causal
Bottom-Up Moral Machines Inherit Human Biases
Training machines to imitate human moral behavior in a bottom-up approach will incorporate the biases and limitations of the humans modeled, producing machines that are racist, sexist, and poor at reasoning about consequences versus rewards.
causalpending
Speaker
Derek LebenEvidence Quote
“you're probably going to incorporate all of the terrible biases and limitations of the humans that you're using to model your machine's behavior on”
Created: 6/13/2026, 12:30:07 AM
Your notes
Loading notes...