Back to Applied AI Engineering
🧠
Phase 1
Foundations: LLM Terminology & Mechanics
How Transformers actually work, how a model goes from raw internet text to something that follows instructions, and what's really happening when you turn the temperature dial.
1
Transformers & Attention, Explained Without the Math
How self-attention actually works, why it replaced recurrent networks, and why every modern chat model is a decoder-only Transformer stack.
transformersattentiondeep-learning
2
Tokens, Context Windows & Latent Space
What a token actually is, why context windows are a hard ceiling rather than a soft suggestion, and how embeddings turn meaning into geometry.
tokenscontext-windowembeddings
3
Pre-training, Post-training & Inference
The three-stage model lifecycle — and why nothing in it directly rewards being correct, which is the actual, mechanical reason LLMs hallucinate.
pretrainingpost-trainingrlhf