Philosophical research in AI has hitherto largely focused on the ethics of AI. In this paper we, an ethicist of belief and a machine learning scientist, suggest that we need to pursue a novel area of philosophical research in AI - the epistemology of AI, and in particular an ethics of belief for AI, i.e., an ethics of AI belief. Here we take the ethics of belief, a field that has been defined in various ways, to refer to a sub-field within epistemology. This subfield is concerned with the study of possible moral, practical, and other non-alethic dimensions of belief. And in this paper, we will primarily be concerned with the normative question within the ethics of belief of what agents - both human and artificial - ought to believe, rather than with descriptive questions concerning whether certain beliefs meet various evaluative standards such as being true, being justified or warranted, constituting knowledge, and so on. We suggest four topics in extant work in the ethics of (human) belief that can be applied to an ethics of AI belief: doxastic wronging by AI; morally owed beliefs; pragmatic and moral encroachment on AI beliefs; and moral responsibility for AI beliefs. We also indicate an important nascent area of philosophical research in epistemic injustice and AI that has not yet been recognized as research in the ethics of AI belief, but which is so in virtue of concerning moral and practical dimensions of belief.

翻译：人工智能（AI）的哲学研究迄今主要聚焦于AI伦理。在本文中，我们——一位信念伦理学者与一位机器学习科学家——提出需要开拓AI哲学研究的新领域：AI认识论，特别是AI信念伦理，即AI信念的伦理规范。此处将信念伦理（该领域有多种界定）视为认识论的一个子领域，主要研究信念可能的道德、实践及其他非真理性维度。本文主要关注信念伦理中的规范性议题，即主体（包括人类与人工智能）应当相信什么，而非描述性问题（如特定信念是否符合真、确证、辩护或构成知识等评价标准）。我们提出人类信念伦理现有研究中可适用于AI信念伦理的四个议题：AI的信念性错误、道德应然信念、信念的实用与道德侵入、以及AI信念的道德责任。我们还指出，关于认知不正义与AI的重要新兴哲学研究领域尚未被确认为AI信念伦理研究，但因其涉及信念的道德与实践维度，实属该领域范畴。