// axioncore journal — theory, made visible
Concepts you can see move.
Long-form, animated essays on the theory underneath the tools — for the ideas that deserve more than a paragraph and a diagram once.
ARTICLES:02|PRICE:0.00|FORMAT:INTERACTIVE
ESSAY N° 001/Machine Learning Theory
Why Models Overfit: A Theory of Generalization
"The model memorized the data" is the surface explanation. Underneath it are empirical risk, hypothesis spaces, bias–variance, and the inductive biases that let a model guess correctly about points it has never seen.
Keywords — overfitting, generalization, bias-variance, regularization
Intermediate · 19 min readRead essay
ESSAY N° 002/AI Systems Engineering
From Model Orchestration to Harness Engineering: What Makes AI Production-Ready?
The demo works perfectly. The same system falls over in production. The model didn't get worse — it just lost the layer of engineering standing between raw intelligence and a system you can trust.
Keywords — harness engineering, AI agents, production AI, reliability
Intermediate · 13 min readRead essay