Researchers tested leading AI models for copyright infringement using popular books, and GPT-4 performed worst
Summary
"The Perks of Being a Wallflower," "The Fault in Our Stars," "New Moon" — none are safe from copyright infringement by leading artificial intelligence models, according to research released Wednesday by Patronus AI. The company, founded by ex-Meta researchers, specializes in evaluation and testing for large language models — the technology behind generative AI products. "We pretty much found copyrighted content across the board, across all models that we evaluated, whether its open source or closed source," Rebecca Qian, Patronus AIs cofounder and CTO, who previously worked on responsible AI research at Meta, told CNBC in an interview. Qian added, "Perhaps what was surprising is that we found that OpenAIs GPT-4, which is arguably the most powerful model thats being used by a lot of companies and also individual developers, produced copyrighted content on 44% of prompts that we constructed." Patronus only tested the models using books under copyright protection in the U.S., choosing popular titles from cataloging website Goodreads.