Courses › Course06
Course06 · LLMs and Generative AI
Large language models as a working material: how they are made, how to prompt and call them, how to ground them with retrieval, customize them, and go multimodal.
49 days 49 written 49 complete
Days 239-245 · The LLM Landscape 7/7 complete
- Day 239 How Large Language Models Are Trained complete
- Day 240 Pretraining, Fine-Tuning, and RLHF complete
- Day 241 The Model Landscape: Claude, GPT, Gemini, Llama complete
- Day 242 Open Weights versus Closed APIs complete
- Day 243 Tokens, Context Windows, and Sampling complete
- Day 244 Capabilities, Limits, and Hallucination complete
- Day 245 Benchmarking Models Yourself complete
Project: Model Comparison Study — Design a ten-task benchmark and compare two accessible models on it, documenting failure patterns and cost.
Days 246-252 · Prompt Engineering 7/7 complete
- Day 246 Prompting Fundamentals complete
- Day 247 System Prompts and Role Design complete
- Day 248 Few-Shot Examples and Chain of Thought complete
- Day 249 Structured Output: Getting Reliable JSON complete
- Day 250 Prompt Patterns and Templates complete
- Day 251 Prompt Injection and Safe Prompting complete
- Day 252 A Tested Prompt Library complete
Project: Reusable Prompt Library — Build a tested library of parameterized prompts for five recurring tasks, each with evaluation examples.
Days 253-259 · LLM APIs 7/7 complete
- Day 253 First Calls to the Claude API complete
- Day 254 The OpenAI-Compatible Ecosystem complete
- Day 255 Streaming Responses complete
- Day 256 Tool Use and Function Calling complete
- Day 257 Working with Images and Documents complete
- Day 258 Cost, Caching, and Rate Limits complete
- Day 259 Building a CLI Assistant complete
Project: Command-Line AI Assistant — Build a streaming CLI assistant with conversation memory, tool use, and a cost meter.
Days 260-266 · Embeddings and Vector Search 7/7 complete
- Day 260 What Embeddings Are complete
- Day 261 Semantic Similarity Search complete
- Day 262 Vector Databases complete
- Day 263 Chunking Strategies complete
- Day 264 Hybrid Search and Rerankers complete
- Day 265 Evaluating Retrieval Quality complete
- Day 266 Semantic Search over Your Own Notes complete
Project: Semantic Search Engine — Build semantic search over your own notes with embeddings, a vector store, and a retrieval-quality evaluation.
Days 267-273 · Retrieval-Augmented Generation 7/7 complete
- Day 267 The RAG Architecture complete
- Day 268 A Minimal RAG System from Scratch complete
- Day 269 RAG over PDFs and Messy Documents complete
- Day 270 Citations and Grounded Answers complete
- Day 271 Advanced RAG Patterns complete
- Day 272 Evaluating RAG Systems complete
- Day 273 A Documentation Assistant complete
Project: Documentation Q&A Bot — Build a RAG assistant over a real documentation set with citations and a measured answer-quality eval.
Days 274-280 · Customizing and Running Models 7/7 complete
- Day 274 Prompting versus RAG versus Fine-Tuning complete
- Day 275 Fine-Tuning with LoRA complete
- Day 276 Building Fine-Tuning Datasets complete
- Day 277 Running Local Models with Ollama complete
- Day 278 Quantized Inference and llama.cpp complete
- Day 279 Serving Open Models complete
- Day 280 Fine-Tune and Serve Your Own Model complete
Project: Local Fine-Tuned Model — Fine-tune a small open model with LoRA on a task dataset and serve it locally, comparing before and after.
Days 281-287 · Multimodal and Generative Media 7/7 complete
- Day 281 How Diffusion Models Generate Images complete
- Day 282 Image Generation in Practice complete
- Day 283 Speech: Recognition and Synthesis complete
- Day 284 Video and Music Generation complete
- Day 285 Multimodal Models complete
- Day 286 Generative AI Ethics and Copyright complete
- Day 287 Section Project: A Multimodal Application complete
Project: Section Project: Multimodal App — Build an application combining at least two modalities — for example, speech in, grounded text out, generated image alongside.