factual

AI Reads Sex From Retinal Images Humans Cannot

AI trained on hundreds of thousands of retinal images with known sex can determine whether an eye is male or female with about 98% accuracy, a task at which human retinal experts have no clue, demonstrating that machines see features humans cannot—even though we don't know what those features are.

factualpending

Speaker

Eric Topol

Evidence Quote

“we still don't know what those features are that machines are picking up when they were fed... hundreds of thousands of retinal images with a known gender”

Source

162 - Medical Intelligence— Making Sense with Sam Harris
Created: 6/14/2026, 2:12:33 AM

Your notes

Loading notes...