KL constraint

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 KL constraint, oldest first

Jan 11, 2024 neutral

Insight

Lambert: RLHF fails completely without a KL divergence constraint

“The KL constraint prevents that. There's not that much documented work on that, but there's a lot of people that know if you take that away, it just doesn't work at all.”

Nathan Lambert Jan 11, 2024 ▶ 35:51 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.

KL constraint

Everything said about KL constraint, oldest first

Turn any episode into a week of clips.