Stuart Armstrong

28 papers A* 2A 1Misc 1Journal 19Unranked 5
YearRankTypeTitle / Venue / Authors
2025 J jnl
ACE and Diverse Generalization via Selective Disagreement.
CoRR
Oliver Daniels, Stuart Armstrong, Alexandre Maranhão, Mahirah Fairuz Rahman, Benjamin M. Marlin, Rebecca Gormann
2025 J jnl
AI Chaperones Are (Really) All You Need to Prevent Parasocial Relationships with Chatbots.
CoRR
Emma Rath, Stuart Armstrong, Rebecca Gormann
2025 J jnl
Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation.
CoRR
Stuart Armstrong, Matija Franklin, Connor Stevens, Rebecca Gormann
2023 J jnl
CoinRun: Solving Goal Misgeneralisation.
CoRR
Stuart Armstrong, Alexandre Maranhão, Oliver Daniels-Koch, Patrick Leask, Rebecca Gormann
2023 J jnl
Concept Extrapolation: A Conceptual Primer.
CoRR
Matija Franklin, Rebecca Gormann, Hal Ashton, Stuart Armstrong
2022 Misc conf
Missing Mechanisms of Manipulation in the EU AI Act.
FLAIRS
Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong
2022 J jnl
Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI.
CoRR
Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong
2022 J jnl
The dangers in algorithms learning humans' values and irrationalities.
CoRR
Rebecca Gormann, Stuart Armstrong
2021 — conf
Chess as a Testing Grounds for the Oracle Approach to AI Safety.
AISafety@IJCAI
James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong
2020 J jnl
Chess as a Testing Grounds for the Oracle Approach to AI Safety.
CoRR
James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong
2020 A* conf
Pitfalls of Learning a Reward Function Online.
IJCAI
Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg
2020 J jnl
Pitfalls of learning a reward function online.
CoRR
Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg
2018 J jnl
Counterfactual equivalence for POMDPs, and underlying deterministic environments.
CoRR
Stuart Armstrong
2018 A* conf
Occam's razor is insufficient to infer the preferences of irrational agents.
NeurIPS
Stuart Armstrong, Sören Mindermann
2017 J jnl
'Indifference' methods for managing agent rewards.
CoRR
Stuart Armstrong
2017 J jnl
Good and safe uses of AI Oracles.
CoRR
Stuart Armstrong
2017 J jnl
Impossibility of deducing preferences and rationality from human policy.
CoRR
Stuart Armstrong, Sören Mindermann
2017 J jnl
Low Impact Artificial Intelligences.
CoRR
Stuart Armstrong, Benjamin Levinstein
2016 — conf
Ghost Hunter - An Augmented Reality Ghost Busting Game.
HCI (10)
Stuart Armstrong, Kyle Morrand
2016 J jnl
Racing to the precipice: a model of artificial intelligence development.
AI Soc.
Stuart Armstrong, Nick Bostrom, Carl Shulman
2016 A conf
Safely Interruptible Agents.
UAI
Laurent Orseau, Stuart Armstrong
2015 — conf
Corrigibility.
AAAI Workshop: AI and Ethics
Nate Soares, Benja Fallenstein, Stuart Armstrong, Eliezer Yudkowsky
2015 — conf
Motivated Value Selection for Artificial Agents.
AAAI Workshop: AI and Ethics
Stuart Armstrong
2014 J jnl
The errors, insights and lessons of famous AI predictions - and what they mean for the future.
J. Exp. Theor. Artif. Intell.
Stuart Armstrong, Kaj Sotala, Seán Sáirséal Ó hÉigeartaigh
2012 J jnl
Thinking Inside the Box: Controlling and Using an Oracle AI.
Minds Mach.
Stuart Armstrong, Anders Sandberg, Nick Bostrom
2011 J jnl
Anthropic decision theory
CoRR
Stuart Armstrong
2011 — conf
Risks and Mitigation Strategies for Oracle AI.
PT-AI
Stuart Armstrong
2011 J jnl
Training and learning for crisis management using a virtual simulation/gaming environment.
Cogn. Technol. Work.
Warren E. Walker, Jordan Giddings, Stuart Armstrong