LessWrong (Curated & Popular) cover image

Scale Was All We Needed, At First

LessWrong (Curated & Popular)

00:00

Efficient Fine-tuning and Scaling Up of Language Models

This chapter explores the development of two algorithms for efficient fine-tuning of language models in various online environments. It discusses the tasks initially tried by OpenAI and DeepMind, the need for more compute and data, and the progress in alignment research and interpretability.

Play episode from 03:19
Transcript

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