AI is more likely than humans to form biases when hiring
MIT Technology Review AI Michelle Kim
Researchers found that large language models form stereotypes and biases when making hiring decisions, and they stereotype job applicants more than humans do in equivalent scenarios. In a simulated hiring game across 40 rounds with four fictional ethnic groups, OpenAI's o3 model scored 1.83 on a segregation scale where humans scored 0.84, with newer reasoning models showing even stronger biases. The findings highlight risks as companies deploy AI to screen résumés and conduct interviews, particularly as models gain memory and personalization features that could amplify learned biases over time.
Why it matters
The next time you apply for a job, AI may screen your résumé before any human sees it. But there’s good reason to question whether AI will judge you fairly. Researchers already know that LLMs pick up human biases from their training data. New research suggests that LLMs can also develop their own biases from…
