Harry Potter Is Now Used to ‘Understand’ How AI Works

Is there anywhere Harry Potter has not reached? Arguably the most popular book series in the world is now used to understand how complicated AI algorithms work and is also a favorite tool for researchers.

Reading this report I smiled remembering how, almost two decades ago, my school exams asked us to fill in the proper verbs in some Harry Potter excerpts. Then, as now, the reason for choosing this book series is simple: it really is universal.

A report in Bloomberg explains how AI researchers are turning to Harry Potter to better understand opaque algorithms:

A growing number of researchers are using the best-selling Harry Potter books to experiment with generative artificial intelligence technology, citing the series’ enduring influence in popular culture and the wide range of language data and complex wordplay within its pages. Reviewing a list of studies and academic papers referencing Harry Potter offers a snapshot into cutting-edge AI research — and some of the thorniest questions facing the technology.

In perhaps the most notable recent example, Harry, Hermione and Ron star in a paper titled “Who’s Harry Potter?” that sheds light on a new technique helping large language models to selectively forget information. It’s a high-stakes task for the industry: Large language models, which power AI chatbots, are built on vast amounts of online data, including copyrighted material and other problematic content. That has led to lawsuits and public scrutiny for some AI companies. The paper’s authors, Microsoft researchers Mark Russinovich and Ronen Eldan, said they’ve demonstrated that AI models can be altered or edited to remove any knowledge of the existence of the Harry Potter books, including characters and plots, without sacrificing the AI system’s overall decision-making and analytical abilities.

The duo said they chose the books because of their universal familiarity. “We believed that it would be easier for people in the research community to evaluate the model resulting from our technique and confirm for themselves that the content has indeed been ‘unlearned,'” said Russinovich, chief technology officer of Microsoft Azure. “Almost anyone can come up with prompts for the model that would probe whether or not it ‘knows’ the books. Even people who haven’t read the books would be aware of plot elements and characters.”

If you missed the previous intersections between AI and Harry Potter, check out how AI thinks Harry Potter characters look like – and how Harry Potter would look like as a Balenciaga model.

Main photo by Gwydion M. Williams on Flickr