RESEARCH

Research

28 SEPT 2023

Solving goal misgeneralisation

19 JUN 2023

Concept extrapolation: A conceptual primer

4 MAY 2022

Missing mechanisms of manipulation in the EU AI Act

20 MAR 2022

Recognising the importance of preference change

28 FEB 2022

The dangers in algorithms learning humans' values and irrationalities

9 SEPT 2021

Sigmoids behaving badly

©2025 Aligned AI

/ Press

/ Careers