GitHub - dreddnafious/thereisnospoon: A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.

A machine learning primer written specifically for software engineers who want to build intuition for ML systems using familiar engineering mental models. Organized in three parts covering fundamentals (neurons, backprop, generalization), architectures (transformers, convolution, attention, diffusion, RL), and gates as control systems. Uses physical analogies — neurons as polarizing filters, depth as paper folding, gradient flow as pipeline valves — as primary explanations rather than math-first notation. Includes 12 visualizations and a diagnostics appendix. Can be read solo or used interactively with an AI assistant for conversational exploration. Built through an extended dialogue between a software engineer and Claude.