Why does GPT rank equally-qualified resumes differently based on names? Looking at how GPT represents the 800 names in our experiment as embeddings provides a clue. bloom.bg/3It4cE4

Read our methodology at the end of the main article: www.bloomberg.com/graphics/202...github.com/BloombergGra...

GitHub - BloombergGraphics/2024-openai-gpt-hiring-racial-discrimination: Data and materials to reproduce Bloomberg's investigation into racial and gender bias in OpenAI's GPT

Data and materials to reproduce Bloomberg's investigation into racial and gender bias in OpenAI's GPT - BloombergGraphics/2024-openai-gpt-hiring-racial-discrimination