Experiences and Proposals of Use of Generative AI in Advanced Software Courses

Abstract

The last year, we have witnessed the popularization of generative artificial intelligence. Its output includes text, code, image, audio, speech, voice, music, and video. Therefore, it impacts education courses where students are required to elaborate on any of these artifacts. In particular, the generation of code affects informatics courses, where assignments usually ask students to develop and deliver programming code. The impact of generative artificial intelligence on informatics courses has been mainly studied for introductory programming courses. These studies have shown that generative artificial intelligence is able to produce highly sophisticated programs, but also that its results and rationale can be inaccurate. Moreover, the impact of generative artificial intelligence has not been studied for other informatics subjects. In this paper, we present our preliminary experience and proposals on three advanced software courses, namely video games, advanced algorithms and language processors. For the video games course, we present the opportunities of use of generative artificial intelligence and the results of a survey conducted with students on their use to obtain different media products. For the algorithms course, we present the result of a session driven by the instructor on different design techniques, showing the merits and demerits of the answers generated. For the language processors course, a proposal of use of generative artificial intelligence is presented, broken down into the parts of a typical language processor. The paper concludes with some suggestions for instructors.