How Machines Learn
An accessible explanation of how AI systems learn through pattern fitting, using analogies like dart throwing to explain the core concepts of data, models, and loss functions.
Notes on engineering, performance, and developer experience.
Showing all 8 posts
An accessible explanation of how AI systems learn through pattern fitting, using analogies like dart throwing to explain the core concepts of data, models, and loss functions.
Java’s data types, wrapper classes, and concurrency helpers look excessive until you see the trade-offs they unlock.
Legacy syntax, paradigm overload, and a forgiving runtime make JavaScript tough on newcomers, but understanding those quirks helps.
A playful look at Java’s entry point, file conventions, and curly-brace culture, and why the verbosity pays off in large systems.
Reflecting on why machine learning feels more like tacit, embodied expertise than conscious reasoning—and what that means for AI hype.
This post showcases the power of MDX by combining Markdown with React components for rich, interactive content.
Kickstarting this blog with a few thoughts on what will land here and why it exists.
Why treating programming as a bundle of practiced skills—rather than pure theory—helps developers escape plateaus.