Crazy Wisdom
Episode #549: From MS-DOS to Vibe Coding: How Non-Technical Founders Build Complex Software
- AI & Agents
- Vibe coding
- AI psychosis
- cursor
- Buenos Aires
- AI Whispers meetup
- app development
- landing page
- beta testing
This video isn't available here. Try YouTube, or listen to the audio below.
Watch on YouTubeAbout this episode
Show Notes:
- Dan Martell's book "Buy Back Your Time" was mentioned as one of the best business books for thinking about life and business
- Check out John Vervaeke's "Awakening from the Meaning Crisis" for understanding relevance realization and why AI fundamentally cannot determine what's relevant to humans without being told
Timestamps
- 00:00Michael discusses being exhausted from getting his app ready for launch, working nonstop with AI to prepare landing page for podcast traffic driving beta signups
- 05:00Stewart explains starting AI Whispers in Buenos Aires after leaving OpenAI vendor company, meeting early adopters like Torin who was building mind-reading EEG technology
- 10:00Discussion of how corporations resist AI adoption due to political games and job security fears while some companies use AI as excuse for pandemic-era layoffs
- 15:00Stewart describes teaching workshops on using LLMs as linguistic tools rather than coding tools, noting technical people often lack humanities background needed for prompting
- 20:00Explaining chatbot wrappers, API calls, and how Anthropic's reasoning quality declined after Chinese distillation attacks copied their secret sauce developed with philosophers
- 25:00Technical discussion of model training, fine-tuning versus RAG for new information, and different approaches to updating AI knowledge beyond initial training
- 30:00Stewart describes building podcast recording software to replace expensive Riverside, struggling with syncing audio and video files across different computer clocks
- 35:00Discussion of critical factors in vibe coding, discovering unknown technical requirements, and how AIs don't automatically reveal missing information
- 40:00Stewart's reverse engineering process using deep research function to study competitors' hiring and technology stacks, separating planning agents from coding agents
- 45:00Prompting techniques including "explain like I know everything" and using spaced repetition systems to capture valuable prompts and technical knowledge
- 50:00Michael explains his Generux app for generating ecommerce content using Amazon review data analysis to inform high-converting listing images and videos
- 55:00Discussion of founder mentality involving self-delusion about project timelines, Michael working nine-plus hours daily for nine months on app development
- 60:00Comparing Amazon's expert software to prosumer software approach, discussing distribution challenges and future robotics applications for customized products
- 65:00Stewart demonstrates spaced repetition app for memory improvement and knowledge retention, explaining relevance realization problem that AI agents cannot solve without embodiment
Key Insights
- Stewart Alsop started AI Whisperers in Buenos Aires after leaving his role at Invisible Technologies, which was OpenAI's largest vendor for RLHF work. He noticed that machine learning engineers at tech companies lacked the humanities background needed to properly interact with large language models, which are fundamentally linguistic tools. This led him to create weekly workshops teaching non-technical people how to use AI effectively, running events every Thursday for two years straight. The group attracted intense geeks from the start and eventually led to Stewart speaking right after Vitalik Buterin at DevConnect, marking a significant milestone for the community.
- Large corporations are resistant to AI adoption due to multiple factors including political dynamics within organizations and employees fearing job loss. Many companies that grew during the pandemic are now using AI as an excuse to downsize when the real issue is inefficiency from rapid expansion. Stewart observed that even technical people in machine learning often don't understand how to properly use AI tools because they lack linguistic and humanities training. The fundamental problem is educational, requiring companies to train people how to use these new tools while those same people resist learning them.
- Vibe coding has evolved significantly with Claude Code being a game changer that reduced the technical barrier to entry. Before Claude Code, developers needed substantial technical knowledge to work through constant doom loops and debugging cycles. The success of coding AI tools stems from thirty years of testing infrastructure that provides clear yes or no feedback on whether code works. This infrastructure doesn't exist in the same way for manufacturing, science, and other fields, which is why software became the dominant area for AI assistance initially.
- Claude's quality degradation over recent months resulted from multiple factors including distillation attacks by Chinese companies who reverse engineered Anthropic's reasoning capabilities. Anthropic had hired philosophers, sociologists, and psychologists to develop exceptional reasoning in Claude 4.5, but this was expensive to run. When Chinese models like Kimi copied these capabilities at one tenth the cost, and when mainstream users flooded the platform before Anthropic's planned IPO, the company had to reduce quality to manage computational costs. This represents a significant loss for power users who relied on Claude's superior reasoning abilities.
- Stewart built a podcast recording application to replace Riverside because he needed API access to automate workflows, which Riverside wanted one thousand dollars monthly to provide. The technical challenge involves syncing audio and video from local recordings on multiple computers with different clocks through a server, then merging them so voices match lip movements. This problem requires understanding complex timing issues across different network conditions and file formats. Stewart has been working through AI psychosis for months on this FFMPEG pipeline problem, illustrating how vibe coding still requires building intuition about technical problems even without traditional coding knowledge.
- The transition from expert software to prosumer software represents a major opportunity for AI-enabled tools. Expert software like Photoshop, Blender, and terminal interfaces have extreme complexity that intimidates beginners, but AI is making these capabilities accessible through natural language. The reign of specialists is ending as generalists with broad knowledge and curiosity can now build complete applications by leveraging AI to fill technical gaps. This shift particularly benefits entrepreneurs and founders who specialize in getting into difficult situations and figuring them out, even when they originally thought tasks would be easier than they turned out to be.
- Building applications with AI requires accepting massive time investments beyond initial estimates and developing strategies for overcoming knowledge gaps. Michael estimated his ecommerce content generation app would take months but spent nearly a year working over nine hours daily, while Stewart spent months solving audio-video sync issues. Success requires using tools like deep research to understand how competitors solve problems, maintaining separate planning and coding agents, and learning to ask the right questions. The key insight is that vibe coders can achieve ninety percent of functionality independently, but the final ten percent often requires understanding specific technical concepts that AI cannot intuit without proper context and domain knowledge.
Episode transcript
Welcome to the Crazy Wisdom podcast. This podcast is for you. If you have an insane drive to find the truth of things, it's not the good answers that we seek, but the good questions. I interview a range of different guests from many different fields, all with the intention to uncover the simple truths that are hidden in plain sight. Most people don't want to go there. I go there, my guests go there, and you benefit. Please let me know if you enjoy these episodes and as always, subscribe on itunes, Spotify or wherever you listen to the podcasts. Welcome to another episode of Crazy Wisdom. Today we've got a special episode for you, the listening audience with Michael. And Michael is a AI whisperer. He took what we were teaching about Claude Code about a year ago. I can't remember now. It's all mixed up. And as a non technical business idea guy like myself went and ran with it and both of us are now pretty good at vibe coding. And so he interviewed me about this new world that we're entering and so we have a lot of insights for you. I do a full share of everything I know at this moment. and I think that's pretty special. and I'm recording this intro to solve a specific problem I've had for a very long time of how do I just very quickly record video and audio in a way that I can pipeline it through all of the things I've been thinking about for many years. And we go into that in this episode about what I've built. So please go check out Michael's new application. and also all that stuff will be in the show notes and please let me know what you think. Find Crazy Wisdom on Spotify, iTunes, YouTube and have a great day.
Your first full transcript is free. After that, an email opens every transcript in the index — a list of readers we can write to, not a guest book.