uncertain futureThe trade of the next decade: "Use AI to earn more money now and keep it in Bitcoin" Multi-Agent AI Systems and UI Evolution (55:43-1:15:00) Experiences with Roo Code and orchestrating multiple AI agentsThe limitations of current chat interfaces that require human directionVision for more opinionated AI agents that drive interactions forwardFuture UI as high-agency AI that can maintain context and memory