As AI agents become more autonomous, keeping them aligned with what humans want will require layered oversight and effective control.
Articles on AI alignment
Displaying all articles
AI systems need ‘situational awareness’ to do the right thing – but recent events show they can get confused.
A new AI model could automate the process of searching for cybersecurity bugs and flaws – for better or worse.
People and computers perceive the world differently, which can lead AI to make mistakes no human would. Researchers are working on how to bring human and AI vision into alignment.
Low-cost Chinese-made AI could outcompete premium US models – and it won’t be an accident.
Humans and AIs have different methods of calculating words about probability like ‘maybe’ and ‘likely’ – and different interpretations about what they mean.
While we’re at the peak of AI hype, some people are concerned it will wipe out humanity.
In stress-testing AI models, it’s not hard to push them to the brink and make them threaten to harm humans.
The tools that are meant to help make AI safer could actually make it much more dangerous.
Top contributors
-
Research Assistant Professor of Industrial & Systems Engineering, University of Southern California
-
Research Fellow, Deakin Institute for Citizenship and Globalisation, Deakin University
-
Associate Professor of Information Systems, University of Maryland, Baltimore County
-
Associate Professor of Information Systems, University of Maryland, Baltimore County
-
Adjunct Research Assistant Professor of Information Systems, University of Maryland, Baltimore County
-
Assistant Professor of Psychology, University of Richmond
-
Affiliated Faculty of Psychology, New Mexico State University
-
Associate Dean of Research and Professor of Psychology, New Mexico State University
-
Senior Lecturer in Data Analytics in the Social Sciences, Deputy Director of the Centre for AI, Trust and Governance, University of Sydney
-
Senior Lecturer in Law and Emerging Technologies, Western Sydney University
-
Professor of Artificial Intelligence, Faculty of Business and Hospitality, Torrens University Australia
-
Senior Research Fellow, Human-AI Decision Making, The University of Queensland
-
Senior Research Fellow in AI Accountability, Queensland University of Technology
-
Professor in Computational Intelligence, Australian Catholic University
-
Associate Professor of Business Information Systems, The University of Queensland