Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)

31 December 2018

Papers citing "Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)"

10 / 10 papers shown

Title
Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems Enrico Liscio Luciano Cavalcante Siebert Catholijn M. Jonker P. Murukannaiah 40 4 0 26 Feb 2024
Designing Fiduciary Artificial Intelligence Sebastian Benthall David Shekman 51 4 0 27 Jul 2023
`It is currently hodgepodge'': Examining AI/ML Practitioners' Challenges during Co-production of Responsible AI Values R. Varanasi Nitesh Goyal 37 46 0 14 Jul 2023
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased Chao Yu Jiaxuan Gao Weiling Liu Bo Xu Hao Tang Jiaqi Yang Yu Wang Yi Wu 31 39 0 03 Feb 2023
Impossibility Results in AI: A Survey Mario Brčič Roman V. Yampolskiy 29 25 0 01 Sep 2021
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences Daniel S. Brown Russell Coleman R. Srinivasan S. Niekum BDL 32 101 0 21 Feb 2020
Unpredictability of AI Roman V. Yampolskiy 16 30 0 29 May 2019
Augmented Utilitarianism for AGI Safety Nadisha-Marie Aliman L. Kester 22 8 0 02 Apr 2019
The Ethics of AI Ethics -- An Evaluation of Guidelines Thilo Hagendorff AI4TS 28 1,156 0 28 Feb 2019
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments Alexandra Chouldechova FaML 207 2,091 0 24 Oct 2016