Chess as a Testing Grounds for the Oracle Approach to AI Safety

10/06/2020
by   James D. Miller, et al.
0

To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages. This paper proposes a possibly practical means of using machine learning to create two classes of narrow AI oracles that would provide chess advice: those aligned with the player's interest, and those that want the player to lose and give deceptively bad advice. The player would be uncertain which type of oracle it was interacting with. As the oracles would be vastly more intelligent than the player in the domain of chess, experience with these oracles might help us prepare for future artificial general intelligence oracles.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/07/2021

Using reinforcement learning to design an AI assistantfor a satisfying co-op experience

In this project, we designed an intelligent assistant player for the sin...
research
05/07/2021

AI in (and for) Games

This chapter outlines the relation between artificial intelligence (AI) ...
research
11/01/2021

Gomoku: analysis of the game and of the player Wine

Gomoku, also known as five in a row, is a classical board game, ideally ...
research
09/06/2011

Measuring Intelligence through Games

Artificial general intelligence (AGI) refers to research aimed at tackli...
research
07/19/2020

Expected Utilitarianism

We want artificial intelligence (AI) to be beneficial. This is the groun...
research
12/07/2022

Improving Deep Localized Level Analysis: How Game Logs Can Help

Player modelling is the field of study associated with understanding pla...
research
04/04/2023

Rolling the Dice: Imagining Generative AI as a Dungeons Dragons Storytelling Companion

AI Advancements have augmented casual writing and story generation, but ...

Please sign up or login with your details

Forgot password? Click here to reset