How AI Is Built cover image

#022 The Limits of Embeddings, Out-of-Domain Data, Long Context, Finetuning (and How We're Fixing It)

How AI Is Built

00:00

Challenges in Deep Learning Embeddings

This chapter explores the difficulties encountered with embeddings in deep learning, emphasizing the significance of data quality and the complexities of evaluating similarity in embeddings. It sets the stage for a series on embeddings, outlining strategies for improving classifier performance and considerations for long context settings.

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