The Script That Was Built for AI (And That AI Has Never Heard Of)

In 1949, a self-taught scholar in Kankan, Guinea named Solomana Kante designed a writing system from scratch. He was responding to a claim that African languages could not be written. He took that as a challenge and spent years analyzing the phonological structure of Manding languages, then built a script that encodes their sounds with a precision that linguists and engineers spend careers trying to achieve in synthetic alphabets. Every phoneme gets exactly one character. Every character represents exactly one phoneme. Tone is marked explicitly. No digraphs. No silent letters. No exceptions. The script is called N'Ko, which means "I say" in every Manding language. It has 40 million speakers across Guinea, Mali, Cote d'Ivoire, Senegal, Burkina Faso, and diaspora communities worldwide. That is the paradox I spent the last several months trying to fix. Here is what I found. Before building anything, I wanted to understand the problem precisely. Not "N'Ko is underrepresented in training data" as a vague statement, but a precise measurement of what that underrepresentation looks like inside a large language model.