Course
Conceptual LLM Mechanics
Understand how language models work: from training to tokens to inference.
Modules
7 total
How LLMs Are Created
ApplyUnderstand how pretraining, post-training, fixed weights, and inference-time context shape assistant behavior — and diagnose which layer produced a wrong answer.
How An LLM Becomes An Assistant
ApplyUnderstand architecture, weights, checkpoints, the learning loop, and how one model becomes a deployed assistant.
Transformers, Attention, And Context
Build a conceptual model of transformers, attention, and context influence.
In-Context Learning And Prompt Influence
Explain why prompts, examples, and retrieved context influence behavior.
Sampling, Variability, And Evals
Connect temperature, sampling, and output variability to evals.
Inference Runtime: Prefill, Decode, KV Cache
Connect prefill, decode, KV cache, streaming, output length, latency, and cost.
Lab 1: AI-Native Mindset Challenge
LabBuild a support-ticket router and practice deterministic boundaries around probabilistic model output.