Luning Sun

Research Associate

BSc (Zhejiang University), MSc (University of Munich), PhD (University of Cambridge)

As a research associate in the Organisational Behaviour subject group, I examine personality and ability assessment; adaptive testing in clinical assessment; and test development for educational and occupational assessment.

Luning Sun.

My details

Academic area

Organisational Behaviour

News and insights

AI can reason – but only to a point – resolving a long-running debate by showing that contradictory claims about AI reasoning simply reflect tests demanding very different levels of the same abilities.

A new study led by the University of Cambridge introduces an ‘ability profile’ for artificial intelligence models to predict how they will perform on any tasks – including unfamiliar ones – greatly advancing understanding beyond current AI benchmarks that only tell how an AI model performs on a specific test.

Person using AI for medical purposes.

Artificial intelligence holds great promise in healthcare. Yet such use of AI use poses risks, especially in relying on benchmarks to evaluate medical expertise and practice. Research co-authored at the Psychometrics Centre at Cambridge Judge Business School outlines a better methodology that improves benchmarking through the application of psychometrics.

When questioned 10 times, an LLM’s collective creativity is equivalent to 8-10 humans. When more responses are requested, 2 additional LLM responses equal one extra human.

The collective creativity of large language models (LLMs), such as ChatGPT, is equivalent to 8-10 humans when generative AI models are questioned 10 times, says new study co-authored at Cambridge Judge Business School that challenges the idea that AI can’t handle creative tasks.

Top