Connected by a concept
Fundamentals
6 articles across the publication.
Why AI Requests Wait: Bounded Queues and Deadlines
Use a worked queue example to understand overload, admission limits, deadlines, retries, and the difference between offered and successful throughput.
Why More AI Replicas Do Not Immediately Fix a Spike
Trace demand through an autoscaling controller, provisioning, model startup, and readiness. Calculate the backlog accumulated before new capacity can help.
Before generation, there was representation.
From term counts to embeddings: the choices that determine what a language system can compare.
Simple operations. Learned representations.
Follow a signal through a neural network, then follow the error back to understand what training changes.
The context is a design decision.
What a model sees is a product of selection, permissions, and time—not just the size of a context window.
What does it actually mean for a machine to learn?
Start with the gap between memorizing examples and learning a pattern that survives new data.