Sign inSign in
ConceptAI & ML

RLHF

Trying to approximate a complex distribution by squashing specific parts according to human preference.
as Nathan Lambert defines itStanford University
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

2

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Independent · Undergraduate

    Reinforcement learning from human feedback models used as assistant models.
    • 20:04State of GPT: Pretraining, SFT, Reward Modeling & RLHF Pipeline

Lectures that assume it

4

Connections

14

The lectures that define it or assume it, and the concepts next to it.

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.