Administered by:
Well then.
“we demonstrate that language models embody covert racism in the form of dialect prejudice, exhibiting raciolinguistic stereotypes about speakers of African American English (AAE) that are more negative than any human stereotypes about African Americans ever experimentally recorded”
NatureAI generates covertly racist decisions about people based on their dialect - NatureDespite efforts to remove overt racial prejudice, language models using artificial intelligence still show covert racism against speakers of African American English that is triggered by features of the dialect.
Succubard's Library 
Who could *ever* have expected this.
Also: these LLM outputs are like holding up a mirror to ourselves. Some of it is not pretty.
@CelloMomOnCars And no one talks about how things could be worse because of network effects.
@ppatel it’s crazy how assuming the status quo is correct and should be copied infinitely leads to recreating existing problems. It’s almost like there’s flaws in the base assumptions that you have to make when creating AI systems