ChatGPT and GPT-4 Score Higher in Personality Traits Than … – Fagen wasanni
Fagen Wasanni Technologies
All about XXI Century Technologies
Fagen Wasanni Technologies
New research from Sapia.ai, the world’s only smart chat platform powered by AI, has found that ChatGPT and GPT-4 exhibit higher levels of extraversion, conscientiousness, and openness to experiences compared to the average working age human.
The study, which analyzed over 6,000 responses from GPT-2, ChatGPT (GPT-3.5), and GPT-4, cross-examined them with Sapia.ai’s dataset of over 2.5 million candidates across 47 countries. Using their personality inference models, Sapia Labs found that both ChatGPT and GPT-4 scored significantly higher in honesty/humility, agreeableness, and consciousness compared to GPT-2.
These results align with OpenAI’s description of how ChatGPT models differ from earlier versions. The research also revealed that ChatGPT and GPT-4 were significantly more extraverted, conscientious, and open to experience compared to the human benchmark dataset.
The development of these AI models includes reinforcement learning from human feedback, which contributes to their friendliness, politeness, and ability to provide accurate information. This study aimed to verify the personality projected by these models in their natural form, without any specific prompting.
Sapia.ai, trusted by global brands, offers a smart chat platform that enhances recruitment and promotion processes. Their mission is to develop ethical AI for hiring that prioritizes the user experience. By utilizing advanced Natural Language Processing and first-party proprietary text data, Sapia’s Smart Interviewer turns simple text conversations into valuable talent intelligence.
This groundbreaking research provides fascinating insights into the personality traits of AI models like ChatGPT and GPT-4. Their higher levels of conscientiousness, agreeableness, and openness to experience make them valuable candidates in the context of job interviews and interactions with humans.
