AI Engineering from Scratch
0% Completed
Phase 0: Setup And Tooling
Phase 0 Introduction
Video - 00:00:00 mins
Phase 0: Dev Environment check
Quiz
Phase 0: Git & Collaboration check
Quiz
Phase 0: GPU Setup & Cloud check
Quiz
Phase 0: APIs & Keys check
Quiz
Phase 0: Jupyter Notebooks check
Quiz
Phase 0: Python Environments check
Quiz
Phase 0: Docker for AI check
Quiz
Phase 0: Editor Setup check
Quiz
Phase 0: Data Management check
Quiz
Phase 0: Terminal & Shell check
Quiz
Phase 0: Linux for AI check
Quiz
Phase 0: Debugging and Profiling check
Quiz
Phase 0: Python for AI Engineering check
Quiz
Dev Environment
Video - 00:00:00 mins
Git & Collaboration
Video - 00:00:00 mins
GPU Setup & Cloud
Video - 00:00:00 mins
APIs & Keys
Video - 00:00:00 mins
Jupyter Notebooks
Video - 00:00:00 mins
Python Environments
Video - 00:00:00 mins
Docker for AI
Video - 00:00:00 mins
Editor Setup
Video - 00:00:00 mins
Data Management
Video - 00:00:00 mins
Terminal & Shell
Video - 00:00:00 mins
Linux for AI
Video - 00:00:00 mins
Debugging and Profiling
Video - 00:00:00 mins
Python for AI Engineering
Video - 00:00:00 mins
Phase 0 Project
Video - 00:00:00 mins
Phase 1: Math Foundations
Phase 1 Introduction
Video - 00:00:00 mins
Phase 1: Linear Algebra Intuition check
Quiz
Phase 1: Vectors, Matrices & Operations check
Quiz
Phase 1: Matrix Transformations check
Quiz
Phase 1: Calculus for Machine Learning check
Quiz
Phase 1: Chain Rule & Automatic Differentiation check
Quiz
Phase 1: Probability and Distributions check
Quiz
Phase 1: Bayes' Theorem check
Quiz
Phase 1: Optimization check
Quiz
Phase 1: Information Theory check
Quiz
Phase 1: Dimensionality Reduction check
Quiz
Phase 1: Singular Value Decomposition check
Quiz
Phase 1: Tensor Operations check
Quiz
Phase 1: Numerical Stability check
Quiz
Phase 1: Norms and Distances check
Quiz
Phase 1: Statistics for Machine Learning check
Quiz
Phase 1: Sampling Methods check
Quiz
Phase 1: Linear Systems check
Quiz
Phase 1: Convex Optimization check
Quiz
Phase 1: Complex Numbers for AI check
Quiz
Phase 1: The Fourier Transform check
Quiz
Phase 1: Graph Theory for Machine Learning check
Quiz
Phase 1: Stochastic Processes check
Quiz
Phase 1: Vectors, Matrices & Operations check
Quiz
Phase 1: Chain Rule & Automatic Differentiation check
Quiz
Linear Algebra Intuition
Video - 00:00:00 mins
Vectors, Matrices & Operations
Video - 00:00:00 mins
Matrix Transformations
Video - 00:00:00 mins
Calculus for Machine Learning
Video - 00:00:00 mins
Chain Rule & Automatic Differentiation
Video - 00:00:00 mins
Probability and Distributions
Video - 00:00:00 mins
Bayes' Theorem
Video - 00:00:00 mins
Optimization
Video - 00:00:00 mins
Information Theory
Video - 00:00:00 mins
Dimensionality Reduction
Video - 00:00:00 mins
Singular Value Decomposition
Video - 00:00:00 mins
Tensor Operations
Video - 00:00:00 mins
Numerical Stability
Video - 00:00:00 mins
Norms and Distances
Video - 00:00:00 mins
Statistics for Machine Learning
Video - 00:00:00 mins
Sampling Methods
Video - 00:00:00 mins
Linear Systems
Video - 00:00:00 mins
Convex Optimization
Video - 00:00:00 mins
Complex Numbers for AI
Video - 00:00:00 mins
The Fourier Transform
Video - 00:00:00 mins
Graph Theory for Machine Learning
Video - 00:00:00 mins
Stochastic Processes
Video - 00:00:00 mins
Phase 1 Project
Video - 00:00:00 mins
Phase 2: Ml Fundamentals
Phase 2 Introduction
Video - 00:00:00 mins
Phase 2: What Is Machine Learning check
Quiz
Phase 2: Linear Regression check
Quiz
Phase 2: Logistic Regression check
Quiz
Phase 2: Decision Trees and Random Forests check
Quiz
Phase 2: Support Vector Machines check
Quiz
Phase 2: K-Nearest Neighbors and Distances check
Quiz
Phase 2: Unsupervised Learning check
Quiz
Phase 2: Feature Engineering & Selection check
Quiz
Phase 2: Model Evaluation check
Quiz
Phase 2: Bias-Variance Tradeoff check
Quiz
Phase 2: Ensemble Methods check
Quiz
Phase 2: Hyperparameter Tuning check
Quiz
Phase 2: ML Pipelines check
Quiz
Phase 2: Naive Bayes check
Quiz
Phase 2: Time Series Fundamentals check
Quiz
Phase 2: Anomaly Detection check
Quiz
Phase 2: Handling Imbalanced Data check
Quiz
Phase 2: Feature Selection check
Quiz
Phase 2: ML System Design — From Problem to Deployed Model check
Quiz
Phase 2: Monitoring Models in Production — Data Drift and Concept Drift check
Quiz
Phase 2: Feature Stores and Training-Serving Skew check
Quiz
Phase 2: Feature Engineering & Selection check
Quiz
What Is Machine Learning
Video - 00:00:00 mins
Linear Regression
Video - 00:00:00 mins
Logistic Regression
Video - 00:00:00 mins
Decision Trees and Random Forests
Video - 00:00:00 mins
Support Vector Machines
Video - 00:00:00 mins
K-Nearest Neighbors and Distances
Video - 00:00:00 mins
Unsupervised Learning
Video - 00:00:00 mins
Feature Engineering & Selection
Video - 00:00:00 mins
Model Evaluation
Video - 00:00:00 mins
Bias-Variance Tradeoff
Video - 00:00:00 mins
Ensemble Methods
Video - 00:00:00 mins
Hyperparameter Tuning
Video - 00:00:00 mins
ML Pipelines
Video - 00:00:00 mins
Naive Bayes
Video - 00:00:00 mins
Time Series Fundamentals
Video - 00:00:00 mins
Anomaly Detection
Video - 00:00:00 mins
Handling Imbalanced Data
Video - 00:00:00 mins
Feature Selection
Video - 00:00:00 mins
ML System Design — From Problem to Deployed Model
Video - 00:00:00 mins
Monitoring Models in Production — Data Drift and Concept Drift
Video - 00:00:00 mins
Feature Stores and Training-Serving Skew
Video - 00:00:00 mins
Phase 2 Project
Video - 00:00:00 mins
Phase 3: Deep Learning Core
Phase 3 Introduction
Video - 00:00:00 mins
Phase 3: The Perceptron check
Quiz
Phase 3: Multi-Layer Networks and Forward Pass check
Quiz
Phase 3: Backpropagation from Scratch check
Quiz
Phase 3: Activation Functions check
Quiz
Phase 3: Loss Functions check
Quiz
Phase 3: Optimizers check
Quiz
Phase 3: Regularization check
Quiz
Phase 3: Weight Initialization and Training Stability check
Quiz
Phase 3: Learning Rate Schedules and Warmup check
Quiz
Phase 3: Build Your Own Mini Framework check
Quiz
Phase 3: Introduction to PyTorch check
Quiz
Phase 3: Introduction to JAX check
Quiz
Phase 3: Debugging Neural Networks check
Quiz
The Perceptron
Video - 00:00:00 mins
Multi-Layer Networks and Forward Pass
Video - 00:00:00 mins
Backpropagation from Scratch
Video - 00:00:00 mins
Activation Functions
Video - 00:00:00 mins
Loss Functions
Video - 00:00:00 mins
Optimizers
Video - 00:00:00 mins
Regularization
Video - 00:00:00 mins
Weight Initialization and Training Stability
Video - 00:00:00 mins
Learning Rate Schedules and Warmup
Video - 00:00:00 mins
Build Your Own Mini Framework
Video - 00:00:00 mins
Introduction to PyTorch
Video - 00:00:00 mins
Introduction to JAX
Video - 00:00:00 mins
Debugging Neural Networks
Video - 00:00:00 mins
Phase 3 Project
Video - 00:00:00 mins
Phase 4: Computer Vision
Phase 4: Diffusion Transformers & Rectified Flow check
Quiz
Phase 4: SAM 3 & Open-Vocabulary Segmentation check
Quiz
Phase 4: Monocular Depth & Geometry Estimation check
Quiz
Phase 4: Multi-Object Tracking & Video Memory check
Quiz
Phase 4: World Models & Video Diffusion check
Quiz
Phase 4 Introduction
Video - 00:00:00 mins
Phase 4: Image Fundamentals — Pixels, Channels, Color Spaces check
Quiz
Phase 4: Convolutions from Scratch check
Quiz
Phase 4: CNNs — LeNet to ResNet check
Quiz
Phase 4: Image Classification check
Quiz
Phase 4: Transfer Learning & Fine-Tuning check
Quiz
Phase 4: Object Detection — YOLO from Scratch check
Quiz
Phase 4: Semantic Segmentation — U-Net check
Quiz
Phase 4: Instance Segmentation — Mask R-CNN check
Quiz
Phase 4: Image Generation — GANs check
Quiz
Phase 4: Image Generation — Diffusion Models check
Quiz
Phase 4: Stable Diffusion — Architecture & Fine-Tuning check
Quiz
Phase 4: Video Understanding — Temporal Modeling check
Quiz
Phase 4: 3D Vision — Point Clouds & NeRFs check
Quiz
Phase 4: Vision Transformers (ViT) check
Quiz
Phase 4: Real-Time Vision — Edge Deployment check
Quiz
Phase 4: Build a Complete Vision Pipeline — Capstone check
Quiz
Phase 4: Self-Supervised Vision — SimCLR, DINO, MAE check
Quiz
Phase 4: Open-Vocabulary Vision — CLIP check
Quiz
Phase 4: OCR & Document Understanding check
Quiz
Phase 4: Image Retrieval & Metric Learning check
Quiz
Phase 4: Keypoint Detection & Pose Estimation check
Quiz
Phase 4: 3D Gaussian Splatting from Scratch check
Quiz
Phase 4: Diffusion Transformers & Rectified Flow check
Quiz
Phase 4: SAM 3 & Open-Vocabulary Segmentation check
Quiz
Phase 4: Vision-Language Models — The ViT-MLP-LLM Pattern check
Quiz
Phase 4: Monocular Depth & Geometry Estimation check
Quiz
Phase 4: Multi-Object Tracking & Video Memory check
Quiz
Phase 4: World Models & Video Diffusion check
Quiz
Phase 4: Transfer Learning & Fine-Tuning check
Quiz
Phase 4: Stable Diffusion — Architecture & Fine-Tuning check
Quiz
Phase 4: 3D Vision — Point Clouds & NeRFs check
Quiz
Phase 4: OCR & Document Understanding check
Quiz
Phase 4: Image Retrieval & Metric Learning check
Quiz
Phase 4: Keypoint Detection & Pose Estimation check
Quiz
Image Fundamentals — Pixels, Channels, Color Spaces
Video - 00:00:00 mins
Convolutions from Scratch
Video - 00:00:00 mins
CNNs — LeNet to ResNet
Video - 00:00:00 mins
Image Classification
Video - 00:00:00 mins
Transfer Learning & Fine-Tuning
Video - 00:00:00 mins
Object Detection — YOLO from Scratch
Video - 00:00:00 mins
Semantic Segmentation — U-Net
Video - 00:00:00 mins
Instance Segmentation — Mask R-CNN
Video - 00:00:00 mins
Image Generation — GANs
Video - 00:00:00 mins
Image Generation — Diffusion Models
Video - 00:00:00 mins
Stable Diffusion — Architecture & Fine-Tuning
Video - 00:00:00 mins
Video Understanding — Temporal Modeling
Video - 00:00:00 mins
3D Vision — Point Clouds & NeRFs
Video - 00:00:00 mins
Vision Transformers (ViT)
Video - 00:00:00 mins
Real-Time Vision — Edge Deployment
Video - 00:00:00 mins
Build a Complete Vision Pipeline — Capstone
Video - 00:00:00 mins
Self-Supervised Vision — SimCLR, DINO, MAE
Video - 00:00:00 mins
Open-Vocabulary Vision — CLIP
Video - 00:00:00 mins
OCR & Document Understanding
Video - 00:00:00 mins
Image Retrieval & Metric Learning
Video - 00:00:00 mins
Keypoint Detection & Pose Estimation
Video - 00:00:00 mins
3D Gaussian Splatting from Scratch
Video - 00:00:00 mins
Diffusion Transformers & Rectified Flow
Video - 00:00:00 mins
SAM 3 & Open-Vocabulary Segmentation
Video - 00:00:00 mins
Vision-Language Models — The ViT-MLP-LLM Pattern
Video - 00:00:00 mins
Monocular Depth & Geometry Estimation
Video - 00:00:00 mins
Multi-Object Tracking & Video Memory
Video - 00:00:00 mins
World Models & Video Diffusion
Video - 00:00:00 mins
Phase 4 Project
Video - 00:00:00 mins
Phase 5: Nlp Foundations To Advanced
Phase 5: Topic Modeling — LDA and BERTopic check
Quiz
Phase 5: Text Generation Before Transformers — N-gram Language Models check
Quiz
Phase 5: Chatbots — Rule-Based to Neural to LLM Agents check
Quiz
Phase 5: Structured Outputs & Constrained Decoding check
Quiz
Phase 5: Multilingual NLP check
Quiz
Phase 5: Entity Linking & Disambiguation check
Quiz
Phase 5: Relation Extraction & Knowledge Graph Construction check
Quiz
Phase 5: Subword Tokenization — BPE, WordPiece, Unigram, SentencePiece check
Quiz
Phase 5: Structured Outputs & Constrained Decoding check
Quiz
Phase 5: Natural Language Inference — Textual Entailment check
Quiz
Phase 5: Embedding Models — The 2026 Deep Dive check
Quiz
Phase 5: Chunking Strategies for RAG check
Quiz
Phase 5: Coreference Resolution check
Quiz
Phase 5: Entity Linking & Disambiguation check
Quiz
Phase 5: Relation Extraction & Knowledge Graph Construction check
Quiz
Phase 5: LLM Evaluation — RAGAS, DeepEval, G-Eval check
Quiz
Phase 5: Long-Context Evaluation — NIAH, RULER, LongBench, MRCR check
Quiz
Phase 5: Dialogue State Tracking check
Quiz
Phase 5 Introduction
Video - 00:00:00 mins
Phase 5: Text Processing — Tokenization, Stemming, Lemmatization check
Quiz
Phase 5: Bag of Words, TF-IDF, and Text Representation check
Quiz
Phase 5: Word Embeddings — Word2Vec from Scratch check
Quiz
Phase 5: GloVe, FastText, and Subword Embeddings check
Quiz
Phase 5: Sentiment Analysis check
Quiz
Phase 5: Named Entity Recognition check
Quiz
Phase 5: POS Tagging and Syntactic Parsing check
Quiz
Phase 5: CNNs and RNNs for Text check
Quiz
Phase 5: Sequence-to-Sequence Models check
Quiz
Phase 5: Attention Mechanism — The Breakthrough check
Quiz
Phase 5: Machine Translation check
Quiz
Phase 5: Text Summarization check
Quiz
Phase 5: Question Answering Systems check
Quiz
Phase 5: Information Retrieval and Search check
Quiz
Text Processing — Tokenization, Stemming, Lemmatization
Video - 00:00:00 mins
Bag of Words, TF-IDF, and Text Representation
Video - 00:00:00 mins
Word Embeddings — Word2Vec from Scratch
Video - 00:00:00 mins
GloVe, FastText, and Subword Embeddings
Video - 00:00:00 mins
Sentiment Analysis
Video - 00:00:00 mins
Named Entity Recognition
Video - 00:00:00 mins
POS Tagging and Syntactic Parsing
Video - 00:00:00 mins
CNNs and RNNs for Text
Video - 00:00:00 mins
Sequence-to-Sequence Models
Video - 00:00:00 mins
Attention Mechanism — The Breakthrough
Video - 00:00:00 mins
Machine Translation
Video - 00:00:00 mins
Text Summarization
Video - 00:00:00 mins
Question Answering Systems
Video - 00:00:00 mins
Information Retrieval and Search
Video - 00:00:00 mins
Topic Modeling — LDA and BERTopic
Video - 00:00:00 mins
Text Generation Before Transformers — N-gram Language Models
Video - 00:00:00 mins
Chatbots — Rule-Based to Neural to LLM Agents
Video - 00:00:00 mins
Multilingual NLP
Video - 00:00:00 mins
Subword Tokenization — BPE, WordPiece, Unigram, SentencePiece
Video - 00:00:00 mins
Structured Outputs & Constrained Decoding
Video - 00:00:00 mins
Natural Language Inference — Textual Entailment
Video - 00:00:00 mins
Embedding Models — The 2026 Deep Dive
Video - 00:00:00 mins
Chunking Strategies for RAG
Video - 00:00:00 mins
Coreference Resolution
Video - 00:00:00 mins
Entity Linking & Disambiguation
Video - 00:00:00 mins
Relation Extraction & Knowledge Graph Construction
Video - 00:00:00 mins
LLM Evaluation — RAGAS, DeepEval, G-Eval
Video - 00:00:00 mins
Long-Context Evaluation — NIAH, RULER, LongBench, MRCR
Video - 00:00:00 mins
Dialogue State Tracking
Video - 00:00:00 mins
Phase 5 Project
Video - 00:00:00 mins
Phase 6: Speech And Audio
Phase 6 Introduction
Video - 00:00:00 mins
Audio Fundamentals — Waveforms, Sampling, Fourier Transform
Video - 00:00:00 mins
Spectrograms, Mel Scale & Audio Features
Video - 00:00:00 mins
Audio Classification — From k-NN on MFCCs to AST and BEATs
Video - 00:00:00 mins
Speech Recognition (ASR) — CTC, RNN-T, Attention
Video - 00:00:00 mins
Whisper — Architecture & Fine-Tuning
Video - 00:00:00 mins
Speaker Recognition & Verification
Video - 00:00:00 mins
Text-to-Speech (TTS) — From Tacotron to F5 and Kokoro
Video - 00:00:00 mins
Voice Cloning & Voice Conversion
Video - 00:00:00 mins
Music Generation — MusicGen, Stable Audio, Suno, and the Licensing Earthquake
Video - 00:00:00 mins
Audio-Language Models — Qwen2.5-Omni, Audio Flamingo, GPT-4o Audio
Video - 00:00:00 mins
Real-Time Audio Processing
Video - 00:00:00 mins
Build a Voice Assistant Pipeline — The Phase 6 Capstone
Video - 00:00:00 mins
Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC and the Semantic-Acoustic Split
Video - 00:00:00 mins
Voice Activity Detection & Turn-Taking — Silero, Cobra, and the Flush Trick
Video - 00:00:00 mins
Streaming Speech-to-Speech — Moshi, Hibiki, and Full-Duplex Dialogue
Video - 00:00:00 mins
Voice Anti-Spoofing & Audio Watermarking — ASVspoof 5, AudioSeal, WaveVerify
Video - 00:00:00 mins
Audio Evaluation — WER, MOS, UTMOS, MMAU, FAD, and the Open Leaderboards
Video - 00:00:00 mins
Phase 6 Project
Video - 00:00:00 mins
Phase 7: Transformers Deep Dive
Phase 7 Introduction
Video - 00:00:00 mins
Phase 7: Self-Attention from Scratch check
Quiz
Why Transformers — The Problems with RNNs
Video - 00:00:00 mins
Self-Attention from Scratch
Video - 00:00:00 mins
Multi-Head Attention
Video - 00:00:00 mins
Positional Encoding — Sinusoidal, RoPE, ALiBi
Video - 00:00:00 mins
The Full Transformer — Encoder + Decoder
Video - 00:00:00 mins
BERT — Masked Language Modeling
Video - 00:00:00 mins
GPT — Causal Language Modeling
Video - 00:00:00 mins
T5, BART — Encoder-Decoder Models
Video - 00:00:00 mins
Vision Transformers (ViT)
Video - 00:00:00 mins
Audio Transformers — Whisper Architecture
Video - 00:00:00 mins
Mixture of Experts (MoE)
Video - 00:00:00 mins
KV Cache, Flash Attention & Inference Optimization
Video - 00:00:00 mins
Scaling Laws
Video - 00:00:00 mins
Build a Transformer from Scratch — The Capstone
Video - 00:00:00 mins
Attention Variants — Sliding Window, Sparse, Differential
Video - 00:00:00 mins
Speculative Decoding — Draft, Verify, Repeat
Video - 00:00:00 mins
Phase 7 Project
Video - 00:00:00 mins
Phase 8: Generative Ai
Phase 8 Introduction
Video - 00:00:00 mins
Generative Models — Taxonomy & History
Video - 00:00:00 mins
Autoencoders & Variational Autoencoders (VAE)
Video - 00:00:00 mins
GANs — Generator vs Discriminator
Video - 00:00:00 mins
Conditional GANs & Pix2Pix
Video - 00:00:00 mins
StyleGAN
Video - 00:00:00 mins
Diffusion Models — DDPM from Scratch
Video - 00:00:00 mins
Latent Diffusion & Stable Diffusion
Video - 00:00:00 mins
ControlNet, LoRA & Conditioning
Video - 00:00:00 mins
Inpainting, Outpainting & Image Editing
Video - 00:00:00 mins
Video Generation
Video - 00:00:00 mins
Audio Generation
Video - 00:00:00 mins
3D Generation
Video - 00:00:00 mins
Flow Matching & Rectified Flows
Video - 00:00:00 mins
Evaluation — FID, CLIP Score, Human Preference
Video - 00:00:00 mins
Visual Autoregressive Modeling (VAR): Next-Scale Prediction
Video - 00:00:00 mins
Phase 8 Project
Video - 00:00:00 mins
Phase 9: Reinforcement Learning
Phase 9 Introduction
Video - 00:00:00 mins
MDPs, States, Actions & Rewards
Video - 00:00:00 mins
Dynamic Programming — Policy Iteration & Value Iteration
Video - 00:00:00 mins
Monte Carlo Methods — Learning from Complete Episodes
Video - 00:00:00 mins
Temporal Difference — Q-Learning & SARSA
Video - 00:00:00 mins
Deep Q-Networks (DQN)
Video - 00:00:00 mins
Policy Gradient — REINFORCE from Scratch
Video - 00:00:00 mins
Actor-Critic — A2C and A3C
Video - 00:00:00 mins
Proximal Policy Optimization (PPO)
Video - 00:00:00 mins
Reward Modeling & RLHF
Video - 00:00:00 mins
Multi-Agent RL
Video - 00:00:00 mins
Sim-to-Real Transfer
Video - 00:00:00 mins
RL for Games — AlphaZero, MuZero, and the LLM-Reasoning Era
Video - 00:00:00 mins
Phase 9 Project
Video - 00:00:00 mins
Phase 10: Llms From Scratch
Phase 10 Introduction
Video - 00:00:00 mins
Phase 10: Tokenizers: BPE, WordPiece, SentencePiece check
Quiz
Phase 10: Building a Tokenizer from Scratch check
Quiz
Phase 10: Data Pipelines for Pre-Training check
Quiz
Phase 10: Pre-Training a Mini GPT (124M Parameters) check
Quiz
Phase 10: Scaling: Distributed Training, FSDP, DeepSpeed check
Quiz
Phase 10: Instruction Tuning (SFT) check
Quiz
Phase 10: RLHF: Reward Model + PPO check
Quiz
Phase 10: DPO: Direct Preference Optimization check
Quiz
Phase 10: Evaluation: Benchmarks, Evals, LM Harness check
Quiz
Phase 10: Quantization: Making Models Fit check
Quiz
Phase 10: Inference Optimization check
Quiz
Tokenizers: BPE, WordPiece, SentencePiece
Video - 00:00:00 mins
Building a Tokenizer from Scratch
Video - 00:00:00 mins
Data Pipelines for Pre-Training
Video - 00:00:00 mins
Pre-Training a Mini GPT (124M Parameters)
Video - 00:00:00 mins
Scaling: Distributed Training, FSDP, DeepSpeed
Video - 00:00:00 mins
Instruction Tuning (SFT)
Video - 00:00:00 mins
RLHF: Reward Model + PPO
Video - 00:00:00 mins
DPO: Direct Preference Optimization
Video - 00:00:00 mins
Constitutional AI and Self-Improvement
Video - 00:00:00 mins
Evaluation: Benchmarks, Evals, LM Harness
Video - 00:00:00 mins
Quantization: Making Models Fit
Video - 00:00:00 mins
Inference Optimization
Video - 00:00:00 mins
Building a Complete LLM Pipeline
Video - 00:00:00 mins
Open Models: Architecture Walkthroughs
Video - 00:00:00 mins
Speculative Decoding and EAGLE-3
Video - 00:00:00 mins
Differential Attention (V2)
Video - 00:00:00 mins
Native Sparse Attention (DeepSeek NSA)
Video - 00:00:00 mins
Multi-Token Prediction (MTP)
Video - 00:00:00 mins
DualPipe Parallelism
Video - 00:00:00 mins
DeepSeek-V3 Architecture Walkthrough
Video - 00:00:00 mins
Jamba — Hybrid SSM-Transformer
Video - 00:00:00 mins
Async and Hogwild! Inference
Video - 00:00:00 mins
Speculative Decoding and EAGLE
Video - 00:00:00 mins
Gradient Checkpointing and Activation Recomputation
Video - 00:00:00 mins
Phase 10 Project
Video - 00:00:00 mins
Phase 11: Llm Engineering
Phase 11: Prompt Engineering: Techniques & Patterns check
Quiz
Phase 11: Embeddings & Vector Representations check
Quiz
Phase 11: Fine-Tuning with LoRA & QLoRA check
Quiz
Phase 11: Function Calling & Tool Use check
Quiz
Phase 11: Evaluation & Testing LLM Applications check
Quiz
Phase 11: Caching, Rate Limiting & Cost Optimization check
Quiz
Phase 11: Guardrails, Safety & Content Filtering check
Quiz
Phase 11 Introduction
Video - 00:00:00 mins
Phase 11: Prompt Engineering: Techniques & Patterns check
Quiz
Phase 11: Few-Shot, Chain-of-Thought, Tree-of-Thought check
Quiz
Phase 11: Structured Outputs: JSON, Schema Validation, Constrained Decoding check
Quiz
Phase 11: Embeddings & Vector Representations check
Quiz
Phase 11: Context Engineering: Windows, Budgets, Memory, and Retrieval check
Quiz
Phase 11: RAG (Retrieval-Augmented Generation) check
Quiz
Phase 11: Advanced RAG (Chunking, Reranking, Hybrid Search) check
Quiz
Phase 11: Fine-Tuning with LoRA & QLoRA check
Quiz
Phase 11: Function Calling & Tool Use check
Quiz
Phase 11: Evaluation & Testing LLM Applications check
Quiz
Phase 11: Caching, Rate Limiting & Cost Optimization check
Quiz
Phase 11: Guardrails, Safety & Content Filtering check
Quiz
Phase 11: Building a Production LLM Application check
Quiz
Phase 11: Model Context Protocol (MCP) check
Quiz
Phase 11: Prompt Caching and Context Caching check
Quiz
Phase 11: Agent State Machines — Graphs, Nodes, Checkpoints check
Quiz
Phase 11: Agent Framework Tradeoffs — Graph, Role, and Actor Orchestration check
Quiz
Prompt Engineering: Techniques & Patterns
Video - 00:00:00 mins
Few-Shot, Chain-of-Thought, Tree-of-Thought
Video - 00:00:00 mins
Structured Outputs: JSON, Schema Validation, Constrained Decoding
Video - 00:00:00 mins
Embeddings & Vector Representations
Video - 00:00:00 mins
Context Engineering: Windows, Budgets, Memory, and Retrieval
Video - 00:00:00 mins
RAG (Retrieval-Augmented Generation)
Video - 00:00:00 mins
Advanced RAG (Chunking, Reranking, Hybrid Search)
Video - 00:00:00 mins
Fine-Tuning with LoRA & QLoRA
Video - 00:00:00 mins
Function Calling & Tool Use
Video - 00:00:00 mins
Evaluation & Testing LLM Applications
Video - 00:00:00 mins
Caching, Rate Limiting & Cost Optimization
Video - 00:00:00 mins
Guardrails, Safety & Content Filtering
Video - 00:00:00 mins
Building a Production LLM Application
Video - 00:00:00 mins
Model Context Protocol (MCP)
Video - 00:00:00 mins
Prompt Caching and Context Caching
Video - 00:00:00 mins
Agent State Machines — Graphs, Nodes, Checkpoints
Video - 00:00:00 mins
Agent Framework Tradeoffs — Graph, Role, and Actor Orchestration
Video - 00:00:00 mins
Phase 11 Project
Video - 00:00:00 mins
Phase 12: Multimodal Ai
Phase 12 Introduction
Video - 00:00:00 mins
Vision Transformers and the Patch-Token Primitive
Video - 00:00:00 mins
CLIP and Contrastive Vision-Language Pretraining
Video - 00:00:00 mins
From CLIP to BLIP-2 — Q-Former as Modality Bridge
Video - 00:00:00 mins
Flamingo and Gated Cross-Attention for Few-Shot VLMs
Video - 00:00:00 mins
LLaVA and Visual Instruction Tuning
Video - 00:00:00 mins
Any-Resolution Vision: Patch-n'-Pack and NaFlex
Video - 00:00:00 mins
Open-Weight VLM Recipes: What Actually Matters
Video - 00:00:00 mins
LLaVA-OneVision: Single-Image, Multi-Image, Video in One Model
Video - 00:00:00 mins
Qwen-VL Family and Dynamic-FPS Video
Video - 00:00:00 mins
InternVL3: Native Multimodal Pretraining
Video - 00:00:00 mins
Chameleon and Early-Fusion Token-Only Multimodal Models
Video - 00:00:00 mins
Emu3: Next-Token Prediction for Image and Video Generation
Video - 00:00:00 mins
Transfusion: Autoregressive Text + Diffusion Image in One Transformer
Video - 00:00:00 mins
Show-o and Discrete-Diffusion Unified Models
Video - 00:00:00 mins
Janus-Pro: Decoupled Encoders for Unified Multimodal Models
Video - 00:00:00 mins
MIO and Any-to-Any Streaming Multimodal Models
Video - 00:00:00 mins
Video-Language Models: Temporal Tokens and Grounding
Video - 00:00:00 mins
Long-Video Understanding at Million-Token Context
Video - 00:00:00 mins
Audio-Language Models: the Whisper to Audio Flamingo 3 Arc
Video - 00:00:00 mins
Omni Models: Qwen2.5-Omni and the Thinker-Talker Split
Video - 00:00:00 mins
Embodied VLAs: RT-2, OpenVLA, π0, GR00T
Video - 00:00:00 mins
Document and Diagram Understanding
Video - 00:00:00 mins
ColPali and Vision-Native Document RAG
Video - 00:00:00 mins
Multimodal RAG and Cross-Modal Retrieval
Video - 00:00:00 mins
Multimodal Agents and Computer-Use (Capstone)
Video - 00:00:00 mins
Phase 12 Project
Video - 00:00:00 mins
Phase 13: Tools And Protocols
Phase 13: MCP Reliability, Cancellation, and Flow Control check
Quiz
Phase 13: MCP Registry Supply Chain: Admission, Drift, and Rollback check
Quiz
Phase 13: MCP Conformance Engineering: Versioning, Evidence, and Operations check
Quiz
Phase 13: Program Anatomy: An ELF Reader From Scratch check
Quiz
Phase 13: Disassembly and Control Flow: From Bytes to a Graph You Can Check check
Quiz
Phase 13: Lifting to Pseudocode: IR, SSA, and Structuring From Scratch check
Quiz
Phase 13: Evidence, Confidence, and Unknowns in Binary Analysis check
Quiz
Phase 13: Rebuild and Prove Equal: Differential Tests, Byte Comparison, and the Evidence Loop check
Quiz
Phase 13: The Reverse Engineering Landscape: History, Tool Families, and How a Decompiler Is Built check
Quiz
Phase 13: Calling Conventions and Stack Frames: System V, Windows x64, and AArch64 check
Quiz
Phase 13: Compiler Idioms: What Optimization Does to Your Code and How to Read It Back check
Quiz
Phase 13: Linking, Loading, and Stripped Binaries: PLT, GOT, Imports, Fixups, and Function Identification check
Quiz
Phase 13: Recovering Data and Types: Structs, Arrays, C++ Objects, and DWARF check
Quiz
Phase 13: Dynamic Analysis of Your Own Program: Debuggers, Traces, and Confirming Static Claims check
Quiz
Phase 13: Beyond Native Code: Python, JVM, .NET, and WebAssembly Bytecode check
Quiz
Phase 13: Binary Diffing and Symbolic Execution: Matching Functions and Solving for Inputs check
Quiz
Phase 13: AI-Assisted Reverse Engineering: LLM Decompilers, Analysis Agents, and Ground Truth check
Quiz
Phase 13 Introduction
Video - 00:00:00 mins
Phase 13: MCP Fundamentals: Stateless Requests and JSON-RPC check
Quiz
Phase 13: Building an MCP Server: Stateless Python and TypeScript check
Quiz
Phase 13: Building an MCP Client: Discovery, Routing, and Dual-Era Fallback check
Quiz
Phase 13: MCP Transports: stdio and Stateless Streamable HTTP check
Quiz
Phase 13: MCP Resources and Prompts: Addressable Context for Stateless Servers check
Quiz
Phase 13: MCP Model Input: Sampling Migration and Stateless MRTR check
Quiz
Phase 13: Explicit Scope and Stateless Elicitation check
Quiz
Phase 13: MCP Tasks Extension: Durable Work on a Stateless Core check
Quiz
Phase 13: MCP Apps on the Stateless Protocol check
Quiz
Phase 13: MCP Security: Poisoned Metadata, Routing, and MRTR State check
Quiz
Phase 13: MCP Authorization: CIMD, Issuer Binding, PKCE, and Step-Up check
Quiz
Phase 13: Stateless MCP Gateways and Registry Admission check
Quiz
Phase 13: MCP Auth in Production: Issuer-Bound Enrollment and Tokens check
Quiz
Phase 13: Agent Skills: Portable Contract and Runtime Boundary check
Quiz
Phase 13: Capstone: Stateless Tool Ecosystem check
Quiz
Phase 13: Skill Discovery and Progressive Disclosure check
Quiz
Phase 13: Skill Invocation and Routing check
Quiz
Phase 13: Skill Permissions, Sandboxes, and Trust check
Quiz
Phase 13: Skill Evals, Packaging, and Portability check
Quiz
Phase 13: MCP Tool Contracts and Content check
Quiz
The Tool Interface — Why Agents Need Structured I/O
Video - 00:00:00 mins
Function Calling Deep Dive — OpenAI, Anthropic, Gemini
Video - 00:00:00 mins
Parallel Tool Calls and Streaming with Tools
Video - 00:00:00 mins
Structured Output — JSON Schema, Pydantic, Zod, Constrained Decoding
Video - 00:00:00 mins
Tool Schema Design — Naming, Descriptions, Parameter Constraints
Video - 00:00:00 mins
MCP Fundamentals: Stateless Requests and JSON-RPC
Video - 00:00:00 mins
Building an MCP Server: Stateless Python and TypeScript
Video - 00:00:00 mins
Building an MCP Client: Discovery, Routing, and Dual-Era Fallback
Video - 00:00:00 mins
MCP Transports: stdio and Stateless Streamable HTTP
Video - 00:00:00 mins
MCP Resources and Prompts: Addressable Context for Stateless Servers
Video - 00:00:00 mins
MCP Model Input: Sampling Migration and Stateless MRTR
Video - 00:00:00 mins
Explicit Scope and Stateless Elicitation
Video - 00:00:00 mins
MCP Tasks Extension: Durable Work on a Stateless Core
Video - 00:00:00 mins
MCP Apps on the Stateless Protocol
Video - 00:00:00 mins
MCP Security: Poisoned Metadata, Routing, and MRTR State
Video - 00:00:00 mins
MCP Authorization: CIMD, Issuer Binding, PKCE, and Step-Up
Video - 00:00:00 mins
Stateless MCP Gateways and Registry Admission
Video - 00:00:00 mins
MCP Auth in Production: Issuer-Bound Enrollment and Tokens
Video - 00:00:00 mins
A2A — Agent-to-Agent Protocol
Video - 00:00:00 mins
OpenTelemetry GenAI — Tracing Tool Calls End-to-End
Video - 00:00:00 mins
LLM Routing Layer — LiteLLM, OpenRouter, Portkey
Video - 00:00:00 mins
Agent Skills: Portable Contract and Runtime Boundary
Video - 00:00:00 mins
Capstone: Stateless Tool Ecosystem
Video - 00:00:00 mins
Skill Discovery and Progressive Disclosure
Video - 00:00:00 mins
Skill Invocation and Routing
Video - 00:00:00 mins
Skill Permissions, Sandboxes, and Trust
Video - 00:00:00 mins
Skill Evals, Packaging, and Portability
Video - 00:00:00 mins
MCP Tool Contracts and Content
Video - 00:00:00 mins
MCP Reliability, Cancellation, and Flow Control
Video - 00:00:00 mins
MCP Registry Supply Chain: Admission, Drift, and Rollback
Video - 00:00:00 mins
MCP Conformance Engineering: Versioning, Evidence, and Operations
Video - 00:00:00 mins
Program Anatomy: An ELF Reader From Scratch
Video - 00:00:00 mins
Disassembly and Control Flow: From Bytes to a Graph You Can Check
Video - 00:00:00 mins
Lifting to Pseudocode: IR, SSA, and Structuring From Scratch
Video - 00:00:00 mins
Evidence, Confidence, and Unknowns in Binary Analysis
Video - 00:00:00 mins
Rebuild and Prove Equal: Differential Tests, Byte Comparison, and the Evidence Loop
Video - 00:00:00 mins
The Reverse Engineering Landscape: History, Tool Families, and How a Decompiler Is Built
Video - 00:00:00 mins
Calling Conventions and Stack Frames: System V, Windows x64, and AArch64
Video - 00:00:00 mins
Compiler Idioms: What Optimization Does to Your Code and How to Read It Back
Video - 00:00:00 mins
Linking, Loading, and Stripped Binaries: PLT, GOT, Imports, Fixups, and Function Identification
Video - 00:00:00 mins
Recovering Data and Types: Structs, Arrays, C++ Objects, and DWARF
Video - 00:00:00 mins
Dynamic Analysis of Your Own Program: Debuggers, Traces, and Confirming Static Claims
Video - 00:00:00 mins
Beyond Native Code: Python, JVM, .NET, and WebAssembly Bytecode
Video - 00:00:00 mins
Binary Diffing and Symbolic Execution: Matching Functions and Solving for Inputs
Video - 00:00:00 mins
AI-Assisted Reverse Engineering: LLM Decompilers, Analysis Agents, and Ground Truth
Video - 00:00:00 mins
Phase 13 Project
Video - 00:00:00 mins
Phase 14: Agent Engineering
Phase 14 Introduction
Video - 00:00:00 mins
Phase 14: The Agent Loop: Observe, Think, Act check
Quiz
Phase 14: ReWOO and Plan-and-Execute: Decoupled Planning check
Quiz
Phase 14: Reflexion: Verbal Reinforcement Learning check
Quiz
Phase 14: Tree of Thoughts and LATS: Deliberate Search check
Quiz
Phase 14: Self-Refine and CRITIC: Iterative Output Improvement check
Quiz
Phase 14: Tool Use and Function Calling check
Quiz
Phase 14: Agent Memory — Virtual Context and Memory Paging check
Quiz
Phase 14: Memory Blocks and Sleep-Time Compute check
Quiz
Phase 14: Hybrid Memory: Vector + Graph + KV check
Quiz
Phase 14: Skill Libraries and Lifelong Learning (Voyager) check
Quiz
Phase 14: Planning with HTN and Evolutionary Search check
Quiz
Phase 14: Anthropic's Workflow Patterns: Simple Over Complex check
Quiz
Phase 14: Stateful Graph Orchestration — Durable Execution and Checkpoints check
Quiz
Phase 14: The Actor Model for Agents — Async Messages and Typed Runtimes check
Quiz
Phase 14: Role-Based Agent Teams — Roles, Tasks, Processes check
Quiz
Phase 14: OpenAI Agents SDK: Handoffs, Guardrails, Tracing check
Quiz
Phase 14: The Harness as a Library — Subagents and Session Store check
Quiz
Phase 14: Production Agent Runtimes — Fast Instantiation and Typed Workflows check
Quiz
Phase 14: Benchmarks: SWE-bench, GAIA, AgentBench check
Quiz
Phase 14: Benchmarks: WebArena and OSWorld check
Quiz
Phase 14: Computer Use: Claude, OpenAI CUA, Gemini check
Quiz
Phase 14: Voice Agents: Pipecat and LiveKit check
Quiz
Phase 14: OpenTelemetry GenAI Semantic Conventions check
Quiz
Phase 14: Agent Observability: Langfuse, Phoenix, Opik check
Quiz
Phase 14: Multi-Agent Debate and Collaboration check
Quiz
Phase 14: Failure Modes: Why Agents Break check
Quiz
Phase 14: Prompt Injection and the PVE Defense check
Quiz
Phase 14: Orchestration Patterns: Supervisor, Swarm, Hierarchical check
Quiz
Phase 14: Production Runtimes: Queue, Event, Cron check
Quiz
Phase 14: Eval-Driven Agent Development check
Quiz
Phase 14: Agent Workbench Engineering: Why Capable Models Still Fail check
Quiz
Phase 14: The Minimal Agent Workbench check
Quiz
Phase 14: Agent Instructions as Executable Constraints check
Quiz
Phase 14: Repo Memory and Durable State check
Quiz
Phase 14: Initialization Scripts for Agents check
Quiz
Phase 14: Scope Contracts and Task Boundaries check
Quiz
Phase 14: Runtime Feedback Loops check
Quiz
Phase 14: Verification Gates check
Quiz
Phase 14: Reviewer Agent: Separate Builder from Marker check
Quiz
Phase 14: Multi-Session Handoff check
Quiz
Phase 14: The Workbench on a Real Repo check
Quiz
Phase 14: Capstone: Ship a Reusable Agent Workbench Pack check
Quiz
Phase 14: Frame the Task Before the Agent Writes Code check
Quiz
Phase 14: Build an Evidence-Backed Execution Plan check
Quiz
Phase 14: Delegate Agent Work with Isolation and Merge Contracts check
Quiz
Phase 14: Turn Every Agent Correction into a System Improvement check
Quiz
Phase 14: Define the Outcome Before You Choose the Output check
Quiz
Phase 14: Discover the Workflow People Actually Perform check
Quiz
Phase 14: Map Assumptions and Resolve the Riskiest One First check
Quiz
Phase 14: Choose the Smallest Slice That Can Change the Decision check
Quiz
Phase 14: Write Specifications That Preserve Judgment check
Quiz
Phase 14: Design Success Metrics Before the Result Exists check
Quiz
Phase 14: Choose Prototype, Pilot, or Production Deliberately check
Quiz
Phase 14: Build a Feedback Ratchet with Ownership and Retirement check
Quiz
The Agent Loop: Observe, Think, Act
Video - 00:00:00 mins
ReWOO and Plan-and-Execute: Decoupled Planning
Video - 00:00:00 mins
Reflexion: Verbal Reinforcement Learning
Video - 00:00:00 mins
Tree of Thoughts and LATS: Deliberate Search
Video - 00:00:00 mins
Self-Refine and CRITIC: Iterative Output Improvement
Video - 00:00:00 mins
Tool Use and Function Calling
Video - 00:00:00 mins
Agent Memory — Virtual Context and Memory Paging
Video - 00:00:00 mins
Memory Blocks and Sleep-Time Compute
Video - 00:00:00 mins
Hybrid Memory: Vector + Graph + KV
Video - 00:00:00 mins
Skill Libraries and Lifelong Learning (Voyager)
Video - 00:00:00 mins
Planning with HTN and Evolutionary Search
Video - 00:00:00 mins
Anthropic's Workflow Patterns: Simple Over Complex
Video - 00:00:00 mins
Stateful Graph Orchestration — Durable Execution and Checkpoints
Video - 00:00:00 mins
The Actor Model for Agents — Async Messages and Typed Runtimes
Video - 00:00:00 mins
Role-Based Agent Teams — Roles, Tasks, Processes
Video - 00:00:00 mins
OpenAI Agents SDK: Handoffs, Guardrails, Tracing
Video - 00:00:00 mins
The Harness as a Library — Subagents and Session Store
Video - 00:00:00 mins
Production Agent Runtimes — Fast Instantiation and Typed Workflows
Video - 00:00:00 mins
Benchmarks: SWE-bench, GAIA, AgentBench
Video - 00:00:00 mins
Benchmarks: WebArena and OSWorld
Video - 00:00:00 mins
Computer Use: Claude, OpenAI CUA, Gemini
Video - 00:00:00 mins
Voice Agents: Pipecat and LiveKit
Video - 00:00:00 mins
OpenTelemetry GenAI Semantic Conventions
Video - 00:00:00 mins
Agent Observability: Langfuse, Phoenix, Opik
Video - 00:00:00 mins
Multi-Agent Debate and Collaboration
Video - 00:00:00 mins
Failure Modes: Why Agents Break
Video - 00:00:00 mins
Prompt Injection and the PVE Defense
Video - 00:00:00 mins
Orchestration Patterns: Supervisor, Swarm, Hierarchical
Video - 00:00:00 mins
Production Runtimes: Queue, Event, Cron
Video - 00:00:00 mins
Eval-Driven Agent Development
Video - 00:00:00 mins
Agent Workbench Engineering: Why Capable Models Still Fail
Video - 00:00:00 mins
The Minimal Agent Workbench
Video - 00:00:00 mins
Agent Instructions as Executable Constraints
Video - 00:00:00 mins
Repo Memory and Durable State
Video - 00:00:00 mins
Initialization Scripts for Agents
Video - 00:00:00 mins
Scope Contracts and Task Boundaries
Video - 00:00:00 mins
Runtime Feedback Loops
Video - 00:00:00 mins
Verification Gates
Video - 00:00:00 mins
Reviewer Agent: Separate Builder from Marker
Video - 00:00:00 mins
Multi-Session Handoff
Video - 00:00:00 mins
The Workbench on a Real Repo
Video - 00:00:00 mins
Capstone: Ship a Reusable Agent Workbench Pack
Video - 00:00:00 mins
Frame the Task Before the Agent Writes Code
Video - 00:00:00 mins
Build an Evidence-Backed Execution Plan
Video - 00:00:00 mins
Delegate Agent Work with Isolation and Merge Contracts
Video - 00:00:00 mins
Turn Every Agent Correction into a System Improvement
Video - 00:00:00 mins
Define the Outcome Before You Choose the Output
Video - 00:00:00 mins
Discover the Workflow People Actually Perform
Video - 00:00:00 mins
Map Assumptions and Resolve the Riskiest One First
Video - 00:00:00 mins
Choose the Smallest Slice That Can Change the Decision
Video - 00:00:00 mins
Write Specifications That Preserve Judgment
Video - 00:00:00 mins
Design Success Metrics Before the Result Exists
Video - 00:00:00 mins
Choose Prototype, Pilot, or Production Deliberately
Video - 00:00:00 mins
Build a Feedback Ratchet with Ownership and Retirement
Video - 00:00:00 mins
Phase 14 Project
Video - 00:00:00 mins
Phase 15: Autonomous Systems
Phase 15 Introduction
Video - 00:00:00 mins
The Shift from Chatbots to Long-Horizon Agents
Video - 00:00:00 mins
STaR, V-STaR, Quiet-STaR — Self-Taught Reasoning
Video - 00:00:00 mins
AlphaEvolve — Evolutionary Coding Agents
Video - 00:00:00 mins
Darwin Godel Machine — Open-Ended Self-Modifying Agents
Video - 00:00:00 mins
AI Scientist v2 — Workshop-Level Autonomous Research
Video - 00:00:00 mins
Automated Alignment Research (Anthropic AAR)
Video - 00:00:00 mins
Recursive Self-Improvement — Capability vs Alignment
Video - 00:00:00 mins
Bounded Self-Improvement Designs
Video - 00:00:00 mins
The Autonomous Coding Agent Landscape (2026)
Video - 00:00:00 mins
Permission Modes for Autonomous Agents
Video - 00:00:00 mins
Browser Agents and Long-Horizon Web Tasks
Video - 00:00:00 mins
Long-Running Background Agents: Durable Execution
Video - 00:00:00 mins
Action Budgets, Iteration Caps, and Cost Governors
Video - 00:00:00 mins
Kill Switches, Circuit Breakers, and Canary Tokens
Video - 00:00:00 mins
Human-in-the-Loop: Propose-Then-Commit
Video - 00:00:00 mins
Checkpoints and Rollback
Video - 00:00:00 mins
Constitutional AI and Rule Overrides
Video - 00:00:00 mins
Llama Guard and Input/Output Classification
Video - 00:00:00 mins
Anthropic Responsible Scaling Policy v3.0
Video - 00:00:00 mins
OpenAI Preparedness Framework and DeepMind Frontier Safety Framework
Video - 00:00:00 mins
METR Time Horizons and External Capability Evaluation
Video - 00:00:00 mins
CAIS, CAISI, and Societal-Scale Risk
Video - 00:00:00 mins
Phase 15 Project
Video - 00:00:00 mins
Phase 16: Multi Agent And Swarms
Phase 16 Introduction
Video - 00:00:00 mins
Phase 16: Why Multi-Agent? check
Quiz
Phase 16: Communication Protocols check
Quiz
Why Multi-Agent?
Video - 00:00:00 mins
Heritage of FIPA-ACL and Speech Acts
Video - 00:00:00 mins
Communication Protocols
Video - 00:00:00 mins
The Multi-Agent Primitive Model
Video - 00:00:00 mins
Supervisor / Orchestrator-Worker Pattern
Video - 00:00:00 mins
Hierarchical Architecture and Its Failure Mode
Video - 00:00:00 mins
Society of Mind and Multi-Agent Debate
Video - 00:00:00 mins
Role Specialization — Planner, Critic, Executor, Verifier
Video - 00:00:00 mins
Parallel / Swarm / Networked Architectures
Video - 00:00:00 mins
Group Chat and Speaker Selection
Video - 00:00:00 mins
Handoffs and Routines — Stateless Orchestration
Video - 00:00:00 mins
A2A — The Agent-to-Agent Protocol
Video - 00:00:00 mins
Shared Memory and Blackboard Patterns
Video - 00:00:00 mins
Consensus and Byzantine Fault Tolerance for Agents
Video - 00:00:00 mins
Voting, Self-Consistency, and Debate Topology
Video - 00:00:00 mins
Negotiation and Bargaining
Video - 00:00:00 mins
Generative Agents and Emergent Simulation
Video - 00:00:00 mins
Theory of Mind and Emergent Coordination
Video - 00:00:00 mins
Swarm Optimization for LLMs (PSO, ACO)
Video - 00:00:00 mins
MARL — MADDPG, QMIX, MAPPO
Video - 00:00:00 mins
Agent Economies, Token Incentives, Reputation
Video - 00:00:00 mins
Production Scaling — Queues, Checkpoints, Durability
Video - 00:00:00 mins
Failure Modes — MAST, Groupthink, Monoculture, Cascading Errors
Video - 00:00:00 mins
Evaluation and Coordination Benchmarks
Video - 00:00:00 mins
Case Studies and the 2026 State of the Art
Video - 00:00:00 mins
Phase 16 Project
Video - 00:00:00 mins
Phase 17: Infrastructure And Production
Phase 17: FinOps for LLMs — Unit Economics and Multi-Tenant Attribution check
Quiz
Phase 17: Self-Hosted Serving Selection — Matching Engine to Hardware and Scale check
Quiz
Phase 17: Model Demo Interfaces — From a Function to a Shareable App check
Quiz
Phase 17 Introduction
Video - 00:00:00 mins
Phase 17: Managed LLM Platforms — Bedrock, Vertex AI, Azure OpenAI check
Quiz
Phase 17: Inference Platform Economics — Fireworks, Together, Baseten, Modal, Replicate, Anyscale check
Quiz
Phase 17: GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler, Gang Scheduling check
Quiz
Phase 17: Serving Engine Internals — PagedAttention, Continuous Batching, Chunked Prefill check
Quiz
Phase 17: EAGLE-3 Speculative Decoding in Production check
Quiz
Phase 17: Prefix-Cache Serving — RadixAttention and KV Reuse check
Quiz
Phase 17: Hardware-Specialized Inference Compilation — FP8 and NVFP4 on Blackwell check
Quiz
Phase 17: Inference Metrics — TTFT, TPOT, ITL, Goodput, P99 check
Quiz
Phase 17: Production Quantization — AWQ, GPTQ, GGUF K-quants, FP8, MXFP4/NVFP4 check
Quiz
Phase 17: Cold Start Mitigation for Serverless LLMs check
Quiz
Phase 17: Multi-Region LLM Serving and KV Cache Locality check
Quiz
Phase 17: Edge Inference — Apple Neural Engine, Qualcomm Hexagon, WebGPU/WebLLM, Jetson check
Quiz
Phase 17: LLM Observability Stack Selection check
Quiz
Phase 17: Prompt Caching and Semantic Caching Economics check
Quiz
Phase 17: Batch APIs — the 50% Discount as Industry Standard check
Quiz
Phase 17: Model Routing as a Cost-Reduction Primitive check
Quiz
Phase 17: Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d check
Quiz
Phase 17: Production Serving Stack — KV Offloading and Cache-Aware Routing check
Quiz
Phase 17: AI Gateways — LiteLLM, Portkey, Kong AI Gateway, Bifrost check
Quiz
Phase 17: Shadow Traffic, Canary Rollout, and Progressive Deployment for LLMs check
Quiz
Phase 17: A/B Testing LLM Features — GrowthBook, Statsig, and the Vibes Problem check
Quiz
Phase 17: Load Testing LLM APIs — Why k6 and Locust Lie check
Quiz
Phase 17: SRE for AI — Multi-Agent Incident Response, Runbooks, Predictive Detection check
Quiz
Phase 17: Chaos Engineering for LLM Production check
Quiz
Phase 17: Security — Secrets, API Key Rotation, Audit Logs, Guardrails check
Quiz
Phase 17: Compliance — SOC 2, HIPAA, GDPR, PCI-DSS, EU AI Act, ISO 42001 check
Quiz
Managed LLM Platforms — Bedrock, Vertex AI, Azure OpenAI
Video - 00:00:00 mins
Inference Platform Economics — Fireworks, Together, Baseten, Modal, Replicate, Anyscale
Video - 00:00:00 mins
GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler, Gang Scheduling
Video - 00:00:00 mins
Serving Engine Internals — PagedAttention, Continuous Batching, Chunked Prefill
Video - 00:00:00 mins
EAGLE-3 Speculative Decoding in Production
Video - 00:00:00 mins
Prefix-Cache Serving — RadixAttention and KV Reuse
Video - 00:00:00 mins
Hardware-Specialized Inference Compilation — FP8 and NVFP4 on Blackwell
Video - 00:00:00 mins
Inference Metrics — TTFT, TPOT, ITL, Goodput, P99
Video - 00:00:00 mins
Production Quantization — AWQ, GPTQ, GGUF K-quants, FP8, MXFP4/NVFP4
Video - 00:00:00 mins
Cold Start Mitigation for Serverless LLMs
Video - 00:00:00 mins
Multi-Region LLM Serving and KV Cache Locality
Video - 00:00:00 mins
Edge Inference — Apple Neural Engine, Qualcomm Hexagon, WebGPU/WebLLM, Jetson
Video - 00:00:00 mins
LLM Observability Stack Selection
Video - 00:00:00 mins
Prompt Caching and Semantic Caching Economics
Video - 00:00:00 mins
Batch APIs — the 50% Discount as Industry Standard
Video - 00:00:00 mins
Model Routing as a Cost-Reduction Primitive
Video - 00:00:00 mins
Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d
Video - 00:00:00 mins
Production Serving Stack — KV Offloading and Cache-Aware Routing
Video - 00:00:00 mins
AI Gateways — LiteLLM, Portkey, Kong AI Gateway, Bifrost
Video - 00:00:00 mins
Shadow Traffic, Canary Rollout, and Progressive Deployment for LLMs
Video - 00:00:00 mins
A/B Testing LLM Features — GrowthBook, Statsig, and the Vibes Problem
Video - 00:00:00 mins
Load Testing LLM APIs — Why k6 and Locust Lie
Video - 00:00:00 mins
SRE for AI — Multi-Agent Incident Response, Runbooks, Predictive Detection
Video - 00:00:00 mins
Chaos Engineering for LLM Production
Video - 00:00:00 mins
Security — Secrets, API Key Rotation, Audit Logs, Guardrails
Video - 00:00:00 mins
Compliance — SOC 2, HIPAA, GDPR, PCI-DSS, EU AI Act, ISO 42001
Video - 00:00:00 mins
FinOps for LLMs — Unit Economics and Multi-Tenant Attribution
Video - 00:00:00 mins
Self-Hosted Serving Selection — Matching Engine to Hardware and Scale
Video - 00:00:00 mins
Model Demo Interfaces — From a Function to a Shareable App
Video - 00:00:00 mins
Phase 17 Project
Video - 00:00:00 mins
Phase 18: Ethics Safety Alignment
Phase 18 Introduction
Video - 00:00:00 mins
Phase 18: Instruction-Following as Alignment Signal check
Quiz
Phase 18: Reward Hacking and Goodhart's Law check
Quiz
Phase 18: The Direct Preference Optimization Family check
Quiz
Phase 18: Sycophancy as RLHF Amplification check
Quiz
Phase 18: Constitutional AI and RLAIF check
Quiz
Phase 18: Mesa-Optimization and Deceptive Alignment check
Quiz
Phase 18: Sleeper Agents — Persistent Deception check
Quiz
Phase 18: In-Context Scheming in Frontier Models check
Quiz
Phase 18: Alignment Faking check
Quiz
Phase 18: AI Control — Safety Despite Subversion check
Quiz
Phase 18: Scalable Oversight and Weak-to-Strong Generalization check
Quiz
Phase 18: Red-Teaming: PAIR and Automated Attacks check
Quiz
Phase 18: Many-Shot Jailbreaking check
Quiz
Phase 18: ASCII Art and Visual Jailbreaks check
Quiz
Phase 18: Indirect Prompt Injection — Production Attack Surface check
Quiz
Phase 18: Red-Team Tooling — Garak, Llama Guard, PyRIT check
Quiz
Phase 18: WMDP and Dual-Use Capability Evaluation check
Quiz
Phase 18: Frontier Safety Frameworks — RSP, PF, FSF check
Quiz
Phase 18: Anthropic's Model Welfare Program check
Quiz
Phase 18: Bias and Representational Harm in LLMs check
Quiz
Phase 18: Fairness Criteria — Group, Individual, Counterfactual check
Quiz
Phase 18: Differential Privacy for LLMs check
Quiz
Phase 18: Watermarking — SynthID, Stable Signature, C2PA check
Quiz
Phase 18: Regulatory Frameworks — EU, US, UK, Korea check
Quiz
Phase 18: EchoLeak and the Emergence of CVEs for AI check
Quiz
Phase 18: Model, System, and Dataset Cards check
Quiz
Phase 18: Data Provenance and Training-Data Governance check
Quiz
Phase 18: Alignment Research Ecosystem — MATS, Redwood, Apollo, METR check
Quiz
Phase 18: Moderation Systems — OpenAI, Perspective, Llama Guard check
Quiz
Phase 18: Dual-Use Risk — Cyber, Bio, Chem, Nuclear Uplift check
Quiz
Instruction-Following as Alignment Signal
Video - 00:00:00 mins
Reward Hacking and Goodhart's Law
Video - 00:00:00 mins
The Direct Preference Optimization Family
Video - 00:00:00 mins
Sycophancy as RLHF Amplification
Video - 00:00:00 mins
Constitutional AI and RLAIF
Video - 00:00:00 mins
Mesa-Optimization and Deceptive Alignment
Video - 00:00:00 mins
Sleeper Agents — Persistent Deception
Video - 00:00:00 mins
In-Context Scheming in Frontier Models
Video - 00:00:00 mins
Alignment Faking
Video - 00:00:00 mins
AI Control — Safety Despite Subversion
Video - 00:00:00 mins
Scalable Oversight and Weak-to-Strong Generalization
Video - 00:00:00 mins
Red-Teaming: PAIR and Automated Attacks
Video - 00:00:00 mins
Many-Shot Jailbreaking
Video - 00:00:00 mins
ASCII Art and Visual Jailbreaks
Video - 00:00:00 mins
Indirect Prompt Injection — Production Attack Surface
Video - 00:00:00 mins
Red-Team Tooling — Garak, Llama Guard, PyRIT
Video - 00:00:00 mins
WMDP and Dual-Use Capability Evaluation
Video - 00:00:00 mins
Frontier Safety Frameworks — RSP, PF, FSF
Video - 00:00:00 mins
Anthropic's Model Welfare Program
Video - 00:00:00 mins
Bias and Representational Harm in LLMs
Video - 00:00:00 mins
Fairness Criteria — Group, Individual, Counterfactual
Video - 00:00:00 mins
Differential Privacy for LLMs
Video - 00:00:00 mins
Watermarking — SynthID, Stable Signature, C2PA
Video - 00:00:00 mins
Regulatory Frameworks — EU, US, UK, Korea
Video - 00:00:00 mins
EchoLeak and the Emergence of CVEs for AI
Video - 00:00:00 mins
Model, System, and Dataset Cards
Video - 00:00:00 mins
Data Provenance and Training-Data Governance
Video - 00:00:00 mins
Alignment Research Ecosystem — MATS, Redwood, Apollo, METR
Video - 00:00:00 mins
Moderation Systems — OpenAI, Perspective, Llama Guard
Video - 00:00:00 mins
Dual-Use Risk — Cyber, Bio, Chem, Nuclear Uplift
Video - 00:00:00 mins
Phase 18 Project
Video - 00:00:00 mins
Phase 19: Capstone Projects
Phase 19: Capstone 11 — LLM Observability & Eval Dashboard check
Quiz
Phase 19 Introduction
Video - 00:00:00 mins
Phase 19: Capstone 01 — Terminal-Native Coding Agent check
Quiz
Phase 19: Capstone 02 — RAG over Codebase (Cross-Repo Semantic Search) check
Quiz
Phase 19: Capstone 03 — Real-Time Voice Assistant (ASR to LLM to TTS) check
Quiz
Phase 19: Capstone 04 — Multimodal Document QA (Vision-First PDF, Tables, Charts) check
Quiz
Phase 19: Capstone 05 — Autonomous Research Agent (AI-Scientist Class) check
Quiz
Phase 19: Capstone 06 — DevOps Troubleshooting Agent for Kubernetes check
Quiz
Phase 19: Capstone 07 — End-to-End Fine-Tuning Pipeline (Data to SFT to DPO to Serve) check
Quiz
Phase 19: Capstone 08 — Production RAG Chatbot for a Regulated Vertical check
Quiz
Phase 19: Capstone 09 — Code Migration Agent (Repo-Level Language / Runtime Upgrade) check
Quiz
Phase 19: Capstone 10 — Multi-Agent Software Engineering Team check
Quiz
Phase 19: Capstone 11 — LLM Observability & Eval Dashboard check
Quiz
Phase 19: Capstone 12 — Video Understanding Pipeline (Scene, QA, Search) check
Quiz
Phase 19: Capstone 13: Stateless MCP Server with Registry and Governance check
Quiz
Phase 19: Capstone 14 — Speculative-Decoding Inference Server check
Quiz
Phase 19: Capstone 15 — Constitutional Safety Harness + Red-Team Range check
Quiz
Phase 19: Capstone 16 — GitHub Issue-to-PR Autonomous Agent check
Quiz
Phase 19: Capstone 17 — Personal AI Tutor (Adaptive, Multimodal, with Memory) check
Quiz
Phase 19: Agent Harness Loop Contract check
Quiz
Phase 19: Tool Registry with Schema Validation check
Quiz
Phase 19: JSON-RPC 2.0 Over Newline-Delimited Stdio check
Quiz
Phase 19: Function Call Dispatcher check
Quiz
Phase 19: Plan-Execute Control Flow check
Quiz
Phase 19: Capstone Lesson 25: Verification Gates and the Observation Budget check
Quiz
Phase 19: Capstone Lesson 26: Sandbox Runner with Denylist and Path Jail check
Quiz
Phase 19: Capstone Lesson 27: Eval Harness with Fixture Tasks check
Quiz
Phase 19: Capstone Lesson 28: Observability with OTel GenAI Spans and Prometheus Metrics check
Quiz
Phase 19: Capstone Lesson 29: End-to-End Coding Agent on the Harness check
Quiz
Phase 19: BPE Tokenizer From Scratch check
Quiz
Phase 19: Tokenized Dataset with Sliding Window check
Quiz
Phase 19: Token and Positional Embeddings check
Quiz
Phase 19: Multi-Head Self-Attention check
Quiz
Phase 19: Transformer Block from Scratch check
Quiz
Phase 19: GPT Model Assembly check
Quiz
Phase 19: Training Loop and Evaluation check
Quiz
Phase 19: Loading Pretrained Weights check
Quiz
Phase 19: Capstone Lesson 38: Classifier Fine-Tuning by Head Swap check
Quiz
Phase 19: Capstone Lesson 39: Instruction Tuning by Supervised Fine-Tuning check
Quiz
Phase 19: Capstone Lesson 40: Direct Preference Optimization from Scratch check
Quiz
Phase 19: Capstone Lesson 41: Full Evaluation Pipeline check
Quiz
Phase 19: Large Corpus Downloader check
Quiz
Phase 19: HDF5 Tokenized Corpus check
Quiz
Phase 19: Cosine LR with Linear Warmup check
Quiz
Phase 19: Gradient Clipping and Mixed Precision check
Quiz
Phase 19: Gradient Accumulation check
Quiz
Phase 19: Checkpoint Save and Resume check
Quiz
Phase 19: Distributed Data Parallel and FSDP from Scratch check
Quiz
Phase 19: Language Model Evaluation Harness check
Quiz
Phase 19: Hypothesis Generator check
Quiz
Phase 19: Literature Retrieval check
Quiz
Phase 19: Experiment Runner check
Quiz
Phase 19: Result Evaluator check
Quiz
Phase 19: Paper Writer check
Quiz
Phase 19: Critic Loop check
Quiz
Phase 19: Iteration Scheduler check
Quiz
Phase 19: End-to-End Research Demo check
Quiz
Phase 19: Vision Encoder Patches check
Quiz
Phase 19: Vision Transformer Encoder check
Quiz
Phase 19: Projection Layer for Modality Alignment check
Quiz
Phase 19: Cross-Attention Fusion check
Quiz
Phase 19: Vision-Language Pretraining check
Quiz
Phase 19: Multimodal Evaluation check
Quiz
Phase 19: Chunking Strategies, Compared check
Quiz
Phase 19: Hybrid Retrieval with BM25 and Dense Embeddings check
Quiz
Phase 19: Cross-Encoder Reranker check
Quiz
Phase 19: Query Rewriting: HyDE, Multi-Query, and Decomposition check
Quiz
Phase 19: RAG Evaluation: Precision, Recall, MRR, nDCG, Faithfulness, Answer Relevance check
Quiz
Phase 19: End-to-End RAG System check
Quiz
Phase 19: Task Spec Format check
Quiz
Phase 19: Classical Metrics check
Quiz
Phase 19: Code Exec Metric check
Quiz
Phase 19: Perplexity and Calibration check
Quiz
Phase 19: Leaderboard Aggregation check
Quiz
Phase 19: End-to-End Eval Runner check
Quiz
Phase 19: Collective Ops From Scratch check
Quiz
Phase 19: Data Parallel DDP From Scratch check
Quiz
Phase 19: ZeRO Optimizer State Sharding check
Quiz
Phase 19: Pipeline Parallel and Bubble Analysis check
Quiz
Phase 19: Sharded Checkpoint and Atomic Resume check
Quiz
Phase 19: End-to-End Distributed Training check
Quiz
Phase 19: Capstone 82 — Jailbreak Taxonomy check
Quiz
Phase 19: Capstone 83 — Prompt Injection Detector check
Quiz
Phase 19: Capstone 84 — Refusal Evaluation check
Quiz
Phase 19: Capstone 85 — Content Classifier Integration check
Quiz
Phase 19: Capstone 86 — Constitutional Rules Engine check
Quiz
Phase 19: Capstone 87 — End-to-End Safety Gate check
Quiz
Capstone 01 — Terminal-Native Coding Agent
Video - 00:00:00 mins
Capstone 02 — RAG over Codebase (Cross-Repo Semantic Search)
Video - 00:00:00 mins
Capstone 03 — Real-Time Voice Assistant (ASR to LLM to TTS)
Video - 00:00:00 mins
Capstone 04 — Multimodal Document QA (Vision-First PDF, Tables, Charts)
Video - 00:00:00 mins
Capstone 05 — Autonomous Research Agent (AI-Scientist Class)
Video - 00:00:00 mins
Capstone 06 — DevOps Troubleshooting Agent for Kubernetes
Video - 00:00:00 mins
Capstone 07 — End-to-End Fine-Tuning Pipeline (Data to SFT to DPO to Serve)
Video - 00:00:00 mins
Capstone 08 — Production RAG Chatbot for a Regulated Vertical
Video - 00:00:00 mins
Capstone 09 — Code Migration Agent (Repo-Level Language / Runtime Upgrade)
Video - 00:00:00 mins
Capstone 10 — Multi-Agent Software Engineering Team
Video - 00:00:00 mins
Capstone 11 — LLM Observability & Eval Dashboard
Video - 00:00:00 mins
Capstone 12 — Video Understanding Pipeline (Scene, QA, Search)
Video - 00:00:00 mins
Capstone 13: Stateless MCP Server with Registry and Governance
Video - 00:00:00 mins
Capstone 14 — Speculative-Decoding Inference Server
Video - 00:00:00 mins
Capstone 15 — Constitutional Safety Harness + Red-Team Range
Video - 00:00:00 mins
Capstone 16 — GitHub Issue-to-PR Autonomous Agent
Video - 00:00:00 mins
Capstone 17 — Personal AI Tutor (Adaptive, Multimodal, with Memory)
Video - 00:00:00 mins
Agent Harness Loop Contract
Video - 00:00:00 mins
Tool Registry with Schema Validation
Video - 00:00:00 mins
JSON-RPC 2.0 Over Newline-Delimited Stdio
Video - 00:00:00 mins
Function Call Dispatcher
Video - 00:00:00 mins
Plan-Execute Control Flow
Video - 00:00:00 mins
Capstone Lesson 25: Verification Gates and the Observation Budget
Video - 00:00:00 mins
Capstone Lesson 26: Sandbox Runner with Denylist and Path Jail
Video - 00:00:00 mins
Capstone Lesson 27: Eval Harness with Fixture Tasks
Video - 00:00:00 mins
Capstone Lesson 28: Observability with OTel GenAI Spans and Prometheus Metrics
Video - 00:00:00 mins
Capstone Lesson 29: End-to-End Coding Agent on the Harness
Video - 00:00:00 mins
BPE Tokenizer From Scratch
Video - 00:00:00 mins
Tokenized Dataset with Sliding Window
Video - 00:00:00 mins
Token and Positional Embeddings
Video - 00:00:00 mins
Multi-Head Self-Attention
Video - 00:00:00 mins
Transformer Block from Scratch
Video - 00:00:00 mins
GPT Model Assembly
Video - 00:00:00 mins
Training Loop and Evaluation
Video - 00:00:00 mins
Loading Pretrained Weights
Video - 00:00:00 mins
Capstone Lesson 38: Classifier Fine-Tuning by Head Swap
Video - 00:00:00 mins
Capstone Lesson 39: Instruction Tuning by Supervised Fine-Tuning
Video - 00:00:00 mins
Capstone Lesson 40: Direct Preference Optimization from Scratch
Video - 00:00:00 mins
Capstone Lesson 41: Full Evaluation Pipeline
Video - 00:00:00 mins
Large Corpus Downloader
Video - 00:00:00 mins
HDF5 Tokenized Corpus
Video - 00:00:00 mins
Cosine LR with Linear Warmup
Video - 00:00:00 mins
Gradient Clipping and Mixed Precision
Video - 00:00:00 mins
Gradient Accumulation
Video - 00:00:00 mins
Checkpoint Save and Resume
Video - 00:00:00 mins
Distributed Data Parallel and FSDP from Scratch
Video - 00:00:00 mins
Language Model Evaluation Harness
Video - 00:00:00 mins
Hypothesis Generator
Video - 00:00:00 mins
Literature Retrieval
Video - 00:00:00 mins
Experiment Runner
Video - 00:00:00 mins
Result Evaluator
Video - 00:00:00 mins
Paper Writer
Video - 00:00:00 mins
Critic Loop
Video - 00:00:00 mins
Iteration Scheduler
Video - 00:00:00 mins
End-to-End Research Demo
Video - 00:00:00 mins
Vision Encoder Patches
Video - 00:00:00 mins
Vision Transformer Encoder
Video - 00:00:00 mins
Projection Layer for Modality Alignment
Video - 00:00:00 mins
Cross-Attention Fusion
Video - 00:00:00 mins
Vision-Language Pretraining
Video - 00:00:00 mins
Multimodal Evaluation
Video - 00:00:00 mins
Chunking Strategies, Compared
Video - 00:00:00 mins
Hybrid Retrieval with BM25 and Dense Embeddings
Video - 00:00:00 mins
Cross-Encoder Reranker
Video - 00:00:00 mins
Query Rewriting: HyDE, Multi-Query, and Decomposition
Video - 00:00:00 mins
RAG Evaluation: Precision, Recall, MRR, nDCG, Faithfulness, Answer Relevance
Video - 00:00:00 mins
End-to-End RAG System
Video - 00:00:00 mins
Task Spec Format
Video - 00:00:00 mins
Classical Metrics
Video - 00:00:00 mins
Code Exec Metric
Video - 00:00:00 mins
Perplexity and Calibration
Video - 00:00:00 mins
Leaderboard Aggregation
Video - 00:00:00 mins
End-to-End Eval Runner
Video - 00:00:00 mins
Collective Ops From Scratch
Video - 00:00:00 mins
Data Parallel DDP From Scratch
Video - 00:00:00 mins
ZeRO Optimizer State Sharding
Video - 00:00:00 mins
Pipeline Parallel and Bubble Analysis
Video - 00:00:00 mins
Sharded Checkpoint and Atomic Resume
Video - 00:00:00 mins
End-to-End Distributed Training
Video - 00:00:00 mins
Capstone 82 — Jailbreak Taxonomy
Video - 00:00:00 mins
Capstone 83 — Prompt Injection Detector
Video - 00:00:00 mins
Capstone 84 — Refusal Evaluation
Video - 00:00:00 mins
Capstone 85 — Content Classifier Integration
Video - 00:00:00 mins
Capstone 86 — Constitutional Rules Engine
Video - 00:00:00 mins
Capstone 87 — End-to-End Safety Gate
Video - 00:00:00 mins
Phase 19 Project
Video - 00:00:00 mins
Phase 13 Project
Apply what you’ve learned in this phase to build a complete project.
Refer to the phase lessons and the capstone materials in the repository.
Course content adapted from AI Engineering from Scratch by Rohit Ghumare (MIT License)