Hal Ashton

According to our database, Hal Ashton authored at least 15 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Beyond Preferences in AI Alignment.

Tan Zhi-Xuan, Micah Carroll, Matija Franklin, Hal Ashton

CoRR, 2024

2023

Definitions of intent suitable for algorithms.

Hal Ashton

Artif. Intell. Law, September, 2023

Concept Extrapolation: A Conceptual Primer.

Matija Franklin, Rebecca Gormann, Hal Ashton, Stuart Armstrong

CoRR, 2023

2022

Solutions to preference manipulation in recommender systems require knowledge of meta-preferences.

Hal Ashton, Matija Franklin

CoRR, 2022

Preference Change in Persuasive Robotics.

Matija Franklin, Hal Ashton

CoRR, 2022

Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI.

Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong

CoRR, 2022

A Method to Check that Participants Really are Imagining Artificial Minds When Ascribing Mental States.

Hal Ashton, Matija Franklin

Proceedings of the HCI International 2022 - Late Breaking Posters, 2022

Missing Mechanisms of Manipulation in the EU AI Act.

Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong

Proceedings of the Thirty-Fifth International Florida Artificial Intelligence Research Society Conference, 2022

Causal Framework of Artificial Autonomous Agent Responsibility.

Matija Franklin, Hal Ashton, Edmond Awad, David A. Lagnado

Proceedings of the AIES '22: AAAI/ACM Conference on AI, Ethics, and Society, Oxford, United Kingdom, May 19, 2022

The Problem of Behaviour and Preference Manipulation in AI Systems.

Hal Ashton, Matija Franklin

Proceedings of the Workshop on Artificial Intelligence Safety 2022 (SafeAI 2022) co-located with the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI2022), 2022

Defining and Identifying the Legal Culpability of Side Effects using Causal Graphs.

Hal Ashton

Proceedings of the Workshop on Artificial Intelligence Safety 2022 (SafeAI 2022) co-located with the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI2022), 2022

2021

Extending counterfactual accounts of intent to include oblique intent.

Hal Ashton

CoRR, 2021

Causal Campbell-Goodhart's Law and Reinforcement Learning.

Hal Ashton

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

What criminal and civil law tells us about Safe RL techniques to generate law-abiding behaviour.

Hal Ashton

Proceedings of the Workshop on Artificial Intelligence Safety 2021 (SafeAI 2021) co-located with the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), 2021

2020

AI Legal Counsel to train and regulate legally constrained Autonomous systems.

Hal Ashton

Proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020), 2020