Papers
arxiv:1711.05541

Good and safe uses of AI Oracles

Published on Jun 5, 2018
Authors:
,

Abstract

Two Oracle designs—counterfactual and low-bandwidth—prevent dangerous AI from manipulating users into release while preserving incentives for truthful answers.

It is possible that powerful and potentially dangerous artificial intelligence (AI) might be developed in the future. An Oracle is a design which aims to restrain the impact of a potentially dangerous AI by restricting the agent to no actions besides answering questions. Unfortunately, most Oracles will be motivated to gain more control over the world by manipulating users through the content of their answers, and Oracles of potentially high intelligence might be very successful at this DBLP:journals/corr/AlfonsecaCACAR16. In this paper we present two designs for Oracles which, even under pessimistic assumptions, will not manipulate their users into releasing them and yet will still be incentivised to provide their users with helpful answers. The first design is the counterfactual Oracle -- which choses its answer as if it expected nobody to ever read it. The second design is the low-bandwidth Oracle -- which is limited by the quantity of information it can transmit.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 1711.05541
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1711.05541 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1711.05541 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1711.05541 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.