How Well Do Models Follow Their Constitutions? 事件

How Well Do Models Follow Their Constitutions? arXiv:2605.24229v1 Announce Type: new Abstract: Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's Model Spec (OpenAI, 2025a), integrated into post-training via methods like character training (Anthropic, 2024) and deliberative alignment (Guan et al., 2024). These documents serve a governance function, but it is unclear how well models actually fol