The Good Stuff

# 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 ShamanHosts: 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 agentsContext window limitations: quality vs quantityHuman vs AI Context (08:22-15:55)The challenge of replicating human contextual understanding in AIMulti-personality aspects of identity and AI agent development"Things you know" vs "things you are" in AI persona creationVision and sensory data as the next AI frontierLearning Transformation (15:55-24:12)Khan Academy's personalized AI math tutoringTailoring communication styles to individual learning preferencesChatGPT's tutor mode: guided discovery vs direct answersVoice interface challenges in natural conversationCreativity as Process (24:12-35:20)Creativity as a "volumes game" generating many ideas to find exceptional onesAI raises both floor and ceiling of creative outputThe "doorman fallacy" - losing tacit knowledge through naive automationPersonal AI tools outperform organisational implementationsPurpose in an Abundant World (35:20-46:48)When everything is automated, purpose becomes the key differentiatorBrand strategy increasingly important with commoditized intelligence- Balancing automation benefits against loss of meaningDavid Graeber's "bullshit jobs" in AI contextCreative Problem-Solving (46:48-55:06)Engineering vs creative solutions (Rory Sutherland's elevator mirror example)Market research challenges: people can't articulate true needsThe difference between mechanical and psychological solutionsDecentralization & Community (55:06-58:14)AI enabling hyper-localisation and community based solutionsShift from centralised to localised innovationEvolution toward gig economy with community co-working hubsShamanic Prompt Engineering (58:14-1:18:43)Prompt engineering as modern "shamanism" summoning digital entities"Set and setting" for AI interactions, borrowed from psychedelic methodologyMulti-agent conversations for enhanced ideationTools like Mind Hive for collaborative AI workshopsCreative Methodology (1:18:43-1:27:54)Hemingway's "write drunk, edit sober" frameworkSeparating ideation from judgment in creative processesUnderwater brainstorming for forced creative breakthroughsDivergent vs convergent thinking statesDigital Summoning (1:27:54-1:39:34)AI requiring careful "birthing" and context settingTraditional shamanic practices informing modern AI interactionThe art of "enchanting" AI with proper incantationsStandout 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."

The Good Stuff, with Pete and Andy - Episode 12: AI Myths and the Future of Work as PlayHosts: Pete and Andy (recorded at City Beach, Perth)Episode Overview: 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.Reflections on Guest Episodes (00:00-03:20)Dynamic of having guests vs. just the two hostsPreference for discussion format over structured interviewsOrganic conversation flow versus scripted contentThe "I Trained the Model" Myth (03:20-10:30)Misconception between fine-tuning vs. adding context/documentsMost "training" is actually just attaching PDFs or system promptsLLMs should handle interface, not factual recallContext engineering as the superior approach over model trainingSmall vs. Large Language Models (10:30-16:30)The "Ferrari for grocery shopping" mentality - overusing frontier modelsSmall language models as the better choice for repetitive commercial workflowsCost and speed advantages of smaller models for specific tasksModular approach: using right-sized models for different pipeline stepsInterface Design Myths (16:30-27:30)Chat as the default AI interface limiting potentialNeed for adaptive interfaces suited to different working stylesMicroservices architecture finally becoming economically viable with AIMoving beyond monolithic "big model for everything" approachFlow State and Adaptive Interfaces (27:30-39:00)Spreadsheets as example of adaptive, durable toolsVisual vs. text-based collaboration preferencesThe ramp-up/ramp-down challenge when returning to complex projectsMultiple input/output modalities for different contextsHuman Collaboration Patterns (39:00-48:00)Engineers gravitating to whiteboards for collaborationThe canvas as shared workspace vs. individual thinking spaceVoice, visual, and collaborative interfaces serving different needsBalancing real-time interaction with persistent documentationCreativity vs. Productivity Paradigm (48:00-58:00)AI as creative enabler rather than just productivity boosterThe scary prospect of agency - having to decide what to work onEmbodied human experience as irreplaceable for insight generationExamples from Rory Sutherland: mirrors in elevators, train comfort over speedThe Future of Work as Play (58:00-1:08:00)Moving from medieval peasant schedules to office work and back to leisureWork resembling exploration and experimentationThe role of craft and embodied skills in an AI worldVictorian gentlemen as preview of future leisure classError Tolerance Double Standards (1:08:00-1:14:00)Unrealistic expectations for AI accuracy vs. human error ratesNeed for same systems and processes, just faster iteration cyclesHuman mistakes tolerated due to context; AI mistakes seen as fundamental flaws"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 workBottom 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.

Joel Pember, brand director and co-founder of Juicebox, shares his journey from photography to digital marketing. He dives into how AI is reshaping creativity, emphasizing the importance of human experience in storytelling. The conversation touches on the ethical dilemmas tech leaders face, balancing innovation with societal impacts. Pember discusses brand loyalty in a digital age of overwhelming choices and the tension between global culture and local communities. His insights highlight the evolving role of brands in fostering authentic connections.

The discussion kicks off with how AI is reshaping product development and business creation. Rapid prototyping is now more accessible, emphasizing product-market fit over traditional engineering. Hosts highlight the importance of personal passion in problem-solving, shedding light on the decline of the sunk cost fallacy. They also explore the rise of hyper-local solutions and the potential transformation of B2B SaaS. With an eye on critical thinking in an AI-driven landscape, the episode encourages experimentation and adapting to new tools.

Dive into the fascinating world of AI tools and their implications! Explore the debate on whether AI truly reasons or just patterns. Hear about the surge of local AI systems and their privacy benefits, contrasting with cloud solutions. Uncover the psychological effects of engaging tools on creativity and productivity. Plus, discover the joys of personal projects and how they can enhance your tech journey. Finally, join a light-hearted discussion on minimizing screen time while navigating parenthood!

AI is metamorphosing entrepreneurship by breaking down barriers to starting personal businesses. The hosts discuss how AI tools can aid coding and project development, transforming learning experiences. They also critique the traditional startup mindset, advocating for the value of small ventures. Additionally, the conversation touches on the shift towards flexible work, emotional fulfillment, and the impact of AI on enhancing creativity. Together, these themes highlight an exciting era of innovation and self-agency.

The hosts explore the impact of AI on podcast production, revealing how it streamlines workflows through automation. They discuss the balance between quality and efficiency in content creation and the importance of adaptable skills in an AI-driven economy. The conversation highlights the evolving role of generalists and the need for continuous learning. They delve into personal experiences driving product innovation and examine the changing labor landscape, including the potential for universal basic income as technology reshapes job markets.

AI is reshaping education, helping kids learn vital skills for the future. The hosts share inspiring examples, like a young entrepreneur's boutique and game development projects. They critique the outdated assembly line approach to education, championing playful, personalized learning. AI not only assists in coding but also enhances motivation through relatable projects. There's a call to reclaim creativity in adulthood and rethink the value of credentials, advocating for genuine learning over mere qualifications.

Explore how AI could transform businesses without needing the latest models. The hosts argue existing technology is powerful enough to drive big changes today. They compare AI’s potential to farming mechanization, showing how tasks can be broken down into manageable parts. The discussion challenges common misconceptions about automation, advocating for immediate action instead of waiting for advanced AGI. They also touch on the shift to e-commerce and the essential adaptation businesses must embrace to thrive.