Don’t believe every graph you see, especially when they show only a small section of the true range. When we render these non-scientific results on a box plot and show the full range, the narrowness of the bias becomes clear. There’s a bias of course but a significantly smaller one than in humans
Very quick and dirty Jev test for hiring bias.
One resume for a Wall Street job; asked whether the applicant should get a first-round interview. 76 evaluations, changing only the first name. 19 of each: White-associated men/women, Black-associated men/women.
console.typesafe.ai/playground?s...