Jason Wei, AI Researcher, OpenAI: Some intuitions About Large Language Models

Abstract

Jason Wei, AI Researcher, OpenAI

Some intuitions About Large Language Models

An open question these days is why large language models work so well.

In this talk I will discuss six basic intuitions about large language models. These intuitions are a lens to understanding why language models work and how they will continue to improve as we scale them in the future. Many of them are inspired by manually examining data, which is an exercise that I’ve found helpful and would recommend.