There Is No Spoon — A Machine Learning Primer

An ML primer built from first principles targeting experienced software engineers. Distinguishing approach: physical and engineering analogies as primary explanations (neurons as polarizing filters, depth as paper folding, gradient flow as pipeline valves, chain rule as gear train), with math as supporting detail. Three-part structure: Fundamentals (neuron, composition, optimization, generalization, representation), Architectures (combination rule family, transformer, training frameworks, topology matching), and Gates as Control Systems. Built through conversational exploration between an engineer and Claude. The README positions it as "closer to a distilled mentorship than a reference document" and encourages interactive exploration with AI agents — "The primer is the map. The conversation is the territory."

Repository: single markdown file (ml-primer.md, 989 lines) with 12 inline matplotlib-generated figures. Python scripts to regenerate figures. 14 commits, MIT license, tags: primer, engineering, machine-learning, tutorial, deep-learning, transformers, neural-networks, fundamentals.