With its increasing popularity, artificial intelligence is increasingly becoming the focus of research. A current study has now addressed the question of whether AI systems can demonstrate human-like behavior.
Whether translating a text or chatting with a customer service bot – we already encounter artificial intelligence in many places in everyday life. Some chatbots are now so good that you can no longer tell whether you are dealing with a human or a machine.
But to what extent can AI systems actually imitate human behavior? This question is addressed in a current study that was recently published in the journal PNAS became.
How human-like is artificial intelligence?
For their study, the researchers chose the GPT series developed by OpenAI. The main focus was on the differences between the ChatGPT-3 and ChatGPT-4 versions as well as the Free and Plus versions of these chatbots.
For the present study, the chatbots had to answer a questionnaire from the Big Five model. They then played six different games in which behavioral characteristics such as fairness or malice can occur.
The researchers compared the results with human data from the Big Five personality test. A data set was used that contains answers from more than 100,000 test subjects from more than 50 countries.
What is the Big Five model all about?
The Big Five model, also known as the five-factor model, is a model of personality psychology. This model attempts to represent the individual characteristics of individual people.
The five dimensions of extraversion, agreeableness, conscientiousness, emotional stability and openness are used. With the help of questionnaires, personality profiles can then be created – whether from humans or from AI systems.
Artificial intelligence behaves so human-like
But how did OpenAI’s GPT systems perform? The results of the study show that ChatGPT-4 is very close to mean human values in all personality dimensions. ChatGPT-3, on the other hand, shows a slight deviation in the openness dimension.
In the dimensions of extraversion and emotional stability, both chatbots show behavioral patterns that are closely based on human tendencies. When it comes to openness and agreeableness, however, there are clear differences.
In the games, the chatbots performed above average compared to humans in terms of generosity and fairness. Similar to humans, the respective framework and context also matters for an AI chatbot. As with humans, these factors have a significant influence on behavior.
Also interesting:
Source: https://www.basicthinking.de/blog/2024/02/27/kuenstliche-intelligenz-menschenaehnliches-verhalten/
