Google DeepMind: The Podcast cover image

Speaking of intelligence

Google DeepMind: The Podcast

CHAPTER

Language Models - Toxicity

Language models have been shown to be repeatedly homophobic, racist, sexist and islam phobic. They sexualize certain groups of women and associate terms of violence with moslems. The challenge of detoxifying language models is a major focus of language researches like lisa anne hendrix.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner