OpenAI says ChatGPT treats us all the same (most of the time)
SMRTR summary
ChatGPT shows gender and racial stereotypes in 0.1-1% of responses based on users' names, with newer models like GPT-4 displaying less bias, though open-ended tasks remain more prone to stereotyping.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article