AI Safety Fundamentals: Alignment cover image

On the Opportunities and Risks of Foundation Models

AI Safety Fundamentals: Alignment

CHAPTER

Introduction

Foundation models are any model that is trained on broad data, generally using self-supervision at scale. Current examples include BERT or BERT, Devlin et al. 2019, GPT-3, Brown and Radford 2021. Emergence means the behavior of a system is implicitly induced rather than explicitly constructed. Homogenization indicates consolidation of methodologies for building machine learning systems across a wide range of applications. It provides strong leverage towards many tasks, but also creates single points of failure.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner