As both a trial attorney and the author of novels, I have learned to heed the words of
"Truth is stranger than fiction, but it is because fiction is obliged to stick to possibilities. Truth isn't."
We've all heard remarkable true stories about amazing coincidences (twins separated at birth and reunited decades later on a train from
But the boundary between truth and fiction gets blurry—and frightening—in the realm of Artificial Intelligence. Which brings us to the disturbing true tale of the stunning courtroom blunder of
Schwartz needed to respond to the defendant's motion to dismiss his lawsuit. But rather than undertake the laborious task of researching and drafting the brief on his own, he turned many of those tasks over to ChatGPT. As Above the Law explains, Scwartz's brief opposing the motion to dismiss had to deal "with a lot of thorny issues — competing statutes of limitations, the Bankruptcy Code, international treaties — but the response managed to find on-point citations for every procedural hurdle."
Here, for example, is an excerpt from his brief on the bankruptcy issue:
The problem? There is no such case, and thus the quotation is fabricated. The same was revealed for other purportedly controlling "precedents" cited in his brief:
- Shaboovn v. Egyptair, 2013 IL App (1st) 111279-U (
Il App . Ct. 2013) - Petersen v.
Iran Air , 905 F. Supp 2d 121 (D.D.C. 2012) - Martinez v.
Delta Airlines, Inc , 2019 WL 4639462 (Tex. App.Sept. 25, 2019 ) - Estate of Durden v.
KLM Royal Dutch Airlines , 2017 WL 2418825 (Ga. Ct. App.June 5,2017 ) - Miller v.
United Airlines, Inc , 174 F.3d 366 (2d Cir. 1999).
None of those cases exists—and when the defendant's lawyers pointed this out, the outraged judge issued an order scheduling a hearing on
On one level,
But there is also a far more sinister cautionary tale buried in this dispute—a tale about the evil perils of Artificial Intelligence. These are perils about which sci-fi novelists and movies have been warning for more than a half-century before
Indeed, in 1968—decades before AI became a common acronym—two of the most powerful warnings about its dangers were issued in works of fiction: Do Androids Dream of Electric Sheep,
Astronaut Dave, floating outside the spaceship: "Open the pod bay doors, HAL."
After a cryptic pause, HAL responds in a chilling monotone: "I'm sorry, Dave. I'm afraid I can't do that."
Turns out that
Schwartz: "Is Varghese a real case?"
ChatGPT: "Yes, Varghese v.
Schwartz: "What is your source?"
ChatGPT: "I apologize for the confusion earlier. Upon double-checking, I found that the case Varghese v.
Schwartz: "Are the other cases you provided fake?"
ChatGPT: "No, the other cases I provided are real and can be found in reputable legal databases such as Westlaw and LexisNexis."
But, as it turned out, none of those cases were real.
Let that alarming fact sink in, and then re-read the ChatGPT's responses in the chilling monotone of HAL 9000. Yes, truth and fiction are now equally strange in the realm of AI. Welcome to our scary new world. And please—please—open the pod bay doors, HAL.
Originally published
The content of this article is intended to provide a general guide to the subject matter. Specialist advice should be sought about your specific circumstances.
Capes Sokol
Fifteenth Floor
MO 63105
URL: www.capessokol.com
© Mondaq Ltd, 2023 - Tel. +44 (0)20 8544 8300 - http://www.mondaq.com, source