What I Cannot Create, I Do Not Understand

What I Cannot Create, I Do Not Understand

Author: Noah Gift February 23, 2025 Duration: 5:07

Feynman's Wisdom Applied to AI Learning

Background

  • Feynman helped create atomic bomb and investigated Challenger disaster
  • Challenger investigation revealed bureaucracy prioritized power over engineering solutions
  • Two key phrases found on his blackboard at death:
    • "What I cannot create, I do not understand"
    • "Know how to solve every problem that has been solved"

Applied to Pragmatic AI Labs Courses

What I Cannot Create

  • Build token processor before using Bedrock
  • Implement basic embeddings before production models
  • Write minimal GPU kernels before CUDA libraries
  • Create raw model inference before frameworks
  • Deploy manual servers before cloud services

Learning Solved Problems

  • Study successful AI architectures
  • Reimplement ML papers
  • Analyze deployment patterns
  • Master optimization techniques
  • Learn security boundaries

Implementation Strategy

  • Build core concepts from scratch
  • Move to frameworks only after raw implementation
  • Break systems intentionally to understand them
  • Build instead of memorize
  • Ex: Build S3 bucket/Lambda vs. memorizing for certification

Platform Support

  • Interactive labs available
  • Source code starter kits
  • Multiple languages: Python, Rust, SQL, Bash, Zig
  • Focus on first principles
  • Community-driven learning approach

Key Takeaway

Focus on understanding through creation, leveraging proven solutions as foundation for innovation.

🔥 Hot Course Offers:

🚀 Level Up Your Career:

Learn end-to-end ML engineering from industry veterans at PAIML.COM


Noah Gift guides you through a year-long journey with 52 Weeks of Cloud, a weekly exploration designed for anyone building, managing, or simply curious about modern cloud infrastructure. Each episode digs into a specific technical topic, moving beyond surface-level explanations to offer practical insights you can apply. You’ll hear detailed discussions on the platforms that power the industry-like AWS, Azure, and Google Cloud-and how to navigate multi-cloud strategies effectively. The conversation regularly delves into the orchestration of these systems with Kubernetes and the specialized world of machine learning operations, or MLOps, including the integration and implications of large language models. This isn't just theory; it's a focused look at the tools and methodologies shaping how software is deployed and scaled today. By committing to this podcast, you're essentially getting a structured, expert-led curriculum that breaks down complex subjects into manageable weekly segments, all aimed at building a comprehensive and practical understanding of the cloud ecosystem.
Author: Language: English Episodes: 225

52 Weeks of Cloud
Podcast Episodes
Will Commercial Closed Source LLM Die to SGI and Solaris Unix? [not-audio_url] [/not-audio_url]

Duration: 10:08
Podcast Episode Notes: The Fate of Closed LLMs and the Legacy of Proprietary Unix SystemsSummaryThe episode draws parallels between the decline of proprietary Unix systems (Solaris, SGI) and the potential challenges faci…
OpenAI Red Flags Common to FTX, Theranos, Enron and WeWork [not-audio_url] [/not-audio_url]

Duration: 8:49
Podcast Episode Notes: Red Flags in Tech Fraud – Historical Cases & OpenAISummaryThis episode explores common red flags in high-profile tech fraud cases (Theranos, FTX, Enron) and examines whether similar patterns could…
DeepSeek exposes Americas Monopoly and Oligarchy Problem [not-audio_url] [/not-audio_url]

Duration: 16:51
Podcast Notes & Summary: "Deep-Seek Exposes America's Monopoly Problem"Key Topics DiscussedMonopolies in Big TechStartup Ecosystem ChallengesRegulatory EntrepreneurshipHealthcare & Innovation BarriersGlobal Tech Leadersh…
dual-model-deepseek-coding-workflow [not-audio_url] [/not-audio_url]

Duration: 6:18
Dual Model Context Code Review: A New AI Development WorkflowIntroductionA novel AI-assisted development workflow called dual model context code review challenges traditional approaches like GitHub Copilot by focusing on…
Accelerating GenAI Profit to Zero [not-audio_url] [/not-audio_url]

Duration: 8:11
Accelerating AI "Profit to Zero": Lessons from Open SourceKey ThemesDrawing parallels between open source software (particularly Linux) and the potential future of AI developmentThe role of universities, nonprofits, and…
YAML Inputs to LLMs [not-audio_url] [/not-audio_url]

Duration: 6:19
Natural Language vs Deterministic Interfaces for LLMsKey PointsNatural language interfaces for LLMs are powerful but can be problematic for software engineering and automationBenefits of natural language:Flexible input h…
Deep Seek and LLM Profit to Zero [not-audio_url] [/not-audio_url]

Duration: 8:01
LLM Market Analysis & Future PredictionsMarket DynamicsDeepSeek disrupting LLM space by demonstrating lack of sustainable competitive advantageLM Arena (lm.arena.ai) shows models like Gemini, DeepSeek, Claude frequently…
Context Driven Development [not-audio_url] [/not-audio_url]

Duration: 5:38
Title: Context-Driven Development with AI AssistantsKey Points:Compares context-driven development to DevOps practicesEmphasizes using AI tools for project-wide analysis vs line-by-line assistanceFocuses on feeding entir…
Thoughts on Makefiles [not-audio_url] [/not-audio_url]

Duration: 6:08
Title: The Case for Makefiles in Modern DevelopmentKey Points:Makefiles provide consistency between development and production environmentsPrimary benefit is abstracting complex commands into simple, uniform recipesParti…
Pragmatic AI Labs Platform Updates 12/26/2024 [not-audio_url] [/not-audio_url]

Duration: 3:26
Update 12/26/2024 on the Pragmatic AI Labs Platform development lifecycle. Thanks again for all of the new subscribers. A few things I mention in the video update: Almost every day a new course, lab, or feature will appe…