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

Embedding Model Training Explained

This chapter explores the options for training embedding models, comparing the challenges of starting from scratch with the advantages of fine-tuning pre-trained models. It emphasizes the importance of selecting the right model for specific tasks and discusses the subjective nature of clustering methods.

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