Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Reasoning Models: The Amazing and Terrifying New Era of AI Thinking
Reasoning Models
Introduction (3:40)
A Note On The Next Two Lessons
Replay: Chain-of-Thought Prompting - Part 1 (5:24)
Replay: Chain-of-Thought Prompting - Part 2 (5:45)
Introduction to Reasoning Models (9:23)
First Contact with Reasoning (16:47)
Secrets and Lies! (12:14)
Setting Up Our Open Source Reasoning Model (5:51)
A Reasoning Model's Real Thoughts - Part 1 (5:15)
A Reasoning Model's Real Thoughts - Part 2 (8:40)
Exercise: Compare Reasoning Style of Different Models
Reasoning & The Context Window
Thinking Like LLMs - Breaking The Chains (12:15)
What Are Reasoning Models Good For? (The Generator-Verifier Gap) (13:32)
Exercise: Determine GVG (10:07)
Prompt Engineering for Reasoning Models (7:27)
Context Engineering (18:19)
Thinking Like LLMs: Cats Are...Confusing? - Part 1 (10:21)
Thinking Like LLMs: Cats Are...Confusing? - Part 2 (7:10)
Reinforcement Learning - The Problem (6:20)
Reinforcement Learning - How It Works (15:02)
Exercise: Code Your Own Maze Game
RL Environments (Soccer) (4:18)
RL Environments (Go) (7:46)
-- Qualitative vs. Quantitative
Reinforcement Learning from Human Feedback (RLHF) (16:06)
Reinforcement Learning for Reasoning Models - Let's Verify Step-By-Step (6:36)
Reinforcement Learning for Reasoning Models - Process Reward Model (9:27)
PRM800K Introduction (7:41)
PRM800K Deep Dive (13:11)
Test-Time Compute (12:40)
Are Reasoning Models Lying To You? - Part 1 (11:07)
Are Reasoning Models Lying To You? - Part 2 (2:42)
Are Reasoning Models Lying To You? - Part 3 (7:53)
Are Reasoning Models Lying To You? - Part 4 (2:51)
Mandatory Homework: The Thinking Game
Challenge - Build Your Third Game (Flappy Bird)
Challenge Instructions
The Flappy Bird Hall of Fame
Reinforcement Learning for Reasoning Models - Process Reward Model
This lecture is available exclusively for ZTM Academy members.
If you're already a member,
you'll need to login
.
Join ZTM To Unlock All Lectures