Quizlet Embraces AI And ChatGPT To Transform The Studying Experience

Following their recent “State of AI in Education Report,” Quizlet announced many new features and tools as part of their core product suite this week. With the addition of ChapGPT and generative AI, Quizlet builds on its six-year history of using AI to enhance student learning and the effectiveness of student notes as learning tools.

Note-taking is a challenge faced daily by students in lecture classes. The question of whether to pay attention to the lecturer or whether to take notes often feels like a Hobson’s choice. In a class where unique information is conveyed during lectures, the failure to take notes can be fatal, even if it means being less able to pay attention to what the lecturer is saying. On the other hand, while there are benefits from prioritizing engagement over notes, there is also the argument that increased focus can come from writing things down. In the former case, students face notes from which to extract whatever meaning they may have missed, while in the latter, students often find themselves wading through bits and pieces written down while attending to the lecturer, finding themselves with notes of varying quality. The problem multiplies if one also takes notes when reading or otherwise studying.

In either case, the question is what to do with the notes. Do you let them sit in the binder where they do no further good, or do you summarize them – a process that can be productive but is time-consuming and, for the inexperienced, often inefficient? Likewise, reading and rereading one’s hastily written notes can degenerate into an exercise of interpretation rather than deepening comprehension.

This problem is similar to what to do with a smartphone’s endless array of photographs. When the number of photos was in the tens or hundreds, it was possible to sort them by hand. With numbers now orders of magnitude greater, sorting is impractical. Fortunately, features like iPhone memories provide an effective way to consume these photos by grouping them thematically as movies with an added soundtrack.

With its new release, Quizlet has harnessed ChatGPT to provide a similar treatment to student notes. With MagicNotes, Quizlet takes notes and repackages them in several ways, serving up flashcards, practice tests, and other interactive experiences designed to deepen and reinforce learning. And for those looking for audio enhancement, “Brain Beats” turns notes into songs to make facts more memorable.

Quizlet goes beyond just making it easier to review and remember notes. Its MemoryScore feature incorporates a memory decay model designed to optimize memorizing and retaining information efficiency by providing just-in-time review. Such learning decay models have long been the secret sauce of programs designed to teach specific skills through distributed study and practice. That this happens automatically is particularly noteworthy.

The real potential for the new tools is best represented by QChat. QChat harnesses the conversational capabilities of ChatGPT to provide students with a natural environment in which they can interact in a question-answer model with the AI, with the AI generating the questions and prompting the students for answers.

One-on-one tutoring has long been the gold standard for instruction, but it is inherently unscalable except with technology tools. Whether Quizlet has achieved the proper formulation for this approach remains to be seen. What is promising is that the system is built not on having the AI do the student’s work but rather on having it do the work of the teaching assistant, providing individual attention and Socratic interaction with each student as needed.

This approach is common to other efforts incorporating ChatGPT into tutoring, as seen in products such as Khanmigo. The key to effective use of such systems is to put them in a position where they can observe students’ work and provide appropriate direction or suggestions. Properly deployed such systems can keep work from being either so easy as to be boring or so difficult as to be frustrating. One can keep the work intrinsically interesting if one can find the Goldilocks space in between. This should keep students engaged, which will, in turn, lead to more productive time on task. Ultimately, better outcomes should result if computer-based systems can employ AI to keep engagement high and encourage students to spend more time and effort learning. Ultimately, such AI deployments could be the key to addressing the post-Covid-19 learning loss facing so many students today.