preference model

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

Everything said about preference model, oldest first

Jan 11, 2024 negative

Insight

Lambert: RLHF reward models lack inductive biases for true preferences

“In RLHF calling things a preference model is a little annoying because There's no inductive bias of what a preference is.”

Nathan Lambert Jan 11, 2024 ▶ 12:41 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.

preference model

Everything said about preference model, oldest first

Turn any episode into a week of clips.