Jonathan E. Prunty
Cognitive Scientist · University of Cambridge
About
I am a cognitive scientist at the Leverhulme Centre for the Future of Intelligence, University of Cambridge, where I use methods from experimental psychology to study cognition in both humans and machines. My recent work focuses on how AI systems perceive, represent, and reason about physical and social environments.
Before joining Cambridge I completed a PhD in Developmental Psychology at the University of Kent, studying face detection, visual attention, and infant social cognition. My work combines behavioural experiments, eye-tracking, and the development of new evaluation methods.
News
- 2026 Our paper General scales unlock AI evaluation with explanatory and predictive power is published in Nature.
- 2026 Visuospatial perspective taking in multimodal language models accepted at the Cognitive Science Society (CogSci).
- 2025 Presented INTUIT: Investigating intuitive reasoning in humans and language models at CogSci in San Francisco.
- 2024 New paper A cognitive template for face detection out in Cognition.
Preprints & under review
-
Reverse Turing tests for human-machine task suitability assessments should be profile-driven
-
Capabilities ain't all you need: Measuring propensities in AI
-
Continual learning requires evaluating trajectories
-
Visual search paradigms reveal human-like signatures in multimodal large language models
Publications
-
General scales unlock AI evaluation with explanatory and predictive power
-
Visuospatial perspective taking in multimodal language models
-
INTUIT: Investigating intuitive reasoning in humans and language models
-
A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment
-
Effect of strengths-based care: Community led support
-
Association between digital front doors and social care use for community-dwelling adults in England: Cross-sectional study
-
Face detection in contextual scenes
-
A cognitive template for face detection
-
Understanding face detection with visual arrays and real-world scenes
-
Facial comparison behaviour of forensic facial examiners
-
Ingroup and outgroup differences in face detection
-
Capacity limits in face detection
-
Infants show pupil dilatory responses to happy and angry facial expressions
-
Infants scan static and dynamic facial expressions differently
-
Eye movements and behavioural responses to gaze contingent expressive faces in typically-developing infants and infant siblings
-
Caucasian infants' attentional orienting to own- and other-race faces
-
Face processing
-
Family therapy for autism spectrum disorders
-
Conceptualizing and treating social anxiety in autism spectrum disorder: A focus group study with multidisciplinary professionals