23 citations · 24 across the 7 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.AI2024★ 1 cited
Towards Shutdownable Agents via Stochastic Choice
Elliott Thornley, Alexander Roman, Christos Ziakas +2
The POST-Agents Proposal (PAP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the PAP is using a novel `Discounted Reward for Same-Len…
cs.AI2024
The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists
Elliott Thornley
I explain the shutdown problem: the problem of designing artificial agents that (1) shut down when a shutdown button is pressed, (2) don't try to prevent or cause the pressing of t…