Real Customization or Just Marketing: Are Customized Versions of Generative AI Useful?

Background: Large Language Models (LLMs), as in the case of OpenAI TM ChatGPT-4 TM Turbo, are revolutionizing several industries, including higher education. In this context, LLMs can be personalised through a fine-tuning process to meet the student demands on every particular subject, like statistics. Recently, OpenAI launched the possibility of fine-tuning their model with a natural language web interface, enabling the creation of customised GPT versions deliberately conditioned to meet the demands of a specific task. Methods: This preliminary research aims to assess the potential of the customised GPTs. After developing a Business Statistics Virtual Professor (BSVP), tailored for students at the Universidad Pontificia Comillas, its behaviour was evaluated and compared with that of ChatGPT-4 Turbo. Firstly, each professor collected 15-30 genuine student questions from "Statistics and Probability" and "Business Statistics" courses across seven degrees, primarily from second-year courses. These questions, often ambiguous and imprecise, were posed to ChatGPT-4 Turbo and BSVP, with their initial responses recorded without follow-ups. In the third stage, professors blindly evaluated the responses on a 0-10 scale, considering quality, depth, and personalization. Finally, a statistical comparison of the systems' performance was conducted. Results: The results lead to several conclusions. Firstly, a substantial modification in the style of communication was observed. Following the instructions it was trained with, BSVP responded in a more relatable and friendly tone, even incorporating a few minor jokes. Secondly, when explicitly asked for something like, "I would like to practice a programming exercise similar to those in R practice 4," BSVP could provide a far superior response. Lastly, regarding overall performance, quality, depth, and alignment with the specific content of the course, no statistically significant differences were observed in the responses between BSVP and ChatGPT-4 Turbo. Conclusions: It appears that customised assistants trained with prompts present advantages as virtual aids for students, yet they do not constitute a substantial improvement over ChatGPT-4 Turbo.

Does loving-kindness meditation elicit empathic emotions? The moderating role of self-discrepancy and self-esteem on guilt.

Our understanding of the emotions elicited by loving-kindness meditation (LKM) at early stages of practice is limited, despite the influence that these emotions may have on later engagement. Past work suggests that LKM may elicit emotional ambivalence at early stages of the practice, but it is still unclear whether the content of LKM activates this ambivalence and who is more likely to experience it. Given the specific content of LKM, we defend that this meditation is likely to elicit empathetic emotions, both positive (compassion and gratitude) and negative (guilt), to a greater extent than an active control. Guilt is likely to be elicited by memories of incidents where naïve meditators were not able to experience compassion and/or by the difficulties in sending compassionate love to disliked others during the meditation. Furthermore, individuals with greater self-discrepancy and lower self-esteem are more likely to experience guilt. These hypotheses were tested in two experimental studies with community and student samples (n = 55 and n = 33, respectively) and using a brief intervention. The results support the hypotheses. These findings have implications for instructors of LKM, especially when organizing meditation practices with naïve meditators who should be aware of the potential negative emotions elicited by this meditation.