Clawdemy Lessons

Orientation for the prompt-engineering lesson: the toolkit, prompt-fix vs code-fix triage, the versioning-and-testing discipline, and where prompts run out.

Preview of reading askFSDL, a real RAG Q&A app, end to end: the production decisions at each pipeline stage and a checklist you can reuse on any app.

A guided tour of LLMOps: the five pillars, a per-request log schema, evaluation in production, prompt versioning, and regression testing for safe changes.

A working picture of a hosted LLM: what it is at the API level, the generation loop, and the three limits (context, cost, latency) you design against.

What this opening lesson covers: the five parts of a minimal LLM app, prerequisites, where it fits in the track, and the skills you will walk away with.

Brief overview of the capstone: the track arc, three rules for reading an industry fireside, five durable bets, and three reader moves to act on next.

A roadmap to the augmented-LLM lesson covering RAG and tool use: what you will learn, where it fits, the prerequisites, and the read and practice time.

A primer on LLM agents: the loop, the three foundational patterns, the three tests for when to use one, the five failure modes, and how to operate one.

Orientation for the generative models track: what generative means, the four paradigms, prerequisites, and the math and time each lesson will ask of you.

Planning brief for the WGAN-GP lesson: learning outcomes, prerequisites, and scope for the Wasserstein distance, 1-Lipschitz critic, and gradient penalty.

Brief on training a variational autoencoder: the reparameterization trick, the closed-form Gaussian KL term, and the per-example reconstruction-plus-KL loss.

Orientation for the score matching lesson: the objectives, why the explicit form does not scale, denoising score matching, and the bridge to diffusion.

Overview of the normalizing flows lesson: learning outcomes, prerequisites, where it fits among generative paradigms, and the time and difficulty to expect.

What the maximum likelihood and forward-KL lesson covers: KL divergence, the derivation, prerequisites, learning outcomes, and time estimates.

Overview of the ELBO lesson: what you'll learn, prerequisites, the math tools involved, and how the latent-variable paradigm fits the generative track.

Overview of the GANs lesson: the minimax objective, deriving the optimal discriminator, the Jensen-Shannon divergence, and paradigm-level failure modes.

What the lesson on evaluating generative models covers: likelihood limits, FID and Inception Score, precision and recall, prerequisites, and time to budget.

Overview of the energy-based model lesson: what you will learn, where it fits, prerequisites, and the math, from the EBM density to the score-function escape.

A study guide to the DDPM diffusion lesson: prerequisites, learning outcomes, where it fits among score-based and SDE lessons, and read and practice time.

A brief on factoring distributions with the chain rule, training by negative log-likelihood, and enforcing causality in autoregressive models.

Editorial brief for the variational inference lesson: scope, capability gained, source, and how the ELBO and reparameterization set up control as inference.

Editorial brief for the value-based RL lesson: the Q-branch, Q-learning from Bellman optimality, dual-path Q-iteration, and the deadly triad.

Editorial brief for the RLHF lesson: scope, learning outcomes, source papers, and how the InstructGPT pipeline maps to a variational framework.

A guide to the RL fundamentals lesson: the MDP tuple, value functions, the Bellman equation, a worked 2-state solve, and the deep-RL dispatch table.

Editorial brief for the PPO lesson: how to derive the clipped surrogate from the on-policy stability problem and frame PPO as the RLHF workhorse.