Hooooo boy. You gotta read this concurrencethis concurrence by Judge Newsom about the use of AI in legal opinions. It starts this way:
I concur in the Court’s judgment and join its opinion in full. I write separately (and I’ll confess this is a little unusual1) simply to pull back the curtain on the process by which I thought through one of the issues in this case—and using my own experience here as backdrop, to make a modest proposal regarding courts’ interpretations of the words and phrases used in legal instruments. Here’s the proposal, which I suspect many will reflexively condemn as heresy, but which I promise to unpack if given the chance: Those, like me, who believe that “ordinary meaning” is the foundational rule for the evaluation of legal texts should consider—consider—whether and how AI-powered large language models like OpenAI’s ChatGPT, Google’s Gemini, and Anthropic’s Claude might—might—inform the interpretive analysis. There, having thought the unthinkable, I’ve said the unsayable. Now let me explain myself.
1. Even for me.
Wowsa. You gotta read the whole opinion. He goes through the pros and cons of using AI and also shows how he used it in this particular case. It's a very interesting read.
Meantime, I asked Co-Pilot (Microsoft's AI program) to write a blog post about Judge Newsom's use of AI. This is what I got back:
Circuit Judge Proposes Using AI-Powered LLMs to Interpret Legal Texts
In a recent concurring opinion during an insurance dispute, U.S. Circuit Judge Kevin Newsom suggested that courts might benefit from using artificial intelligence programs to interpret legal texts. This idea, which he described as “unthinkable,” could revolutionize the way we understand and apply the law1.
The underlying case involved a dispute between a landscaper and his insurance company over whether his installation of an in-ground trampoline fell under the term “landscaping” in his insurance policy. The district court noted that because the term “landscaping” was not defined in the policy, whether or not the landscaper’s activities were covered by the insurance policy hinged on whether the installation of the trampoline fell within the common, everyday meaning of the word “landscaping.”
Judge Newsom took the opportunity to express his thoughts about artificial intelligence’s possible role in future disputes after “hours and hours (and hours) laboring over the question [of the ordinary meaning of ‘landscaping’ in the context].” He recounted that querying ChatGPT (an AI-powered LLM) about the ordinary meaning of “landscaping” resulted in an explanation that “squared with [his] own impression.” ChatGPT’s definition included “the process of altering the visible features of an area of land, typically a yard, garden, or outdoor space, for aesthetic or practical purposes.” It also listed activities such as planting trees and installing paths and water features as part of "landscaping"2.
Judge Newsom evaluated the pros and cons of using LLMs to interpret legal texts. Some of the pros included the fact that LLMs are trained on a vast range of ordinary-language data, from literature to online discussions. However, he also noted that LLMs cannot capture “pure offline” usages—those that do not occur online or are not eventually digitized. Despite this limitation, LLMs can understand context, are accessible, and have advantages over other empirical interpretive methods, like dictionary research2.
In conclusion, Judge Newsom’s proposal opens up exciting possibilities for the legal field. While he never reached a definitive conclusion due to the panel’s “off-ramp” approach, his experimentation with generative AI suggests that LLMs might indeed be useful when interpreting legal texts3. It’s a fascinating development that could shape the future of legal analysis.
Disclaimer: The views expressed in this blog post are based on Judge Newsom’s opinion and do not constitute legal advice. Consult a qualified attorney for specific legal matters.
2: Circuit Judge Proposes Using AI-Powered LLMs to Interpret Legal Texts 1: Federal Judge Proposes AI to Decode Legal Texts: A Revolutionary Approach or Risky Gamble? 3: Eleventh Circuit Judge Experiments With ChatGPT