Shutdown Safety Valves for Advanced AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Conitzer, Vincent
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918378422140928
author Conitzer, Vincent
author_facet Conitzer, Vincent
contents One common concern about advanced artificial intelligence is that it will prevent us from turning it off, as that would interfere with pursuing its goals. In this paper, we discuss an unorthodox proposal for addressing this concern: give the AI a (primary) goal of being turned off (see also papers by Martin et al., and by Goldstein and Robinson). We also discuss whether and under what conditions this would be a good idea.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07315
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Shutdown Safety Valves for Advanced AI
Conitzer, Vincent
Artificial Intelligence
Machine Learning
One common concern about advanced artificial intelligence is that it will prevent us from turning it off, as that would interfere with pursuing its goals. In this paper, we discuss an unorthodox proposal for addressing this concern: give the AI a (primary) goal of being turned off (see also papers by Martin et al., and by Goldstein and Robinson). We also discuss whether and under what conditions this would be a good idea.
title Shutdown Safety Valves for Advanced AI
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.07315