The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

Are Emergent Behaviors in LLMs an Illusion? with Sanmi Koyejo - #671

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

Understanding Transition Points in Language Model Performance

This chapter examines the interplay between model complexity and performance in large language models, focusing on how scaling laws help predict optimal parameter thresholds. It underscores the significance of task-agnostic scaling laws while cautioning against the complexities of their application and the critical role of metric selection in evaluating model effectiveness.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner