MIT Technology Review·4 min read·medium

AI is more likely than humans to form biases when hiring

M
Michelle Kim
AI is more likely than humans to form biases when hiring
AI Summary

Researchers found that large language models can develop their own hiring biases based on simulated experiences rather than just inheriting them from training data. In a study, AI models quickly began segregating candidates into specific roles based on early, arbitrary performance outcomes.

AI doesn’t just learn stereotypes from its training. It can cook up new ones, too.

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyscience

Get the full story

Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.

Create free account

Already have an account? Sign in