-
Positional Encoding Explained: How Transformers Learn Word Order (Ep:04.04)
Attention is mathematically blind to sequence order — swap two tokens and every output is just the same values, permuted. Module 4 of From Zero to Agents derives sinusoidal positional…
-
Learned Q, K, V Explained: What Makes Attention Actually Trainable (Ep:04.02)
Attention only becomes powerful once the query, key, and value projections are learned rather than reused from static embeddings. Module 4 of From Zero to Agents trains a real attention…
-
The Math Behind Every LLM, in Five Steps: Vectors to Cross-Entropy Loss
One continuous derivation connects vectors, matrices, gradients, and probability into the exact training objective behind every modern language model. Here’s the full arc, with the reasoning that forces each step.
-
Matrices — Organized, Simultaneous Dot Products (Ep:02.01)
A matrix is just organized, simultaneous dot products. Module 2 of From Zero to Agents builds matrix multiplication from first principles and uses it to fully decode the real attention…
