kalomaze: transfer extrapolation should be a learned function, not a theory

kalomaze · x · 2026-09-12

Open-source researcher kalomaze threads on X about why extrapolating transfer is probably something that must be learned: his intuition stems from CoT/reasoning being a decomposition of problems into subroutines that compose generically, so good strategies transfer across very distinct domains.

In the quoted post he argues you don't need a strong mechanistic theory of transfer (which may not exist in closed form) before training — you need a strong learned function of transfer extrapolation for a given policy, which is constructible.

Related event: kalomaze: information asymmetry, not verifiability, drives RLVR generalization(9 posts)→

Original post →

More from AGI Musings

AGI Musings channel →