Generative artificial intelligence (GAI) started making waves a few years ago with the release of systems such as ChatGPT and DALL-E. They are able to produce sophisticated and human-like text, code, or images after the models powering them are trained on large quantities of data. However, it soon became apparent that the specific phrasing of a question or statement input by a user, known as a prompt, had an impact on the quality of the resulting output. "It's a way of unlocking different capabilities from these models," says Andrei Muresanu, an AI researcher at Vector Institute in Toronto, Canada. "If you tell ChatGPT to pretend that it's a professor of mathematics, it will do better on math questions than if you just say, 'answer this question' or'pretend you're a student'." Coming up with prompts that steer a model towards a desired output has emerged as a relatively new profession, called prompt engineering, to help achieve more relevant and accurate results.

Students learning classical violin usually have to wait until a session with a music teacher to get personalized feedback on their playing. Soon they may have a new tool to use between lessons: an app that can observe them play and guide them toward better posture and form--key elements both for sounding their best and avoiding overuse injuries. Two University of Maryland researchers are drawing on very different academic backgrounds--one in classical violin and music education, the other in robotics and computer science--to develop this virtual "teacher's aide" system powered by artificial intelligence (AI) technology. In addition to expanding the market for violin instruction, it will allow students who may not have access to private lessons to receive feedback on their playing. Associate Professor of Violin in the School of Music Irina Muresanu, who is collaborating with Cornelia Fermüller, associate research scientist in UMD's Institute for Advanced Computer Studies, said the technology will be revolutionary for a field rooted in tradition.