RL in language models

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 RL in language models, oldest first

Jan 11, 2024 negative

Opinion

Lambert: Reinforcement learning in language models is contrived and not real RL

“And the view of RL in language models is pretty contrived already. So it's not like we're doing real RL.”

Nathan Lambert Jan 11, 2024 ▶ 7:59 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.

RL in language models

Everything said about RL in language models, oldest first

Turn any episode into a week of clips.