> What about cases where the features just merely correlated with a subpopulation of a protected class?
This is just Simpson's paradox [1] which is notoriously hard to identify because you have to compare the overall with the breakdown. As you say, current-AI probably already has such biases.
This is just Simpson's paradox [1] which is notoriously hard to identify because you have to compare the overall with the breakdown. As you say, current-AI probably already has such biases.
[1] https://en.wikipedia.org/wiki/Simpson%27s_paradox