Our foundational work focuses on navigating ethical complexity in AI systems, starting with our position paper on pluralistic value alignment.
Our position paper introduces frameworks for AI systems to handle situations where multiple legitimate values conflict, moving beyond simple alignment to embrace the complexity of human moral reasoning.
Read the full paperWe're actively conducting research on pluralistic value alignment in AI systems. Our work explores the complex landscape of ethical decision-making in artificial intelligence.
Want to stay updated on our latest research? Contact us to join our mailing list.