flâneur — a map of the web's best reading

Optimisation over non-stationary distributions creates weirder minds — LessWrong

lesswrong.com · 2,540 words · saved by 1 readers

TLDR: Sequentially mixing training objectives incentivises different training dynamics depending on the distinguishability of the training environmen…

x Optimisation over non-stationary distributions creates weirder minds — LessWrong AI Frontpage 36 Optimisation over non-stationary distributions creates weirder minds by Samuel Ratnam , Pjain 6th Jun 2026 4 min read 8 36 TLDR: Sequentially mixing training objectives incentivises different training dynamics depending on the distinguishability of the training environments and the amount of pressure for shared circuitry. We classify these patterns into three classes: ecological generalists, conditional policies, and strategy churn. We suggest that careful consideration of the pressures of non-st

Explore this link on the map →

related reading