Sign up to save your podcasts
Or
Share The DPO debate: Do we need RL for RLHF?
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
The DPO debate: Do we need RL for RLHF?
Direct vs. RL methods for preferences, more RLHF models, and hard truths in open RLHF work. We have more questions than answers.
Read the full post here.
View all episodes
By Nathan Lambert
4.1
99 ratings
Direct vs. RL methods for preferences, more RLHF models, and hard truths in open RLHF work. We have more questions than answers.
Read the full post here.
More shows like Interconnects
View all
a16z Podcast
1,036 Listeners
The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch
519 Listeners
ChinaTalk
269 Listeners
Practical AI
192 Listeners
Google DeepMind: The Podcast
198 Listeners
Last Week in AI
287 Listeners
Machine Learning Street Talk (MLST)
88 Listeners
Dwarkesh Podcast
417 Listeners
No Priors: Artificial Intelligence | Technology | Startups
121 Listeners
This Day in AI Podcast
201 Listeners
Latent Space: The AI Engineer Podcast
75 Listeners
"Econ 102" with Noah Smith and Erik Torenberg
146 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
461 Listeners
AI + a16z
31 Listeners
Training Data
43 Listeners