Skill Suites
Code-first guides on AI, DevOps, and shipping software
Real proof-of-concepts you can run today. No fluff, no filler, just working examples.
Latest articles
-
Multi-Head Attention Explained: Why 64 Heads Instead of One
Multi-head attention explained from first principles: why a single softmax is not enough, what a head actually is, and the KV cache…
-
Inside One Transformer Block: The Residual Stream and Its Seven Matrices
A transformer block takes 8,192 numbers in and returns 8,192 out. Follow the residual stream, the seven matrices, and what each of…
-
Byte-Pair Encoding Explained: How LLMs Turn Text Into Tokens
How byte-pair encoding turns text into tokens, walked merge by merge on a four-word corpus, plus why it breaks arithmetic, spelling and…
-
How an LLM Answers a Question: The Complete Inference Path
Trace LLM inference end to end: seven tokens, an embedding lookup, 80 identical layers, sampling, and the memory bandwidth floor that caps…
-
The Calculus Behind Backpropagation: Every Derivative, From First Principles
The calculus behind backpropagation, derived from first principles: the nudge ratio, the power rule, the chain rule, partial derivatives, and the fan-out…
-
How Neural Networks Learn: From One Neuron to Backpropagation, Concept by Concept
How do neural networks learn? Build it from scratch, concept by concept — from a single neuron to weighted sums, ReLU, loss,…
-
The On-Prem LLM Decision: Why the Model Is the Easy Part
An on-prem LLM is no longer a capability gamble — it is an MLOps platform you must build. The trade-offs, break-even math,…
-
Applied Cryptography & Secure Protocols: The Complete Reference
AEAD, hashing, key exchange, TLS 1.3, JWT pitfalls, and threat modeling — a complete, defensive applied-cryptography reference for system design interviews.
-
Performance & Queueing Theory: Little’s Law, Tail Latency & Amdahl
Little’s Law, the utilization-latency knee, tail-at-scale, Amdahl’s law, and the Universal Scalability Law — a complete performance reference for system design interviews.
