Last Week in AI cover image

#126 - few have tried ChatGPT, Baidu’s $145M AI fund, AI job culling, OpenAI grant program

Last Week in AI

00:00

Exploring Scaling Laws and Limitations of Language Models

This chapter discusses a new research paper that expands on chinchilla scaling laws for training large language models with minimal data. The speakers highlight the limitations of transformer models, particularly in complex reasoning and compositional tasks, comparing their behavior to human study habits.

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