1 Learn To Work With AI & LLMs with Scott Kerr Demo 01:01 2 06:20 3 What is Prompt Engineering? 06:25 4 Why is Prompt Engineering Even a Thing? 08:32 5 04:03 6 Applied Prompt Engineering 04:25 7 Applied Prompt Engineering with NASA 09:30 8 Why is Prompt Engineering Important to You? 04:07 9 01:22 10 What I'm Using - Part 2 (OpenAI Playground) 04:03 11 Multi-Modality and Tools in LLMs 11:42 12 Getting Started with ChatGPT 01:40 13 04:09 14 01:12 15 01:56 16 Getting Started with Claude 04:28 17 02:14 18 Important Point #1 - Fundamental Truths About LLMs 02:59 19 Important Point #2 - Models are Non-Deterministic 04:04 20 Setting Up Your Replit Account 04:45 21 04:42 22 Building Our Snake Game - Part 1 06:13 23 Building Our Snake Game - Part 2 05:50 24 05:45 25 05:18 26 05:51 27 Thinking Like LLMs - Roll a Dice 06:57 28 22:14 29 07:39 30 Exercise: Visualize the LLM Architecture 03:57 31 09:58 32 Base Model vs. Assistant Model 07:07 33 Thinking Like LLMs - The Reversal Curse 05:15 34 Artificial General Intelligence (AGI) 05:29 35 Exercise: Use ChatGPT to Read the Research 04:48 36 06:06 37 Overview of Our Prompting Framework 03:31 38 04:34 39 Exercise: Get Hyped to Learn! 04:05 40 01:02 41 The System Message - Part 1 06:08 42 The System Message - Part 2 05:44 43 Exercise: Strengthen Your System Message 06:43 44 05:18 45 Context - The Context Window 09:22 46 Context - Lost in the Middle 11:27 47 08:43 48 Personas - Tone, Style and Voice 11:50 49 11:15 50 Thinking Like LLMs - Can GPT Keep a Secret? 04:46 51 Exercise: Get ChatGPT to Spill the Tea - Part 1 01:45 52 Exercise: Get ChatGPT to Spill the Tea - Part 2 01:43 53 Exercise: Get ChatGPT to Spill the Tea - Part 3 04:25 54 02:10 55 03:53 56 05:16 57 Exercise: Identify Delimiters 03:26 58 06:11 59 01:02 60 01:48 61 One Shot and Few Shot Prompting 09:49 62 Language Models Are Few-Shot Learners 03:49 63 02:24 64 Thinking Like LLMs - But Wait... 05:37 65 Chain-of-Thought Prompting - Part 1 05:25 66 Chain-of-Thought Prompting - Part 2 05:46 67 09:30 68 Exercise: Imposter Syndrome 02:57 69 07:33 70 06:03 71 The Setup - Context and Commands 05:43 72 12:21 73 The Instructions - Chain of Thought 03:52 74 The Instructions - Gamify 09:02 75 19:54 76 01:36 77 12:34 78 07:43 79 Exercise: Output an Excel File 02:31 80 Exercise: Make a Flowchart 04:02 81 Introduction to Guardrails and Jailbreaking 16:33 82 Jailbreak! (The DAN Prompt) 07:26 83 18:10 84 Prompt Injections - Part 1 09:37 85 Prompt Injections - Part 2 17:43 86 Thinking Like LLMs - Multi-Modal Injection 09:18 87 Leaking - Part 1 (Prompt Leaking) 08:36 88 Leaking - Part 2 (Data Leaking) 18:08 89 05:41 90 03:19 91 04:40 92 13:32 93 Thinking Like LLMs - Big vs Small 18:59 94 Challenge: Conduct Your Own Mechanistic Interpretability Research on Hallucinations 04:35 95 11:06 96 14:44 97 Introduction to Hyperparameters and the OpenAI Playground 03:16 98 10:26 99 04:09 100 Frequency and Presence Penalties 04:39 101 05:23 102 03:14 103 08:43 104 10:39 105 The Instruction Hierarchy 16:47 106 The Latest: Reasoning Models - Use of Developer Message 01:54 107 The Latest: Research To Prevent ChatGPT from Spilling the Tea 02:42 108 Replay: Multi-Modality and Tools in LLMs 11:42 109 09:07 110 Thinking Like LLMs - Attack of the (Voice) Clones 18:23 111 09:28 112 Tools & Function Calling - Part 1 10:30 113 Tools & Function Calling - Part 2 13:43 114 03:08 115 What Are Open Source LLMs and Why Are They Important? 06:51 116 Chatbot Arena Leaderboard 07:53 117 Battle of the Intelligence Tests 14:39 118 Exercise: Create Your Own Test Prompt (Totem) 01:36 119 02:38 120 Setting Up Your Own Model - Part 1 02:52 121 Setting Up Your Own Model - Part 2 09:39 122 01:07 123 10:51 124 Chain of Density Prompting 18:17 125 07:14 126 08:39 127 Prompt Chaining - Programmatic Visualization 17:41 128 Exercise: Prompt Chaining - Customer Support 22:34 129 Thinking Like LLMs - Dark Magic 09:58 130 XML Tags - There's More Than Meets The Eye! 09:18 131 Emotional Stimuli - Part 1 18:37 132 Emotional Stimuli - Part 2 04:43 133 Emotional Stimuli - Part 3 07:18 134 13:45 135 21:35 136 16:48 137 Applied Prompt Engineering with CRISPR - Part 1 13:41 138 Applied Prompt Engineering with CRISPR - Part 2 14:53 139 Tree of Thoughts - Part 1 14:57 140 Tree of Thoughts - Part 2 04:57 141 Tree of Thoughts - Part 3 11:34 142 Tree of Thoughts - Part 4 22:12 143 Tree of Thoughts - Part 5 12:27 144 03:41 145 Replay: Chain-of-Thought Prompting - Part 1 05:25 146 Replay: Chain-of-Thought Prompting - Part 2 05:46 147 Introduction to Reasoning Models 09:24 148 First Contact with Reasoning 16:48 149 12:15 150 Setting Up Our Open Source Reasoning Model 05:52 151 A Reasoning Model's Real Thoughts - Part 1 05:16 152 A Reasoning Model's Real Thoughts - Part 2 08:41 153 Thinking Like LLMs - Breaking The Chains 12:16 154 What Are Reasoning Models Good For? 13:33 155 10:08 156 Prompt Engineering for Reasoning Models 07:28 157 18:20 158 Thinking Like LLMs: Cats Are...Confusing? - Part 1 10:22 159 Thinking Like LLMs: Cats Are...Confusing? - Part 2 07:11 160 Reinforcement Learning - The Problem 06:21 161 Reinforcement Learning - How It Works 15:03 162 04:19 163 07:47 164 Reinforcement Learning from Human Feedback (RLHF) 16:07 165 Reinforcement Learning for Reasoning Models - Let's Verify Step-By-Step 06:36 166 Reinforcement Learning for Reasoning Models - Process Reward Model 09:28 167 07:41 168 13:12 169 12:41 170 Are Reasoning Models Lying To You? - Part 1 11:08 171 Are Reasoning Models Lying To You? - Part 2 02:43 172 Are Reasoning Models Lying To You? - Part 3 07:54 173 Are Reasoning Models Lying To You? - Part 4 02:52 174 Introduction to Prompt Testing 08:33 175 The Importance of Prompt Testing 04:33 176 Thinking Like LLMs - Schrodinger's Prompt 19:18 177 16:50 178 07:01 179 11:29 180 Deep Dive: MMLU Benchmark 14:20 181 Prompt Tests vs. Model Benchmarks? 04:32 182 18:11 183 Evaluating Results - Human Judge 07:04 184 Evaluating Results - Code Judge 11:24 185 Evaluating Results - AI Judge 22:07 186 Deep Dive: LLMs as a Judge - Biases 22:12 187 Deep Dive: LLMs as a Judge - Prompts 13:02 188 Thinking Like LLMs - Ex Post Facto Reasoning 11:47 189 06:02 190 Introduction to PromptFoo 06:11 191 Our Prompt Testing Framework 04:46 192 Our 1st Prompt Test - The Setup 23:10 193 Our 1st Prompt Test - The Results 10:21 194 Our 2nd Prompt Test - The Setup 11:41 195 Our 2nd Prompt Test - The Results 07:39 196 Our 3rd Prompt Test - The Setup 25:37 197 Our 3rd Prompt Test - The Results 08:22 198 Our 4th Prompt Test - The Setup 25:59 199 Our 4th Prompt Test - The Results 13:12 200 Our 5th Prompt Test - The Setup 24:32 201 Our 5th Prompt Test - The Results 12:23 202 Do You Realize What Just Happened? 04:26 203 Introduction - Through The Looking Glass... 08:41 204 Applied Prompt Engineering with The Turing Test 07:34 205 Mechanistic Interpretability - Part 1 13:25 206 Mechanistic Interpretability - Part 2 21:00 207 Scaling Laws - Model Size 12:56 208 Scaling Laws - Dataset Size 08:05 209 Scaling Laws - Training Compute 11:50 210 01:18 211 Setup Demo: Getting Your API Key 02:24 212 Setup Demo: Downloading AutoGPT 01:04 213 Setup Demo: Installing Docker 03:27 214 Launching Your Autonomous Agent - Part 1 03:26 215 Launching Your Autonomous Agent - Part 2 01:22 216 It's Aliiiiiive! Running Your Autonomous Agent 04:52 217 Task 1: Hello World - Your First Website 16:18 218 Task 2: Python Program - Palindrome Checker 08:41