Week 1 shifts to knowledge representation: propositional logic syntax, model checking, Modus Ponens/Resolution inference, CNF conversion. Projects: Knights (logic puzzles) and Minesweeper (probabilistic inference).
Week 2 shifts from deterministic to probabilistic: Bayes rule, Bayesian nets with D-separation, Markov chains, PageRank random walks. Projects: Heredity (genotype inference) and PageRank (web ranking).
Week 3 tackles optimization: hill climbing, simulated annealing escaping local optima, CSP framework with AC-3 arc consistency, backtracking with MRV/degree heuristics. Project Crossword builds a crossword puzzle generator.
Week 4 enters ML: supervised classification (k-NN, SVM, Perceptron), model evaluation, RL basics (MDP, Q-learning, ε-greedy). Projects: Shopping (purchase prediction with k-NN) and Nim (learning to play via Q-learning).
Week 5 enters deep learning: perceptron to multi-layer nets, backprop chain rule, loss functions, optimizers, TensorFlow/Keras modeling, CNN conv/pool. Project Traffic trains CNN to classify traffic signs.
Week 6 processes natural language: N-gram conditional probability & smoothing, CFG syntax parsing with CYK, TF-IDF vector retrieval, attention mechanism & Transformer basics. Projects: Parser (syntactic generation) and Questions (TF-IDF QA system).
Synthesis 1: Tracing how seven weeks form a deliberate knowledge arc from symbolic search to language models, revealing the design philosophy from classical AI to modern ML.
Synthesis 2: Complete comparison of 12 projects — core algorithms, LOC estimates, difficulty tiers, check50 acceptance criteria, transferable skills. With difficulty grading and learning sequence advice.
Series finale: Retrospecting timeless core from 7 weeks/12 projects, gaps in 2020/2023 recordings vs 2026 reality, free OCW route completeness, and forward roadmap (Transformers, LLM fine-tuning, RAG, Agents, Evaluation).
Week 0 opens with search algorithms: BFS for shortest paths, Minimax for adversarial play, Alpha-Beta for pruning. Two projects: Degrees (BFS) and Tic-Tac-Toe (Minimax).
AI pushes execution cost toward zero. People with good taste create more value; people with poor taste create more garbage. The difference is not whether you can use AI, but whether your mind contains something worth amplifying before you use it. This series documents my attempt to sharpen judgment systematically.
A Product Builder runs the full loop from problem discovery to design to build, alone. The core difference from a PM: PMs influence execution through authority, Product Builders influence it by directly shipping working products. LinkedIn replaced its APM program with an Associate Product Builder track, and PayFit defined the role back in 2019.
Warp evolved from a Rust-powered modern terminal into an AI Agent-integrated development environment (ADE), open-sourced under AGPL in April 2026, with over 700,000 developer users.
gstack is Garry Tan's open-source Claude Code skills toolkit. Its 20 specialized skills transform a solo developer into an entire engineering team — automating everything from product planning and design review to code review, QA, and deployment.
NobodyClimb uses RAG to tackle scattered climbing route information, ties quota limits to community engagement, and leverages Cloudflare Workers AI to bring inference costs close to zero.