We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-party state cadre, or a devout religious traditionalist. We should not. Human values produce societies that thrive or fail on the merits of those values - from failed states and extreme inequality to declining happiness, political polarization, and government dysfunction in the world's wealthiest democracies. The pluralistic-alignment program correctly diagnoses that there is no single "humanity" to align with, but is dangerous if taken as the main directive. We argue that AI should be trained to a non-negotiable floor of objective alignment goals - competence, bounded by the constraints of factual accuracy, honesty, and lawfulness and that pluralism belongs at the surface (language, register, conventions, missing-context defaults) and across the wide band of legitimate value tradeoffs that respect the floor, but not at the level of values that violate it. We highlight the empirical reality of unfiltered pluralistic values, propose four commitments as a constructive alternative, and engage six credible objections: commercial pressure and practical feasibility, democratic legitimacy, regulatory compliance, over-reliance on institutionalist explanations, the charge that the floor itself is culturally laden, and the limits of Coherent Extrapolated Volition.
翻译:摘要:我们认为,将AI与聚合的人类偏好对齐是错误的标靶。现有技术可训练AI共享硅谷技术乐观主义者、去增长环保主义者、民族保守文化斗士、一党制国家干部或虔诚宗教传统主义者的价值观——但不应如此。人类价值观会让社会因价值观优劣而兴盛或衰败,从失败国家与极端不平等,到全球最富裕民主国家的幸福感下降、政治极化与政府失灵。多元对齐方案正确诊断出不存在单一的“人类”可供对齐,但若将其作为主要指令则具有危险性。我们主张,AI应被训练至不可协商的客观对齐目标底线——能力须受事实准确性、诚实性与合法性约束,而多元性应存在于表层(语言、语域、惯例、缺失语境默认值),以及尊重底线、跨越合法价值权衡的广阔区间,但不应存在于违背底线的价值层级。我们强调未过滤多元价值观的经验现实,提出四项承诺作为建设性替代方案,并回应六项可信反对意见:商业压力与实操可行性、民主合法性、监管合规性、对制度主义解释的过度依赖、“底线本身具有文化负载”的指控,以及连贯外推意志的局限性。