On December 6, 2023, Chong Ke, a Vancouver lawyer at Westside Family Law, filed a notice of application in court for a client who was asking for more access to his kids. Lawyers representing the mother went through the application to put together a response. That’s when they noticed two of the cases cited in the application couldn’t be found. That’s because they didn’t exist. Ke had used ChatGPT, the chatbot developed by OpenAI, to do legal research and didn’t realize the cases he found were fictitious.
Law can be a slog, so it’s no surprise lawyers are eager to leverage AI’s ability to sift through databases of legal texts, case laws, statutes, and regulations. A tool able to summarize findings and highlight relevant precedents can save significant amounts of time and effort. But ChatGPT isn’t a search engine; it’s a large language model. It trains on data and generates human-like responses based on what it learns. That creative streak gives the chatbot a dark side: a tendency to serve up data that’s false or inaccurate, a phenomenon called hallucination.
