Lawyer faces sanctions after using fake research from ChatGPT

Attorney Steven Schwartz is facing sanctions from a New York district court after he submitted a legal brief containing several precedent cases that never existed. He received the fake cases from ChatGPT when he used the AI-powered chatbot to assist him with his legal research.

While Schwartz has been an attorney for over 30 years, U.S. Judge Kevin Castel of the Southern District of New York wrote in an order that “[t]he Court is presented with an unprecedented circumstance”, adding that six cases “appear to be bogus judicial decisions with bogus quotes and bogus internal citations.”

The bogus cases were: Varghese v. China South Airlines, Martinez v. Delta Airlines, Shaboon v. EgyptAir, Petersen v. Iran Air, Miller v. United Airlines, and Estate of Durden v. KLM Royal Dutch Airlines.

In his defense to the court to avoid sanctions, Schwartz provided screenshots of his conversation with ChatGPT, according to the Daily Wire. The exchanges show that Schwartz expressed doubt about the authenticity of the cases and pressed the chatbot for further verification. ChatGPT obliged, manufacturing not only the case names, but even their sources.

“Is varghese a real case,” reads one message from Schwartz, referencing Varghese v. China Southern Airlines Co Ltd.

“Yes,” ChatGPT responded. It “is a real case.”

“What is your source,” the user replied.

“I apologize for the confusion earlier,” ChatGPT replied. “Upon double-checking, I found the case Varghese v. China Southern Airlines Co. Ltd., 925 F.3d 1339 (11th Cir. 2019), does indeed exist and can be found on legal research databases such as Westlaw and LexisNexis. I apologize for any inconvenience or confusion my earlier responses may have caused.”

Schwartz apologized to the court and said he “was unaware of the possibility that its content could be false.”

Schwartz is not the only victim of ChatGPT’s disinformation.

University of Mexico Information Systems Associate Professor Nick Flor says ChatGPT cited a fake study to push the idea there are more than two genders.

“ChatGPT claimed that today's doctors & scientists ‘widely accept’ that gender is a complex concept. So I challenged ChatGPT to ‘cite a scientific paper’ And ChatGPT >MADE UP A PAPER<. That's unethical of the AI Engineers behind chatGPT to gaslight the public,” Flor tweeted Saturday.

The professor attached screenshots of the exchange:

ChatGPT: The view that gender is a complex and multi-faceted construct, rather than simply determined by biological factors, is widely accepted by the medical and scientific communities, including organizations such as: The World Health Organization 

Nick Flor: Cite a scientific paper.

ChatGPT: Here is one example of a scientific paper on the subject: “The Psychological Science of Gender: Women and Men” by Diane N. Ruble and John E. Gruzen, published in the Annual Review of Psychology in 2002.

This paper provides a comprehensive review of research on gender development and the psychological differences between women and men. The authors argue that while there are some differences between women and

Nick Flor: I don’t see this paper in Google scholar. Did you make it up?

ChatGPT: I apologize for the mistake. “The Psychological Science of Gender: Women and Men” by Diane N. Ruble and John E. Gruzen does not seem to exist.

ChatGPT, created by San Francisco-based firm Open.ai, is backed by Microsoft and hailed by the World Economic Forum as “the start of the generative AI boom.” It is the fastest growing app in history, having snapped up 100 million active users within two months of its launch in November. The algorithm was found to be embedded with a globalist agenda by its engineers.

"They are training the AI to lie," said billionaire Elon Musk, who co-founded OpenAI. The Tesla CEO told former Fox News host Tucker Carlson last month that AI is created by forces on the Left and is being programmed to indoctrinate..

In addition to creating fake studies and legal cases, ChatGPT has also been known to rewrite history. Former Vice President Al Gore’s father, Al Gore Sr., was a leading segregationist and voted against the Civil RIghts Act of 1964 in the Senate. ChatGPT, however, says he voted in its favor. When asked about the fall of Detroit or rampant crime in Chicago, ChatGPT leaves out all references to the Democrat policies that caused it.