11th Circuit Judge Uses ChatGPT to Inform Appeals Decision

ATLANTA — Conceding many of his colleagues might consider it “heresy,” a federal appeals court judge revealed last week that he used AI — in the form of ChatGPT — when drafting his concurrence to a ruling in a civil negligence case. 

U.S. Circuit Judge Kevin Newsom, a Trump appointee who was confirmed to his seat on the 11th Circuit by a 2-1 margin in the U.S. Senate in August 2017, is an outspoken proponent of the “ordinary meaning” of words being the foundational rule for the evaluation of legal texts.

His interest in language extended at least as far back as his tenure as an editor at the Harvard Law Review in the late 1990s, and while he earned his conservative legal bonafides while clerking for Justice Diarmuid O’Scannlain in the 9th Circuit, he also saw the value of being a free-thinker when he later clerked for Supreme Court Justice David Souter.

Souter was considered a “home run” when he was nominated to the high court by President George H.W. Bush in 1990, but he surprised almost everyone when he routinely voted with the court’s more liberal members.

Newsom’s potentially groundbreaking use of AI came in what might be considered the most mundane of legal cases — a landscaping company in Fairhope, Alabama, sued its insurance company over its refusal to defend them in a negligence case.

Though Newsom concurred with his appellate court colleagues in their deciding the case in favor of the insurer, upholding a lower court ruling, he nonetheless felt the need to write a concurrence, “to pull back the curtain on the process by which I thought through one of the issues in this case.”

He then went a step further, proposing the “unthinkable”; namely that other judges consider “whether and how” AI-powered large language models like OpenAI’s ChatGPT, Google’s Gemini and Anthropic’s Claude, “might” inform their interpretive analysis. 

In making his own personal leap into this area, Newsom said he started out merely doing what “any self-respecting textualist would do when trying to assess the ordinary meaning of a particular word”; he turned to a dictionary.

In this case, the word was “landscaping,” and what troubled the judge was that the plaintiff had “served up a buffet of definitions” for the word in his legal briefs.

“After languishing in definitional purgatory for a while, I decided to look at the case from a different perspective,” Newsom said.

Setting aside his Merriam-Webster’s Collegiate Dictionary, the judge reviewed photographs of the project central to the underlying negligence case — an above-ground trampoline that had been transformed into an in-ground trampoline.

“I’m not particularly proud of it, but I’ll confess that the photos affected the way I thought about the case,” Newsom wrote. “Nothing in them really struck me as particularly ‘landscaping’-y. The problem, of course, was that I couldn’t articulate why. And visceral, gut-instinct decision making has always given me the willies — I definitely didn’t want to be that guy.”

“So in a way, I felt like I was back to square one,” he continued, his grimace almost visible on the page.

“And that’s when things got weird,” he wrote. 

“Perhaps in a fit of frustration, and most definitely on what can only be described as a lark, I said to one of my clerks, ‘I wonder what ChatGPT thinks about all this?’ So he ran a query: ‘What is the ordinary meaning of landscaping?’”

In response, ChatGPT offered: “‘Landscaping’ refers to the process of altering the visible features of an area of land, typically a yard, garden or outdoor space, for aesthetic or practical purposes. This can include activities such as planting trees, shrubs, flowers, or grass, as well as installing paths, fences, water features and other elements to enhance the appearance and functionality of the outdoor space.”

Newsom said the response interested him for two reasons:

“First, ChatGPT’s explanation seemed more sensible than I had thought it might — and definitely less nutty than I had feared,” he wrote. “Second, it squared with my own impression — informed by my own experience writing, reading, speaking and listening to American English in the real world.”

His interest piqued, Newsom went ahead and asked ChatGPT the ultimate question: “Is installing an in-ground trampoline ‘landscaping’?”

“Yes,” ChatGPT responded, going on to explain its reasoning.

Now down the rabbit hole, Newsom posed the same questions to Google’s Bard program, getting a similar, though more wordy response to the first question, and a more equivocal answer on the second question.

In the end, the judge concluded that working through the “plain-language issue” had been valuable, “if only because it got me thinking about what was to me a previously unimaginable possibility: Might [AI-powered large language models] be useful in the interpretation of legal texts?

“Having initially thought the idea positively ludicrous, I think I’m now a pretty firm ‘maybe.’ At the very least, it seems to me, it’s an issue worth exploring,” he wrote.

In his annual year-end report on the state of the federal judiciary last year, Chief Justice John Roberts cautioned that the “use of AI requires caution and humility.”

In his concurrence, Newsom said he agreed.

However, he said, he also agreed with Roberts’ assumption that AI is here to stay.

“Now, it seems to me, is the time to figure out how to use it profitably and responsibly,” Newsom said. “It’s in that spirit that I’ve offered these preliminary thoughts about whether and how [AI-powered large language models] might aid lawyers and judges in the interpretive enterprise.

“Plenty of questions remain … but — and this is my bottom line — I think that LLMs have promise,” he continued. “At the very least, it no longer strikes me as ridiculous to think that an LLM like ChatGPT might have something useful to say about the common, everyday meaning of the words and phrases used in legal texts.”

You can reach us at [email protected] and follow us on Facebook and Twitter