Rl From Human Feedback Rlhf
Sifting through hundreds of thousands of hours of indexed videos
Rl From Human Feedback Rlhf
Sifting through hundreds of thousands of hours of indexed videos
Rl From Human Feedback Rlhf
3
Mentions
579.0K
Views

“myself and Paul Cristiano and some of the anthropic co-founders had invented this technique called RL from human feedback and that was designed to help steer models in um uh you know in a direction to...”

“the initial method for unhobbling language models”

“Technique for scaling models and safety.”
Arcmira media summary
Arcmira tracks where RL from human feedback (RLHF) is discussed across indexed YouTube videos, transcripts, channels, and related entities.
myself and Paul Cristiano and some of the anthropic co-founders had invented this technique called RL from human feedback and that was designed to help steer models in um uh you know in a direction to follow human intent... even with the more primitive technique RL from human feedback it wasn't working with the small language models with you know GPT1 that we applied it to
the initial method for unhobbling language models
Technique for scaling models and safety.
Arcmira tracks 3 indexed media appearances or mentions for RL from human feedback (RLHF), tied to source videos, channels, and transcript-derived context.
Arcmira uses indexed YouTube videos and transcripts. Representative source evidence on this page includes "Anthropic CEO Dario Amodei: AI's Potential, OpenAI Rivalry, GenAI Business, Doomerism" with transcript-derived context and links when available.
RL from human feedback (RLHF) is connected to OpenAI, Anthropic, Amazon in Arcmira's media graph.