Unlock the power of Generative AI: From understanding its principles to utilizing its power
summary
Generative models train on web-scale corpora (trillions of tokens) and scale to 340 billion to 1.7 trillion parameters, use Transformers from the 2017 “Attention is All You Need” paper, and power apps like ChatGPT (100M weekly users); Google announces Gemini Ultra >90% on MMLU. Practical techniques shown are role/context/task/example prompting and chain-of-thought, plus tuning temperature 0–1 (0.0–0.3 factual, 0.7–1 creative); prompt tuning supplies context without retraining the model.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 0:25What is AI
- 2:47What is ML
- 5:37Why are generative models important
- 7:59Gemini Models
- 10:03Prompt Engineering
- 14:57Temperature
related talks
15mHarnessing the Power of Generative AI for Intelligent Applications
41mThe Unreliable Computer Revolution - Embracing the Double-Edged Sword of GenAI
19mLet's Talk GenAI
11mapproach to generative AI
17mGenerative AI: Keeping it real
32mHow generative AI is Changing the way people interact with computers
49mUsing Generative AI to Strengthen & Accelerate Learning
49mGenerative AI: Concepts, Tools, and Applications for Data Professionals