How I'd Learn AI From Scratch in 2026 (skip the useless 80%)

How I'd Learn AI From Scratch in 2026 (skip the useless 80%)

Learning AI: Practical Steps for Beginners

Introduction to AI Learning

  • The speaker expresses feeling overwhelmed by the vast amount of outdated or theoretical AI information available today.
  • Focus is on the 20% of practical AI knowledge that will remain relevant over the next decade, organized into three levels.

Step One: Choose a Model and Go Deep

  • Emphasizes selecting one AI model to master due to the negligible differences in capabilities among top models.
  • Highlights that major AI companies are adopting similar core features, making skills transferable across models.
  • Suggests three main models: ChatGPT, Claude, and Google Gemini; notes xAI's lack of competitiveness and Perplexity's limitations.

Step Two: Selecting Based on Principles

  • Recommends prioritizing paid tiers for better performance; free versions often lack essential features.
  • Advises choosing an AI model that aligns with your work needs—ChatGPT excels in web search, Claude in writing/design/coding, and Gemini in mixed media processing.
  • Mentions the importance of personal preference ("vibes") when selecting an AI tool for better engagement.

Step Three: Change Your Defaults

  • Urges users to select more powerful models as defaults since companies typically default to weaker options for cost reasons.
  • Recaps key points from Level One: use paid versions, choose based on work relevance, and default to capable models.

Importance of Context Over Prompting

  • Introduces a partnership with HubSpot providing a Google Gemini cheat sheet with productivity tips.
  • Illustrates how context (e.g., past restaurant preferences for recommendations) is more effective than detailed prompts.

Framework for Effective Prompts

  • Proposes using "Outcome + Context" (OC framework), emphasizing clear outcomes paired with relevant context rather than complex prompts.

Finding Relevant Context

Strategies for Providing Context:

  1. Name Framework - Use specific terms like "pyramid principle" instead of lengthy explanations.
  1. Provide Examples - Share real examples of desired outputs instead of detailing formats or tones.
  1. Connect Tools - Integrate tools like email or Google Drive so the AI can access necessary files directly.

Managing Recurring Work with Projects

Project Components:

  1. Project Instructions - Define overarching goals and constraints applicable throughout the project.
  1. Knowledge Files - Include reference materials such as source documents or frameworks used by the AI during tasks.
  1. Memory Updates - Allow the AI to track updates and milestones automatically within projects.

Advancing Beyond Individual Projects

Understanding an AI System:

  1. An AI system connects multiple projects, identifying patterns across them that individual projects may miss.
  1. It learns from user feedback over time, improving its responses based on previous interactions and edits made by users.

Options for Implementing an AI System:

  1. Gemini Spark - Beginner-friendly but offers less control; integrates easily with existing Google tools like Gmail and Calendar.
  1. Claude Cowork - More customizable but requires some setup; designed specifically for non-tech users seeking control over their workflows.[(622)]
  1. Advanced Options (Claude Code & Codex) - Highly customizable but require coding knowledge; suited for power users looking for extensive functionality.[(645)]

Real-Life Applications of an AI System

Example Scenarios:

  1. Migrating health checkup data into Cowork allows cross-referencing insights about fitness plans tailored to health conditions.[(675)]
  1. Using reconciliation features helps refine drafts by analyzing changes made between initial outputs and final edits.[(694)]

Conclusion Recap

  • Level One focuses on mastering one chatbot model deeply while utilizing its strengths effectively.[(755)]
  • Level Two emphasizes understanding context's role in enhancing output quality through saved projects.[(778)]
  • Level Three involves integrating these projects into a cohesive system that improves efficiency over time without rushing progress.[(778)]
Channel: Jeff Su
Video description

✅ Grab my free Google Gemini Pro Tips cheatsheet - https://clickhubspot.com/d1af92 This is my practical roadmap for getting good at AI: how to pick one model and go deep, why the right context beats memorizing prompting frameworks, how to save that context in Projects (or Gems), and how to connect everything into an AI system using tools like #Gemini Spark and #Claude Cowork. Whether you're starting from zero or you've used AI for years without realizing your habits are outdated, you'll know exactly what to focus on and what to skip. *TIMESTAMPS* 00:00 How to Learn AI from Scratch Today 00:20 Level 1: How to Pick the Right Model 04:04 Level 2: The Only Prompting Framework You Need 09:18 Level 3: Build an AI System 12:32 Recap of Levels 1, 2, 3 *RESOURCES MENTIONED* Full written guide - https://www.jeffsu.org/how-id-learn-ai-from-scratch-in-2026-skip-the-useless-80/?utm_source=youtube&utm_medium=video&utm_campaign=v205 My free Cowork Toolkit - https://coworkacademy.ai/toolkit?utm_source=youtube&utm_medium=video&utm_campaign=v205 Cowork Academy waitlist - https://coworkacademy.ai?utm_source=youtube&utm_medium=video&utm_campaign=v205 *BUILD A POWERFUL WORKFLOW* 📈 The Workspace Academy - https://academy.jeffsu.org/workspace-academy?utm_source=youtube&utm_medium=video&utm_campaign=v205 ✍️ My Notion Command Center - https://www.pressplay.cc/link/s/DE1C4C50 *BE MY FRIEND:* 📧 Subscribe to my newsletter - https://www.jeffsu.org/newsletter/?utm_source=youtube&utm_medium=video&utm_campaign=description 📸 Instagram - https://instagram.com/j.sushie 🤝 LinkedIn - https://www.linkedin.com/in/jsu05/ *MY FAVORITE GEAR* 🎬 My YouTube Gear - https://www.jeffsu.org/yt-gear/ 🎒 Everyday Carry - https://www.jeffsu.org/my-edc/ #ChatGPT