Command Palette

Search for a command to run...

PodMine

Sean Kim

Matches in: Person
1 episode
Oct 16, 2025• Latent Space: The AI Engineer Podcast

Why Fine-Tuning Lost and RL Won

A deep dive into the evolution of OpenPipe from fine-tuning to reinforcement learning, culminating in its acquisition by CoreWeave, exploring challenges in AI model training, reward functions, and the future of continual learning for AI agents.