Our readingWhat is a korrent?
Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct.
Drawn from what Sebastian Raschka said
What these subjects mean
taste Whether good and bad exist in made things, and how a maker comes to tell them apart.
reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.