Search a title or topic

Over 20 million podcasts, powered by 

Player FM logo
Artwork

Content provided by George Pu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by George Pu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.
Player FM - Podcast App
Go offline with the Player FM app!

E44: I Failed 6 Times This Morning (And Finally Learned React)

32:49
 
Share
 

Manage episode 520198531 series 3682696
Content provided by George Pu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by George Pu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

After months of failing to learn React from books and courses, I discovered a method that worked in 15 minutes. Failed 6 times debugging code with AI this morning, finally understood on attempt 7. Why traditional education is broken for builders and the daily practice system that actually works.

The 6 failures that changed everything:

  • This morning on subway: failed 6 times debugging React code with ChatGPT
  • Felt embarrassed even though just talking to AI, no one judging me
  • Each time: "George, you're close, but you're wrong" with patient explanation
  • AI asked after attempt 4: "Should we move to next section?"
  • Said no - wanted to keep trying until I actually understood
  • Attempt 7 (15 minutes total): finally got it right because I understood, not memorized

Why I've been failing for months:

  • Tried learning React/Next.js for months - bought books, read documentation, enrolled in Frontend Masters
  • Every time opened book or video: wanted to fall asleep (not exaggeration, actual drowsiness)
  • Eyes would glaze over at code blocks and syntax
  • Even morning sessions left me drained for entire day
  • Same problem in college CS courses - struggled with motivation, not ability

The college trauma that shaped bad learning habits:

  • First year CS: did poorly on midterms/finals, thought I was bad at computer science
  • Problem wasn't me - was how I was forced to learn
  • Was the contrarian student asking "why learn impractical stuff nobody uses?"
  • Afraid to ask questions - wanted to be "George who knows everything"
  • Fear of judgment from professors/peers stopped me from learning effectively
  • Got internship, realized I was actually okay at CS - teaching method was the problem

What I did differently this morning:

  • Opened ChatGPT on phone, VS Code on laptop on subway
  • Asked: "Give me React code with bugs, let me debug them, if I fail tell me what's wrong"
  • First exercise: React state and rendering (didn't understand coming from HTML/CSS/JS world)
  • Failed 6 times, AI gave 6 different scenarios testing same concept
  • Had to explain in natural language what was happening and what caused bug
  • If professor: would be pissed and move to next student
  • If peer: would be dismissive "you still don't get it?"
  • AI: patiently explained differently each time until I understood

Active vs passive learning (the critical difference):

Traditional (Passive):

  • Read documentation about React state
  • Watch video explaining rendering
  • Complete teacher's exercises
  • Hope you remember later

AI-Assisted (Active):

  • Look at actual buggy code
  • Try to figure out what's wrong
  • Fail, get immediate feedback
  • Try again with different example
  • Repeat until actually understand

In 15 minutes of active debugging, learned more than 30 minutes of lecture

Why curriculums are broken:

  • Every system (colleges, bootcamps, Duolingo) uses curriculums to scale
  • One teacher → 100 students, one course → 10,000 people
  • But curriculums assume everyone is same - they're not
  • ANC consulting: no curriculum, one-on-one because every founder at different stage
  • Your context is unique: designer understanding devs, PM estimating complexity, founder prototyping, student building portfolio

The new learning system (15 minutes daily):

Step 1: Pick Your AI (all have generous free tiers)

  • ChatGPT, Claude, Google Gemini, Hugging Face Chat, Meta AI, DeepSeek
  • Don't let cost stop you - free versions work excellently

Step 2: Define Your Context (critical - be specific)

My React prompt: "I'm a founder trying to understand React and Next.js because my repos are built on them. I can read some code, but I fall asleep reading documentation or tutorials. I need to review code and make architectural decisions for my team. I'm not trying to write production code. I have 15 minutes per day. Please design daily debugging exercises for me."

My French prompt: "I'm learning French for work in Canada. I'm currently at A2 level (CLB 4-5). I have basic understanding but struggle with speaking, writing, and French accents. I have 30 minutes per day. Please give me daily reading and writing practice with corrections."

Must include: Role, current level, goal, time commitment, learning style preference

Step 3: Commit to daily practice

  • Doesn't matter if 1, 5, or 10 minutes - just do it daily around same time
  • Like Duolingo but personalized: your pace, your goals, infinite patience
  • I do 15 min React + 15 min French = 30 min total daily
  • On subway, before bed, whenever works

Step 4: Embrace failure

  • You will get things wrong - that's fine
  • AI explains differently each time until you understand
  • No shame in failing 6 times - it's AI not human, be shameless in learning
  • Don't pretend you understand to move on - make sure you actually get it

Step 5: Track progress

  • Every few days: "Based on my progress this week, what should I focus on next?"
  • Let AI adjust curriculum to your learning pattern
  • Creates structure that works FOR YOU, not generic structure for everyone

The French learning breakthrough:

  • Duolingo 10 min daily for 5 months = A2 level = saved $6-8K skipping 2 semesters
  • But still passive - completing exercises for things already knew
  • With ChatGPT: 10 daily vocab words with testing, paragraphs at exact level, 5 questions with corrections
  • AI predicts what I don't know and addresses proactively
  • "George, all 5 correct. However, punctuations wrong. Here's how to fix. In future if you want to say this, here's how."
  • Not just testing what I know - teaching what I'll need next

Why structure is a scam (sort of):

  • Everyone says "you need structure to learn effectively"
  • Truth: structure is valuable but YOUR structure is not THEIRS
  • Generic curriculums designed to sell courses, not optimize your learning
  • Real structure personalizes to: current level, goals, learning style, time availability, context

What this means for founders:

  • I'm founder not developer - don't need to write production code
  • Need to: review team's code, make architectural decisions, give implementation feedback, guide team
  • Traditional courses assume I want to become full-time developer - I don't
  • AI learning focuses on exactly what I need: understanding React state, debugging issues, reading codebase
  • No wasted time on syntax I'll never use or forcing through 500-page books

The fear of judgment problem:

  • In college: afraid to ask questions, everyone seemed so good at CS/math
  • Wanted to be "George who knows everything" - rather struggle silently than show weakness
  • Fear of professor/peer judgment stopped effective learning
  • With AI: fear is gone, no judgment, no embarrassment, just patient explanation
  • Revolutionary for learning

Template prompt for anything you want to learn: "I'm a [your role] trying to learn [skill] because [reason]. I'm...

  continue reading

46 episodes

Artwork
iconShare
 
Manage episode 520198531 series 3682696
Content provided by George Pu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by George Pu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

After months of failing to learn React from books and courses, I discovered a method that worked in 15 minutes. Failed 6 times debugging code with AI this morning, finally understood on attempt 7. Why traditional education is broken for builders and the daily practice system that actually works.

The 6 failures that changed everything:

  • This morning on subway: failed 6 times debugging React code with ChatGPT
  • Felt embarrassed even though just talking to AI, no one judging me
  • Each time: "George, you're close, but you're wrong" with patient explanation
  • AI asked after attempt 4: "Should we move to next section?"
  • Said no - wanted to keep trying until I actually understood
  • Attempt 7 (15 minutes total): finally got it right because I understood, not memorized

Why I've been failing for months:

  • Tried learning React/Next.js for months - bought books, read documentation, enrolled in Frontend Masters
  • Every time opened book or video: wanted to fall asleep (not exaggeration, actual drowsiness)
  • Eyes would glaze over at code blocks and syntax
  • Even morning sessions left me drained for entire day
  • Same problem in college CS courses - struggled with motivation, not ability

The college trauma that shaped bad learning habits:

  • First year CS: did poorly on midterms/finals, thought I was bad at computer science
  • Problem wasn't me - was how I was forced to learn
  • Was the contrarian student asking "why learn impractical stuff nobody uses?"
  • Afraid to ask questions - wanted to be "George who knows everything"
  • Fear of judgment from professors/peers stopped me from learning effectively
  • Got internship, realized I was actually okay at CS - teaching method was the problem

What I did differently this morning:

  • Opened ChatGPT on phone, VS Code on laptop on subway
  • Asked: "Give me React code with bugs, let me debug them, if I fail tell me what's wrong"
  • First exercise: React state and rendering (didn't understand coming from HTML/CSS/JS world)
  • Failed 6 times, AI gave 6 different scenarios testing same concept
  • Had to explain in natural language what was happening and what caused bug
  • If professor: would be pissed and move to next student
  • If peer: would be dismissive "you still don't get it?"
  • AI: patiently explained differently each time until I understood

Active vs passive learning (the critical difference):

Traditional (Passive):

  • Read documentation about React state
  • Watch video explaining rendering
  • Complete teacher's exercises
  • Hope you remember later

AI-Assisted (Active):

  • Look at actual buggy code
  • Try to figure out what's wrong
  • Fail, get immediate feedback
  • Try again with different example
  • Repeat until actually understand

In 15 minutes of active debugging, learned more than 30 minutes of lecture

Why curriculums are broken:

  • Every system (colleges, bootcamps, Duolingo) uses curriculums to scale
  • One teacher → 100 students, one course → 10,000 people
  • But curriculums assume everyone is same - they're not
  • ANC consulting: no curriculum, one-on-one because every founder at different stage
  • Your context is unique: designer understanding devs, PM estimating complexity, founder prototyping, student building portfolio

The new learning system (15 minutes daily):

Step 1: Pick Your AI (all have generous free tiers)

  • ChatGPT, Claude, Google Gemini, Hugging Face Chat, Meta AI, DeepSeek
  • Don't let cost stop you - free versions work excellently

Step 2: Define Your Context (critical - be specific)

My React prompt: "I'm a founder trying to understand React and Next.js because my repos are built on them. I can read some code, but I fall asleep reading documentation or tutorials. I need to review code and make architectural decisions for my team. I'm not trying to write production code. I have 15 minutes per day. Please design daily debugging exercises for me."

My French prompt: "I'm learning French for work in Canada. I'm currently at A2 level (CLB 4-5). I have basic understanding but struggle with speaking, writing, and French accents. I have 30 minutes per day. Please give me daily reading and writing practice with corrections."

Must include: Role, current level, goal, time commitment, learning style preference

Step 3: Commit to daily practice

  • Doesn't matter if 1, 5, or 10 minutes - just do it daily around same time
  • Like Duolingo but personalized: your pace, your goals, infinite patience
  • I do 15 min React + 15 min French = 30 min total daily
  • On subway, before bed, whenever works

Step 4: Embrace failure

  • You will get things wrong - that's fine
  • AI explains differently each time until you understand
  • No shame in failing 6 times - it's AI not human, be shameless in learning
  • Don't pretend you understand to move on - make sure you actually get it

Step 5: Track progress

  • Every few days: "Based on my progress this week, what should I focus on next?"
  • Let AI adjust curriculum to your learning pattern
  • Creates structure that works FOR YOU, not generic structure for everyone

The French learning breakthrough:

  • Duolingo 10 min daily for 5 months = A2 level = saved $6-8K skipping 2 semesters
  • But still passive - completing exercises for things already knew
  • With ChatGPT: 10 daily vocab words with testing, paragraphs at exact level, 5 questions with corrections
  • AI predicts what I don't know and addresses proactively
  • "George, all 5 correct. However, punctuations wrong. Here's how to fix. In future if you want to say this, here's how."
  • Not just testing what I know - teaching what I'll need next

Why structure is a scam (sort of):

  • Everyone says "you need structure to learn effectively"
  • Truth: structure is valuable but YOUR structure is not THEIRS
  • Generic curriculums designed to sell courses, not optimize your learning
  • Real structure personalizes to: current level, goals, learning style, time availability, context

What this means for founders:

  • I'm founder not developer - don't need to write production code
  • Need to: review team's code, make architectural decisions, give implementation feedback, guide team
  • Traditional courses assume I want to become full-time developer - I don't
  • AI learning focuses on exactly what I need: understanding React state, debugging issues, reading codebase
  • No wasted time on syntax I'll never use or forcing through 500-page books

The fear of judgment problem:

  • In college: afraid to ask questions, everyone seemed so good at CS/math
  • Wanted to be "George who knows everything" - rather struggle silently than show weakness
  • Fear of professor/peer judgment stopped effective learning
  • With AI: fear is gone, no judgment, no embarrassment, just patient explanation
  • Revolutionary for learning

Template prompt for anything you want to learn: "I'm a [your role] trying to learn [skill] because [reason]. I'm...

  continue reading

46 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Copyright 2025 | Privacy Policy | Terms of Service | | Copyright
Listen to this show while you explore
Play