ChatGPT is more extraverted, conscientious, and open to experiences than the average working age human, new research from Sapia.ai, the world’s only smart chat platform powered by AI, has found.
If these generative AI models were job candidates responding to interview questions, what kind of personality would they project in their natural form? ChatGPT (based on GPT-3.5) and more recently GPT-4 are built using a process that includes “reinforcement learning from human feedback (RLHF)” to make it less likely to make up facts, be toxic or harmful in sentiment compared to the earlier GPT-2.Could this friendliness and politeness be verified?
“Given these models generate responses similar to humans, we wanted to better understand the personality projected by these models when they are not prompted to be a certain personality, or in its natural form, and be able to distinguish its responses from that of a human,” Sapia.ai’s Chief Data Scientist Dr. Buddhi Jayatilleke said.
CIO INFLUENCE: World Password Day: Password advice for CIOs
The study, a first of its kind, analyzed over 6,000 responses from GPT-2, ChatGPT (GPT-3.5) and GPT-4, and cross-examined them with Sapia.ai’s dataset of over 2.5 million candidates across 47 countries with over 1 billion words shared by job candidates. Sapia Labs used their industry-leading personality inference models based on InterviewBERT, a fine tuned version of Google’s BERT large language model to infer the personality dimensions similar to the well known HEXACO model of personality.
Their findings provide fascinating insights. Both ChatGPT and GPT-4 scored significantly higher on the dimensions of honesty/humility, agreeableness, and consciousness, which is consistent with modesty, politeness, and friendly responses, compared to GPT-2.These results align well with OpenAI’s description of how ChatGPT models differ from earlier GPT models.Additionally, the greater likelihood to follow directions and provide accurate information aligns with ChatGPT’s higher conscientiousness. But the most interesting finding is that both ChatGPT and GPT-4 were significantly more extraverted, conscientious, and open to experience compared to the human benchmark dataset.
CIO INFLUENCE: CIO Influence Interview with Lior Yaari, CEO and Co-Founder at Grip Security
[To share your insights with us, please write to sghosh@martechseries.com]
