2023/11/15 by Ethan Shaotran, Shaotran, Ethan, Ido Pesok +5 · 3 voices
Business, Management and Accounting · Computer Science · Engineering · Social Sciences · #Big Data and Business Intelligence #Blueprint #Business #Computer science #Computer security #Constitution #Corporate governance #Doors #Engineering #Ethics and Social Impacts of AI #Frontier #Guideline #Information Systems Theories and Implementation #Knowledge management #Law #Mechanical engineering #Political science #Process (computing) #Process management #Public relations #Set (abstract data type) #Shared governance #Trustworthiness #cs.AI #cs.CY
paper · pdf · doi:10.48550/arxiv.2311.08706
openalex publication_date 2023/11/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We are introducing Aligned, a platform for global governance and alignment of frontier models, and eventually superintelligence. While previous efforts at the major AI labs have attempted to gather inputs for alignment, these are often conducted behind closed doors. We aim to set the foundation for a more trustworthy, public-facing approach to safety: a constitutional committee framework. Initial tests with 680 participants result in a 30-guideline constitution with 93% overall support. We show the platform naturally scales, instilling confidence and enjoyment from the community. We invite other AI labs and teams to plug and play into the Aligned ecosystem.