It’s all about the prompt. BYU Law’s Future of Law forum welcomed Dazza Greenwood, researcher at MIT’s media lab and executive director of law.MIT.edu., who demonstrated how AI models can generate astonishingly accurate results from detailed inputs. A student inquiry about using AI to generate ideas for amending a patent to avoid prior art had Greenwood inputting a detailed prompt in real time with dazzling results. The model proposed the very changes that had been made to avoid a patent lawsuit. “We are not in an AI winter anymore. It’s late spring,” said Greenwood.
Historically, law has not been an ideal space for AI because results were generated in a logical, decision-tree flow, and legal answers are nuanced and require judgement. “Now what we have is well-suited to the legal domain,” Greenwood observed. The key: giving the AI model as much context as possible yields the most accurate results. Greenwood recommended “utility prompts” that give specific orders and fine-tune the results by specifying a purpose and the desired formatting. “I take great joy in creating enormous prompts!” He urged students to use AI to enhance their capabilities by validating understanding and for brainstorming ideas, but he warned: “do not copy and paste results, ever.” Assessing AI-generated results for accuracy is essential and requires expertise. This necessity, Greenwood observed, is good news for law students: “Law school is still really important because the legal world needs capable shepherds.”
Comments (0)