Mathematical Thinking for AI

Mathematical Thinking for AI, Part 3: Invariance

Before a system learns anything, it decides which differences are noise. That decision cannot come from the data, and it sets a ceiling nothing…

Aug 9 • Hugo

Mathematical Thinking for AI, Part 2: Metric

Resemblance is an argument. Distance is a number. Every embedding you query rests on pretending they are the same, and on one axiom that bends whatever…

Aug 8 • Hugo

Mathematical Thinking for AI, Part 1: Linearity

Ten times the input, ten times the output, no surprises. That refusal of surprise is why anything computes at all, and it quietly forbids the one thing…

Aug 6 • Hugo

Mathematical Thinking for AI, Part 0: The Ideas Beneath the Equations

A series on twelve mathematical ideas that decide what a machine can know.

Aug 5 • Hugo

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts