Picture for Hal Ashton

Hal Ashton

Beyond Preferences in AI Alignment

Add code
Aug 30, 2024
Figure 1 for Beyond Preferences in AI Alignment
Figure 2 for Beyond Preferences in AI Alignment
Figure 3 for Beyond Preferences in AI Alignment
Figure 4 for Beyond Preferences in AI Alignment
Viaarxiv icon

Concept Extrapolation: A Conceptual Primer

Add code
Jun 19, 2023
Viaarxiv icon

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

Add code
Sep 14, 2022
Figure 1 for Solutions to preference manipulation in recommender systems require knowledge of meta-preferences
Viaarxiv icon

Preference Change in Persuasive Robotics

Add code
Jun 21, 2022
Viaarxiv icon

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

Add code
Mar 30, 2022
Figure 1 for Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI
Viaarxiv icon

Definitions of intent suitable for algorithms

Add code
Jun 08, 2021
Figure 1 for Definitions of intent suitable for algorithms
Figure 2 for Definitions of intent suitable for algorithms
Viaarxiv icon

Extending counterfactual accounts of intent to include oblique intent

Add code
Jun 07, 2021
Figure 1 for Extending counterfactual accounts of intent to include oblique intent
Figure 2 for Extending counterfactual accounts of intent to include oblique intent
Viaarxiv icon

Causal Campbell-Goodhart's law and Reinforcement Learning

Add code
Nov 02, 2020
Figure 1 for Causal Campbell-Goodhart's law and Reinforcement Learning
Figure 2 for Causal Campbell-Goodhart's law and Reinforcement Learning
Figure 3 for Causal Campbell-Goodhart's law and Reinforcement Learning
Figure 4 for Causal Campbell-Goodhart's law and Reinforcement Learning
Viaarxiv icon