TheCorporateCounsel.net

Over on the “Delaware Corporate & Commercial Litigation Blog”, Francis Pileggi recently flagged a concurring opinion by federal appellate judge Kevin Newsom in Snell v. United Specialty Ins. Co., (11th Cir.; 5/24). In that opinion, Judge Newsom explains how he used generative AI tools to help determine the “ordinary meaning” of terms at issue in a piece of litigation.  In this particular case, the issue he sought to resolve was whether the installation of a trampoline involved “landscaping” within the meaning of a liability insurance policy.

After unsuccessfully trying to resolve this question by turning to the dictionary and photographs of the (very cool – see the pic on p. 7 of the opinion) in-ground trampoline itself, he decided to take a flyer on Chat GPT.  After being intrigued by Chat GPT’s response to the general question “What is the ordinary meaning of ‘landscaping’?” the judge got more specific:

Suffice it to say, my interest was piqued. But I definitely didn’t want to fall into the trap of embracing ChatGPT’s definition just because it aligned with my priors. (Bad.) So, in what might have been a mistake—more on that later—we went ahead and asked it the ultimate question: “Is installing an in-ground trampoline ‘landscaping’”? ChatGPT responded as follows:

Yes, installing an in-ground trampoline can be considered a part of landscaping. Landscaping involves altering the visible features of an outdoor area for aesthetic or practical purposes, and adding an in-ground trampoline would modify the appearance and function of the space. It’s a deliberate change to the outdoor environment, often aimed at enhancing the overall landscape and usability of the area.

For good measure, I posed the same questions to Google’s Bard (since replaced by Gemini). The precise details aren’t particularly important, but the upshot is that both models’ answers indicated that the trampoline-related work Snell had performed—the excavation of the pit, the construction of the retaining wall, the installation of the mat, and the addition of the decorative wooden cap—just might be landscaping.

Judge Newsom then provides a thoughtful appraisal of some of the pros and cons of using AI large language models as a tool for resolving interpretive issues like this, and suggests that they may have a constructive role to play in judicial efforts to determine “the common, everyday meaning of the words and phrases used in legal texts.”

Francis wraps up his blog by summarizing the key takeaway from Judge Newsom’s opinion: “AI in the law is now mainstream when an appellate court includes references to how it was used as part of an analysis in connection with a published opinion.”  Stay tuned.

– John Jenkins