The Open Problems of the AI Alignment Field and their Cruxes
Previous: AI Safety InterventionsTL;DR: I made an overview of the open problems of AI alignment that reveals cruxes within those open problems and missed opportunities for formalization and collaboration. And CEV may deserve a second look.Epistemic status: Trying too much in too little time. I'm confident I have identified and modeled significant structure within the alignment field, but I urgently need feedback on specific gaps and this post is largely a call for that. My work was LLM-assisted,...
Read full article →