Manifold cover image

Omar Shams: AI Founder and Google AI Agent Lead — #89

Manifold

00:00

Exploring Scaling Laws and Phase Transitions in Language Models

This chapter examines the theoretical foundations of scaling laws in language models and the necessity for models that can account for various observed phenomena. It highlights a researcher's findings on outliers in language models and connects these insights to broader concepts such as phase transitions in physics, alluding to the search for more predictive quantitative measures in this field.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app