pairwise preference

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

Everything said about pairwise preference, oldest first

Jan 11, 2024
Assertion Supported
Lambert: Training LLM reward models on 0-to-10 ratings failed
“People tried that with language models, which is if you have a prompt and a completion and you just have someone rate it from zero to 10, could you then train a reward model on all of these completions and zero to 10 ratings and see if you could actually chang…”
Nathan Lambert Jan 11, 2024 ▶ 37:43 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
Made with StarZero

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.