Blog
Robótica & RL
Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction
arXiv:2607.00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing that preferences are layered, dynamic, and constructed through interaction--particularly with adaptive technologies. As AI systems become more persistent, personalized, and socially embedded, they increasingly participate in shaping what people attend to, value, and endorse over t...
arXiv cs.AI
·Max Kanwal, Caryn Tran
·
// relacionados
Leia também
Editorial
RynnValue: o relógio do vídeo como recompensa para robôs
Blog
Anthropic aplica marca d'água a todas as saídas do Claude globalmente, com marcas que "podem persistir mesmo após alguma edição"
Blog
webAI lança TwIL-LM: uma família de modelos de lógica formal de 1,7B e 3B para autoformalização em hardware local
Blog