Foundation Models vs Task-Specific Models

Limitations, Bias, and Ethics of LLMs

Context Window and Its Limitations

Zero-Shot, One-Shot, Few-Shot Learning

Prompting and Prompt Engineering Basics

Reinforcement Learning from Human Feedback

Fine-Tuning and Instruction Tuning

Pretraining on Large Text Corpora

Next-Token Prediction and Autoregressive Generation

Embeddings in LLMs

Tokens and Tokenization in LLMs

Self-Attention Mechanism Intuition

The Transformer Architecture Overview

What a Large Language Model Is

Generative vs Discriminative AI

Real-World Applications of LLMs

Generative Models Beyond Text

Model Parameters and Scaling Laws

Retrieval-Augmented Generation (RAG)

Hallucinations and Factual Reliability

Decoding: Temperature, Top-k, Top-p