RLHF
Type: Concept
Reinforcement Learning from Human Feedback (appears as 'RHF' in transcript); described as learning via preference comparisons and rewards.
Field: Machine learning; AI alignment
Domain: Artificial Intelligence
Mentioned in 1 podcast episode
Who brought it up
- The $1B Al company training ChatGPT, Claude & Gemini on the path to responsible AGI | Edwin Chen on Lenny's Podcast
RHF became very dominant.