RHf / RLHF

Type: Concept

As of November 2026, RHf / RLHF has been mentioned in one podcast episode on Lenny's Podcast (Dec 2025). Referenced as dominant post-training approach (reinforcement learning/human feedback) in model development history.

In machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent with human preferences. It involves training a reward model to represent preferences, which can then be used to train other models through reinforcement learning.