By Valerie C. David
This article will discuss artificial intelligence, with a specific focus on ChatGPT and its role in the legal realm.
AI is Everywhere!
Artificial Intelligence (“AI”) is paralleled with the same evolutionary path as the splitting of the atom.[1] Perhaps that is why many are hesitant to embrace it. Indeed, the “darker side” of AI (i.e., artificial intelligence tools and technologies) has gone unnoticed but has altered the lifestyles of the masses indefinitely.[2] Believe it or not, AI tools are involved in everyone’s daily life, regardless of if they want it to be or not. For example, AI’s “darker side” products include Apple’s Siri, Amazon’s Alexa, chat bots, social media, facial detection and recognition, autocorrect, maps and navigation, search and recommendation algorithms, e-payments, and even self-driving cars.[3] In the legal community, AI, while likely unnoticed, is found in everyday tasks, including legal research.
Searching for cases in an online database, such as Westlaw or LexisNexis? Both use AI and not merely for searching cases. In fact, recently, Thomas Reuters Corporation, owner of Westlaw, paid $650 million in cash for Casetext.[4] “Casetext uses advanced AI and machine learning . . . its key products include CoCounsel, an AI legal assistant powered by GPT-4 that delivers document review, legal research memos, deposition preparation, and contract analysis in minutes.”[5] Not surprisingly, CoCounsel is powered by the same technology that created ChatGPT.[6] Likewise, with Lexis+, attorneys can utilize AI that interacts with them like a “trusted colleague.”[7] Of course, these programs are extremely helpful, but are the truly reliable?
What Exactly is ChatGPT.
When specifically asking ChatGPT “what is ChatGPT,” this is the result:
ChatGPT is a variant of the Generative Pre-trained Transformer 3.5 (GPT-3.5) model developed by OpenAI. It is an advanced natural language processing model that uses deep learning techniques to generate human-like text based on the input it receives. GPT-3.5, on which ChatGPT is based, is one of the most powerful language models to date.
The “GPT” in ChatGPT stands for Generative Pre-trained Transformer, which refers to the model architecture. “Generative” means the model can generate text, “pre-trained” indicates that it is trained on a large corpus of existing text data, and “Transformer” is the specific deep learning architecture used.
ChatGPT is designed to simulate conversation and generate coherent, contextually relevant responses to user inputs. It’s often used in chatbot applications, virtual assistants, and other conversational AI applications.
Users can interact with ChatGPT by providing prompts or questions, and the model generates responses based on the patterns and information it has learned during its training. The aim is to create an engaging and interactive conversational experience with the model.[8]
Simply put, ChatGPT is an AI chatbot, created by OpenAI, that provides advanced conversational abilities. These abilities include answering questions, and assisting with “tasks, such as drafting emails, essays, code.”[9] Indeed, most people have used it without even knowing. Ever chatted with a virtual assistant, asked for help using a chat on a webpage, or been prompted on the phone to say what you need? Viola! ChatGPT technology.[10] Yes, indeed, humans are aligning and working with robots, but is this a good thing for the legal field or not?
ChatGPT – Benefits to The Legal Community.
“AI is most effective when it is used to complement human skills, and people who learn how to leverage this collaboration will get the most mileage out of AI tools.”[11] ChatGPT needs individuals to provide it with information in order to function. While it is merely an enhancement for humans, there are several benefits surrounding the use of ChatGPT, including for attorneys. A few benefits are outlined below.
First, ChatGPT is a great tool to assist in building resumes. In fact, ChatGPT can generate and optimize any role from scratch, which can certainly set apart job seekers from others looking for the same job.[12] To utilize, the job seeker puts in specifics (i.e., what job or role they are applying for and previous experience) and ChatGPT will do the heavy lifting. Indeed, ChatGPT can actually start a resume with very little information and walk a job seeker through every aspect of finalizing. This is a great tool and resource for anyone looking for a job, especially young lawyers or recent law school graduates.
Next, ChatGPT is a great tool and resource in assisting lawyers with discovery. In majority of cases, dealing with discovery is the top complaint amongst litigators and can be a huge headache. Indeed, discovery can be the most disputed aspect of a case causing significant stress. Specifically, when the size of production gets to be in the tens of thousands. ChatGPT can assist. How can it help? To start, it is able to provide an attorney with proposed keyword searches.[13] All an attorney needs to do is ask ChatGPT about the topic of the lawsuit and a whole conversation will ensue until ChatGPT narrows a good list of keywords.[14] This task easily reduces hours of work time and likely provides additional keywords an attorney may not have considered. In addition, ChatGPT can summarize documents, answer specific questions about these documents, create an investigation report, and let attorneys know which documents are relevant or irrelevant.[15] It, however, still relies on an attorney to feed it accurate information and facts about the case.
Finally, ChatGPT can significantly improve an attorney’s writing skills. As an attorney, the art of communication is extremely important, and most attorneys live by their thesaurus to enhance their writing. While a thesaurus can provide a different word to prevent repetitiveness, that is the extent of its uses. From providing ideas, to drafting persuasive arguments, to expanding vocabulary, and establishing another style of writing, ChatGPT, offers a revolutionized approach to writing.[16] According to ChatGPT, attorneys can also use ChatGPT to assist them with social media posts, proof readings and edits, drafting legal documents, and legal research.[17] This feature, is clearly helpful as attorneys usually rehash the same argument and recycle the same old drafts. ChatGPT can provide fresh arguments to the old. But as ChatGPT is utilized, its reliability is also being put to the test.
There is a reason ChatGPT is considered the “dark side” of AI.[18] Attorneys should remember their ethical obligations.
ChatGPT – The Dark Side of AI.
As mentioned, ChatGPT should be utilized as a tool and resource to assist attorneys. It should not be trusted nor taken at its word. Indeed, ChatGPT can mislead attorneys that do not understand its uses and capabilities. While it can review massive amounts of information and provide answers within seconds, it is simply unreliable. According to the courts, attorneys still have an obligation to review and analyze what ChatGPT provides and can face sanctions if they do not.
In, Mata v. Avianca, Inc., the New York US Southern District Court correctly penalized attorneys found relying on ChatGPT.[19] Indeed, counsel for litigant, Mata, used ChatGPT created filings that included “non-existent judicial opinions with fake quotes and citations,” and failed to admit this usage when questioned by the court. The judge noted the harm caused by relying on ChatGPT, including wasting time, money, and resources in “exposing the deception” and the client being deprived of authentic arguments.[20] Additionally, the court went on to state:
There is potential harm to the reputation of judges and courts whose names are falsely invoked as authors of the bogus opinions and to the reputation of a party attributed with fictional conduct. It promotes cynicism about the legal profession and the American judicial system. And a future litigant may be tempted to defy a judicial ruling by disingenuously claiming doubt about its authenticity.[21]
The court went on to hold that the attorneys violated Fed. R. Civ. P. 11 in relying on ChatGPT and failing to review a single case cited to in their filing.[22] Thus, the court imposed a $5,000 monetary sanction, and as a deterrence, ordered counsel to send a letter to each judge that was falsely identified as an author of the fake opinions.[23]
Additionally, a similar situation happened to a young lawyer working in Colorado Springs. The judge in that case ordered the lawyer to explain “why he shouldn’t be sanctioned under Colorado Rules of Civil Procedure 11 and reported to the Office of Attorney Regulation Counsel for the ‘fictitious case citations.’[24]
ChatGPT’s reputation of being unreliable is spreading in the legal community quickly. In a recent South Carolina patent case, the Court agreed with plaintiff’s argument against ChatGPT’s unsupported definition of “foam” and noted, thus far, that “ChatGPT’s batting average in legal briefs leaves something to be desired.”[25]
Another important Order was recently entered by Honorable Peter D. Russin, in the Bankruptcy Court for the Southern District of Florida. In his Order, Judge Russin provided his thoughts on ChatGPT’s reliability, or lack thereof, concerning a dispute over three social media accounts. Judge Russin wrote that that regulation is necessary to mitigate the risks imposed by AI.[26] He also included in the Order his own personal experience with ChatGPT:
In preparing the introduction for this Memorandum Opinion, the Court prompted ChatGPT to prepare an essay about the evolution of social media and its impact on creating personas and marketing products. Along with the essay it prepared, ChatGPT included the following disclosure: “As an AI language model, I do not have access to the sources used for this essay as it was generated based on the knowledge stored in my database.” It went on to say, however, that it “could provide some general sources related to the topic of social media and its impact on creating personas and marketing products.” It listed five sources in all. As it turns out, none of the five seem to exist. For some of the sources, the author is a real person; for other sources, the journal is real. But all five of the citations seem made up, which the Court would not have known without having conducted its own research. The Court discarded the information entirely and did its own research the old-fashioned way. Well, not quite old fashioned; it’s not like the Court used actual books or anything. But this is an important cautionary tale. Reliance on AI in its present development is fraught with ethical dangers.[27]
Other major concerns surrounding ChatGPT in the legal community are job security and billing issues. Concerning job security, while the technology is not entirely there yet, it is not out of the realm of possibilities that ChatGPT could reduce and/or replace current available jobs in the legal community[28] In fact, AI technology surrounding ChatGPT is ever evolving at an alarming rate and it has all the makings of a true advocate (at least on paper).[29] Interestingly, “ChatGPT is also aware that it could one day ‘be used to replace human lawyers and legal professionals, potentially leading to job losses and economic disruption.’[30] Concerning billings issues, with utilizing ChatGPT attorneys will reduce time, but will that reduction reflect in their billing? Additionally, will double billing become more prevalent as attorneys have more free time? Attorneys are to be held to the highest ethics and ChatGPT could be the very tool to lead them unknowingly to the dark side of AI.[31]
Regulating ChatGPT in the Legal Community.
As mentioned, the courts are becoming aware of ChatGPT’s unreliability and improper use and the need for regulation. Honorable Brantley Starr, of the U.S. District Court for the Northern District of Texas appears to be the first federal court judge to assert a requirement that attorneys “in cases before him certify that they did not use artificial intelligence to draft their filings without a human checking their accuracy.”[32] Judge Starr became aware of ChatGPT’s reliability issues while attending an AI panel and he asserts his requirement is to make attorneys aware of ChatGPT’s reliance issues and remind them they have sworn duties that AI bots do not.[33] Since the ruling in Mata v. Avianca, Inc., several federal judges have since added requirements that attorneys disclose “when they have used artificial intelligence in matters that appear on their dockets.”[34]
I too learned about ChatGPT’s reliability issues during a recent panel, which prompted me to write this article. While I have heard of ChatGPT, I honestly have never used it until writing this article. As the issues surrounding ChatGPT were addressed, most Florida judges agreed that a show cause order should be issued, and potential sanctions would be addressed for any filing that had fake cases cited because it is considered a frivolous filing. Some judges, however, did not feel the need to make the same requirements as Judge Starr, citing the AI used in LexisNexis and WestLaw as reliable.[35]
The Florida Bar appears to also be considering regulating AI in the legal community, including the need for attorneys gaining client consent for using AI. Indeed, it appears “Florida bar leaders have tasked the Florida Board Review Committee on Professional Ethics with creating rules around the use of generative AI, such as OpenAI’s ChatGPT, Google Bard or Microsoft’s Bing.”[36] This could be problematic as AI is ever changing, but broad general regulations that safeguard truth and remind attorneys of their ethical duties are certainly welcome.
In asking ChatGPT how to close my article, below is its response:
As the legal community navigate the uncharted territory of ChatGPT’s influence in the legal sphere, the scales of justice must find equilibrium in the age of AI. To preserve the integrity of our legal system, it’s imperative to craft regulations that harmonize the wisdom of human judgment with the potential of artificial intelligence. In this delicate balance, the future of law hinges on our ability to uphold the ideals of fairness, accuracy, and the sanctity of justice in a world where the line between fact and fiction blurs in the digital realm.[37]
[1] Ron Karjian, The history of artificial intelligence: Complete AI timeline, TechTarget (Aug. 16, 2023), https://www.techtarget.com/searchenterpriseai/tip/The-history-of-artificial-intelligence-Complete-AI-timeline.
[2] Id.
[3] Id.; Sasha Reeves, 8 Helpful Everyday Examples of Artificial Intelligence, iot for all (Jan. 24, 2023), https://www.iotforall.com/8-helpful-everyday-examples-of-artificial-intelligence.
[4] Thomson Reuters Completes Acquisition of Casetext, Inc., Thomson Reuters (Aug. 17, 2023), https://www.thomsonreuters.com/en/press-releases/2023/august/thomson-reuters-completes-acquisition-of-casetext-inc.html.
[5] Id.
[6] John Villasenor, How AI will revolutionize the practice of law, Brookings (Mar. 20, 2023), https://www.brookings.edu/articles/how-ai-will-revolutionize-the-practice-of-law/.
[7] LexisNexis, https://www.lexisnexis.com/en-us/products/lexis-plus-ai.page (last visited Oct. 21, 2023).
[8] In using ChatGPT, I prompted it with the following: “what is chatgpt.”
[9] Sabrina Ortiz, What is ChatGPT and why does it matter? Here’s what you need to know, ZDNET (Sept. 15, 2023), https://www.zdnet.com/article/what-is-chatgpt-and-why-does-it-matter-heres-everything-you-need-to-know/.
[10] In using ChatGPT, I prompted it with the following: “what is chatgpt.”
[11] See John Villasenor, supra note 8.
[12] Sabrina Ortiz, How to use ChatGPT to build your resume, ZDNET (Jun. 21, 2023), https://www.zdnet.com/article/how-to-use-chatgpt-to-build-your-resume/.
[13] John Tredennick and Dr. William Webber, Five Ways to Use ChatGPT for Investigations and E-Discovery, Law.com (May 23, 2023, 9:39 AM), https://www.law.com/legaltechnews/2023/05/24/five-ways-to-use-chatgpt-for-investigations-and-e-discovery/?slreturn=20230915091501.
[14] Id.
[15] Id.
[16] Victoria S., 10 Ways I Use Chat GPT to Improve My Writing Skills, Linkedin (Jul. 9, 2023), https://www.linkedin.com/pulse/10-ways-i-use-chat-gpt-improve-my-writing-skills-victoria-s-#:~:text=One%20of%20the%20most%20effective,sentence%20structure%2C%20and%20improved%20flow.
[17] In using ChatGPT, I prompted it with the following: “Can ChatGPT improve an attorneys writing?”
[18] See generally, PTI, Dark side of AI: Potential consequences of emotionless machines could impact humanity, The Economic Times (Aug. 3, 2023, 6:08 PM), https://economictimes.indiatimes.com/magazines/panache/dark-side-of-ai-potential-consequences-of-emotionless-machines-could-impact-humanity/articleshow/102393338.cms?from=mdr# (“One of the key reasons we shouldn’t let AI have executive power is that is entirely lacks emotion, which is crucial for decision-making. Without emotion, empathy, and a moral compass, you have created the perfect psychopath.”).
[19] Mata v. Avianca, Inc., 22-CV-1461 (PKC), 2023 WL 4114965, at *12 (S.D.N.Y. Jun. 22, 2023).
[20] Id. at *1.
[21] Id.
[22] Id.
[23] Id.
[24] Clara Geoghegan, Colorado Lawyer Cited Fake Cases in Motion Written with ChatGPT, Law Week Colorado (Jun. 21, 2023), https://www.lawweekcolorado.com/article/colorado-lawyer-cited-fake-cases-in-motion-written-with-chatgpt/.
[25] Carl Pegnatori & Monsta Athletics LLC, v. Pure Sports Technologies, LLC, 2:23-CV-01424-DCN, 2023 WL 6626159, at *5 (D.S.C. Oct. 11, 2023).
[26] In re Vital Pharm., 652 B.R. 392, 398 n. 12 (Bankr. S.D. Fla. 2023).
[27] Id.
[28] Jenna Greene, Will ChatGPT make lawyers obsolete? (Hint: be afraid), Reuters (Dec. 9, 2022, 2:33 PM), https://www.reuters.com/legal/transactional/will-chatgpt-make-lawyers-obsolete-hint-be-afraid-2022-12-09/ (“No, lawyers won’t be replaced by artificial intelligence. Yet. Give it a few years.”).
[29] Id.; George T Marvin, Chat GPT-4 is Evolving Faster than Predicted, Medium (Apr. 4, 2023), https://medium.com/@socialautomation/chat-gpt-4-is-evolving-faster-than-predicted-abb4de0d1d45
[30] Jenna Greene, supra note 30.
[31] Francine Ward, Everything You Need to Know About Lawyer Ethics and Social Media, meruscase blog (Aug. 12, 2015), https://blog.meruscase.com/social-media-ethics (“[T]he Florida Bar has imposed among the most restrictive ethics rules of any state.”).
[32] Jacqueline Thomsen, US judge orders lawyers to sign AI pledge, warning chatbots ‘make stuff up’, Reuters (Jun. 2, 2023, 1:17 PM), https://www.reuters.com/legal/transactional/us-judge-orders-lawyers-sign-ai-pledge-warning-they-make-stuff-up-2023-05-31/.
[33] Id.
[34] Karen Sloan, Florida bar weighs whether lawyers using AI need client consent, Reuters (Oct. 16, 2023, 4:27 PM), https://www.reuters.com/legal/transactional/florida-bar-weighs-whether-lawyers-using-ai-need-client-consent-2023-10-16/.
[35] Business Court Roundtable, Business Law Section Labor Day Retreat (Sept. 2, 2023,11:45 PM).
[36] Karen Sloan, supra note 36.
[37] In using ChatGPT, I prompted it with the following: “I need a strong memorable statement to conclude my article which is about ChatGPT and why it needs regulation in the legal community.”