The Expensive-Loop Problem

LLMs are amazing at tasks where they have tight and legible feedback loops. Domains where experiments are quick, deterministic and cheap. I will call these domains "cheap-loop" domains.Presumably, this is mostly a result of the dynamics of LLM training. It's easier to train models in domains where the AI lab can cheaply and quickly assign reward to them. The majority of "computer-checkable" work is in this category1. Conversely, most non-"computer-checkable" tasks are costly or slow to assign…