920: In Case You Missed It in August 2025
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Evolving Dynamics of AI Training Phases
This chapter explores the complexities of reinforcement learning from human feedback in training large language models. It highlights the shifting dynamics between pre-training and post-training phases, as well as the increasing importance and cost of effective post-training to ensure desirable AI outcomes.
Transcript
Play full episode
