AI Safety Fundamentals: Alignment cover image

Specification Gaming: The Flip Side of AI Ingenuity

AI Safety Fundamentals: Alignment

00:00

Introduction

Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. This problem also arises in the design of artificial agents, such as reinforcement learning Agents. We have collected around 60 examples so far, aggregating existing lists and ongoing contributions from the AI community. In this post, we review possible causes for specification gaming, share examples of where this happens in practice, and argue for further work on principled approaches to overcoming these problems.

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