LessWrong AI
· Communities
The iVAIS Manifesto: Safety Through Character, Not Compliance
Masaharu Mizumoto, Mads Udengaard, Rujuta Karekar, Mayank Goel, Daan Henselmans, Nurshafira Noh, Saptadip Saha, Pranshul BohraTL;DRAI safety requires a shift to character-based, virtue-centered alignmentRule-based and principle-based alignment are conceptually insufficientConstitutional AI is still action-based ethicsM