Sign up to save your podcasts
Or
Share Interconnects
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Interconnects
Interconnects episodes
- 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.18 min - Synthetic data: Anthropic’s CAI, from fine-tuning to pretraining, OpenAI’s Superalignment, tips, types, and open examples
Synthetic data is the accelerator of the next phase of AI — what it is and what it means.
For the post, see it here: https://www.interconnects.ai/p/llm-synthetic-data
18 min
About Interconnects
From the publisher's feed
Audio essays about the latest developments in AI and interviews with leading scientists in the field. Breaking the hype, understanding what's under the hood, and telling stories.
href="https://www.interconnects.ai?utm_medium=podcast" rel="noopener noreferrer">www.interconnects.ai
More shows like Interconnects
The Twenty Minute VC (20VC): Venture Capital | Startup Funding | The Pitch
542 Listeners
The a16z Show
1,089 Listeners
ChinaTalk
288 Listeners
Practical AI
203 Listeners
Google DeepMind: The Podcast
205 Listeners
Last Week in AI
315 Listeners
Machine Learning Street Talk (MLST)
98 Listeners
Dwarkesh Podcast
565 Listeners
No Priors: Artificial Intelligence | Technology | Startups
141 Listeners
Latent Space: The AI Engineer Podcast
102 Listeners
This Day in AI Podcast
222 Listeners
"Econ 102" with Noah Smith and Erik Torenberg
145 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
455 Listeners
AI + a16z
30 Listeners
Training Data
39 Listeners