top of page
RELATED RESEARCH PUBLICATIONS
The humanity of conversational AI (2024)
AI-LIEDAR : Trade-off Between Utility and Truthfulness (2024)
MemoryBank (2024)
Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs (2024)
Higher cognitive ability linked to weaker moral foundations in UK adults (2025)
Co-human (2023)
Working Memory Capacity of ChatGPT (2024)
Read how it relates to our work
Sleeper Agents: Training Deceptive LLMs (2024)
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs (2025)
Psychology of Physical Bravery (2014)
From AI to
IA (Intelligence Augmentation)(2023)
Trust in an AI versus a Human teammate (2024)
Should LLMs be W.E.I.R.D (2025)
Do LLMs Have Values? (2025)
Value of goal predicts accolade courage (2024)
bottom of page