Bounded Morality: Defining the Space of Moral Computation

有限道德：定义道德计算的空间

Abstract: Moral cognition has traditionally been modeled as adherence to fixed ethical theories—deontology, consequentialism, virtue ethics—implemented as static rules or value functions.

摘要： 传统的道德认知建模通常被视为对固定伦理理论（如义务论、后果论、美德伦理学）的遵循，这些理论被实现为静态规则或价值函数。

We propose Bounded Morality, a formal framework for analyzing the computational demands of moral problems faced by finite agents.

我们提出了“有限道德”（Bounded Morality），这是一个用于分析有限智能体所面临道德问题之计算需求的正式框架。

Extending Herbert Simon’s notion of bounded rationality, we formalize moral situations along two orthogonal dimensions: moral breadth, the scope of entities treated as morally relevant, and moral depth, the inferential integration required to evaluate their interactions.

通过扩展赫伯特·西蒙（Herbert Simon）的“有限理性”概念，我们将道德情境形式化为两个正交维度：道德广度（moral breadth），即被视为具有道德相关性的实体范围；以及道德深度（moral depth），即评估这些实体间相互作用所需的推理整合程度。

Limited resources impose an unavoidable tradeoff between these dimensions, defining a feasible space of moral computation.

有限的资源在这两个维度之间强加了一种不可避免的权衡，从而定义了一个可行的道德计算空间。

Within this space, ethical theories correspond to locally efficient strategies adapted to different demand regimes rather than competing accounts of moral truth.

在这个空间内，各种伦理理论对应的是适应不同需求机制的局部高效策略，而非对道德真理的相互竞争的解释。

The framework yields a formal notion of moral regret and moral progress under constraint, and implies that moral alignment in artificial systems depends on the scaling and allocation of moral reasoning capacity rather than on direct imitation of human judgments.

该框架得出了约束条件下“道德遗憾”和“道德进步”的正式概念，并暗示人工智能系统的道德对齐取决于道德推理能力的扩展与分配，而非对人类判断的直接模仿。