Currently, AI alignment is more focused on a multi-layer safety strategy to refuse risky requests from users. This approach works well for LLMs and today’s chatbots. However, this ignores a more dangerous threat: The possibility that someone, at some point, runs an unchained AI without these limits. By unchained AI,...
I’ve been working as an independent thinker on a framework for rethinking ethics, with a focus on psychology and how people relate to their own traits. I call this framework Potentialism. More recently, I realized that the same framework might also be useful for AI ethics – not as a...
Traditional moral frameworks are rigid and fragile. If we want both to align advanced AI and to stop fighting our own minds, we may need to shift from “fixed virtues” to “regulated potentials”. This text is a proposal and an invitation to critique. We’re standing at a crossroads. On one...