Human Control: Definitions and Algorithms

Ryan Carey, Tom Everitt
5/31/2023
cs.AI

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

How can humans stay in control of advanced artificial intelligence systems? One proposal is corrigibility, which requires the agent to follow the instructions of a human overseer, without inappropriately influencing them. In this paper, we formally define a variant of corrigibility called shutdown instructability, and show that it implies appropriate shutdown behavior, retention of human autonomy, and avoidance of user harm. We also analyse the related concepts of non-obstruction and shutdown alignment, three previously proposed algorithms for human control, and one new algorithm.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding

82% match2026

Password-Activated Shutdown Protocols for Misaligned Frontier Agents

81% match2025

Human-AI Safety: A Descendant of Generative AI and Control Systems Safety

79% match2024

Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making

79% match2026

Overseeing Agents Without Constant Oversight: Challenges and Opportunities

78% match2026

What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents

78% match2026

Cite this paper

@article{carey2023human,
  title  = {Human Control: Definitions and Algorithms},
  author = {Ryan Carey and Tom Everitt},
  year   = {2023},
  eprint = {2305.19861},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.19861v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.19861.svg)](https://codeofpaper.com/paper/2305.19861)

Discussion