Cover Image
QR Code

Shutdown-seeking AI.

We propose developing AIs whose only final goal is being shut down. We argue that this approach to AI safety has three benefits: (i) it could potentially be implemented in reinforcement learning, (ii) it avoids some dangerous instrumental convergence dynamics, and (iii) it creates trip wires for mon...

Full description

Published in:Philosophical Studies Vol. 182; no. 7; pp. 1567 - 1580
Main Authors: Goldstein, Simon, Robinson, Pamela
Format: Article
Published: Springer Nature Jul2025
Subjects:
Artificial intelligence
Language models
Digital technology
Reinforcement learning
Natural language processing
Online Access:View this record in EBSCOhost