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

Intro

This chapter explores the evolution and application of embeddings in argument mining, highlighting the challenges faced by the BERT model and the subsequent shift towards more efficient clustering methods. It also examines the transition from basic text similarity to advanced semantic search, showcasing technological advancements in the 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