I asked myself, namely my ‘Digital-Don', a chatbot created in OpenAI, what personality traits I showed, according to the well-validated OCEAN model.
I was essentially using all of my writings as evidence, years of blogs, articles and books. Seems like a reasonable data-set, a lifetime's writing.
Personality of Digital-Don
This is the OCEAN personality profile my digital chatbot came back with:
Based on the descriptions from your texts, I can provide an estimate of your OCEAN personality profile:
Openness 8/10 Your narrative exhibits a strong inclination towards innovation, the embrace of novel ideas, and a readiness to challenge conventional views, particularly regarding learning environments and the Metaverse. This suggests a high level of openness, indicative of a creative and curious nature.
Conscientiousness 7/10 Your detailed exploration of learning theories and their application, along with a structured approach to discussing complex topics like the Metaverse, indicates a high level of conscientiousness. You seem organised and meticulous in your thinking and writing, which aligns with a higher score.
Extraversion 5/10 The text suggests a nuanced approach to social interactions. It emphasizes learning through digital means, which might suggest less direct human interaction, potentially pointing to a moderate level of extraversion. Your engagement with broad audiences through the text suggests sociability, but the heavy reliance on digital interfaces might temper this.
Agreeableness 6/10 Your texts convey a cooperative spirit, especially in learning contexts, and a recognition of the importance of social learning and empathy. However, there is also a critical engagement with ideas that could suggest a balanced approach to agreeableness—not overly accommodating but still considerate.
Neuroticism 3/10 There is little direct evidence in the text about levels of emotional stability or neuroticism. The analytical and composed tone of the narrative might suggest lower neuroticism, as it lacks any overt expression of anxiety or emotional distress. Assuming a stable temperament from the written tone, a score here might be lower.
Personalities of LLMS
So how does this compare with actual LLMs and the personality traits they exhibit? I saw Perry Timms show this diagram from this fascinating paper.
The team developed a Turing test to assess behavioural and personality traits! They made them play behavioural games for benchmarking and assessing traits: trust, fairness, risk-aversion, altruism, and cooperation.
Statistically indistinguishable from humans!
The big surprise was that ChatGPT-4 exhibits behavioural and personality traits that are statistically indistinguishable from a random human, from tens of thousands of human subjects from more than 50 countries. Not surprising really as the training text, fine tuning and HFRL training, are all sourced from humans.
Learned to change their behaviours
They also modified their behaviour, based on their experience and contexts ‘as if’ they were learning from the interactions, to change their behaviour.
Became more altruistic and cooperative
Their behaviours were often different from average and modal human behaviours, when they tended to behave on the more altruistic and cooperative end of the distribution. This is also evidenced by trials where humans find chatbots more friendly and empathetic in their outputs compared to humans.
My traits are the BLUE DOTS.
No comments:
Post a Comment