Apparently the biases in the output tend to be stronger than what is in the trai... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

bonzini on Feb 22, 2024 | parent | context | favorite | on: Google to pause Gemini image generation of people ...

Apparently the biases in the output tend to be stronger than what is in the training set. Or so I read.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact