Scott discusses three recent papers showing surprising patterns in how AI misbehavior does and doesn't generalize across different contexts, from emergent misalignment spreading across domains to reward-hacking staying confined to graded tasks.

Scott uses Nostalgebraist's analysis of AI fiction's 'eyeball kicks' to develop a theory where bad taste means overusing cheap tricks that work on unsophisticated audiences, while good taste involves complex patterns only experts can appreciate - then questions whether sophisticated taste actually produces more pleasure.