?
Когда чаще не значит лучше: сценарии использования генеративного ИИ в высшем образовании
The article examines the relationship between the use of generative artificial intelligence in learning and several AI-related characteristics of students at Russian universities. The study is based on the assumption that the frequency of AI use should not be treated as a direct indicator of AI literacy or competence in working with generative systems. Four characteristics are considered separately: functional reliance on AI in decision-making, anthropomorphization of AI, ethical sensitivity to its use, and prompting skill assessed through a performance-based task. The empirical analysis draws on data from 1,647 third- and fourth-year undergraduate students from 10 Russian universities, representing STEM, humanities, and social science fields. The results show that the overall frequency of generative AI use is positively associated with functional reliance on AI and anthropomorphization, but is not significantly related to ethical sensitivity or prompting skill after adjustment for multiple comparisons. The use of AI for preparing course papers and project work is associated with both functional reliance on AI and anthropomorphization. More instrumental scenarios, including programming and searching for learning materials, are associated with lower evels of anthropomorphization. Ethical sensitivity is more strongly related to field of study: students in the humanities and social sciences demonstrate higher levels of ethical concern than students in STEM fields. No robust predictors of prompting skill were identified in the final model. The findings suggest that the frequency of generative AI use cannot serve as a sufficient indicator of students’ AI literacy. The article argues for a more differentiated approach to teaching, assessment, and institutional regulation of AI use in higher education.