RLHF preference data

1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jan 11, 2024 by Nathan Lambert · across every show →

Everything said about RLHF preference data, oldest first

Jan 11, 2024 positive

Opinion

Lambert: OpenAI trains its RLHF models primarily on good-vs-good answer comparisons

“I think open AIs of the world are all in good answer, and have learned to eliminate everything else.”

Nathan Lambert Jan 11, 2024 ▶ 43:19 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

RLHF preference data

Everything said about RLHF preference data, oldest first

Turn any episode into a week of clips.