Chatbots powered by artificial intelligence (AI) large language models (LLMs) are becoming more human-like by design. Do LLMs have personality? Researchers at the University of Cambridge and Google DeepMind created a scientifically-validated personality test for AI chatbots based on established human psychological personality tests and published their new study in Nature Machine Intelligence.
Double-Edged Sword of Personable AI
"Vast amounts of human-generated training data enable LLMs to mimic human characteristics in their outputs and exhibit a form of synthetic personality," wrote the study's research team.
The more personable a chatbot is, the more potential for connections and influence on humans. The upside is that the user experience may be more engaging. The downside is that the persuasiveness may not necessarily be a positive influence.
"As LLMs increasingly power conversational agents used by the general public worldwide, the synthetic personality traits embedded in these models by virtue of training on large amounts of human data are becoming increasingly important to evaluate," the authors wrote.
Why Artificial Personalities Matter
The use of AI tools is growing. According to a 2025 YouGov Survey of 1,132 Americans aged 18 and older, 56% of American adults polled used AI tools.
Young people are using chatbots frequently. According to the 2025 Pew Research Center Survey of 1,458 American teens, 68% between the ages of 15-17 years old and 57% of 13- to 14-year-old teens reported using AI chatbots, and three-in-ten teens interact with AI chatbots daily. The most used chatbot among teens is ChatGPT (59%), followed by Gemini (23%), Meta AI (20%), Copilot (14%), Character.ai (9%), and Claude (3%).
"So far, validated psychometric methods for human personality measurement have not been applied to LLMs end-to-end; although past studies have attempted to measure personality in LLMs with psychometric tests, there remains a scientific need to formally evaluate the reliability and validity of these measurements in the LLM context," the researchers wrote.