Let’s Talk, ChatGPT: What Will the Judiciary’s Future Look Like?
In a 2016 article for The Florida Bar Journal, I offered the following question for discussion: Could computers eventually diminish, or even eliminate, the need for human judges? At the time, I foresaw no danger that trial court judges would become obsolete but predicted that technological progress in artificial intelligence (AI), such as IBM’s Watson program, posed the greatest danger to the existence of appellate court judges.
Appellate issues are presented to the courts by written submission, usually through briefs or motions, identifying the specific issues on appeal. These issues are phrased in a manner to allow appellate judges to analyze them according to an established body of law. The relevant underlying facts have been “found” by the lower tribunal; the appellate court considers those established facts according to the applicable law. Or, the court is asked to interpret the meaning of words or phrases in a law to properly apply to a given set of facts. Under either scenario, a computer program like [IBM’s] Watson could be programmed to provide answers to such questions submitted to it.
Well, move over Watson. Make room for ChatGPT, an AI language model produced by OpenAI that was released in late 2022 and is free for users. A judge in Colombia even used ChatGPT to assist in drafting a court ruling in what was apparently the first public acknowledgement by a judge anywhere that an AI text generator had helped craft a legal decision. The judge included the chatbot’s full responses in the decision, along with his own insights into the applicable legal precedents, using AI only to “extend the arguments of the adopted decision.” Although the judge indicated the AI was “mostly used to speed up drafting the decision and that its responses were fact-checked, it’s likely a sign that more legal and judicial uses of AI are on the way.”
The New York Times called ChatGPT “quite simply, the best artificial intelligence chatbot ever released to the general public.” The program, also known as Generative Pre-trained Transformer 3 (GPT-3) generates sophisticated, human-like responses based on requests from users and derived from mountains of data, including a staggering amount of online published text. To understand how it works, for example, if given the phrase “I drove to — ”, allowing the computer to complete the sentence, the model might predict the next words are “the store” with 5% probability, or “work” with 4% probability, etc. The model can then repeatedly predict subsequent words to add to those that have already been predicted (such as inserting an “and”) to compose indefinitely long bodies of text, each sentence building upon the previous one. In March 2023, OpenAI released the new and improved version of the technology that powers its onloine chatbot based on the GPT-4 platform.
ChatGPT was programmed and trained on a general-purpose body of language using a dataset of text called the Common Crawl corpus, which is a collection of web pages and documents from across the internet. It was optimized for general-purpose dialogue, not to provide answers in specific technical areas. It can complete a wide range of tasks, ranging from trivial matters like joke creation to writing essays about the symbolism found in literary works. Since it was made publicly available in November 2022, ChatGPT has been used to not only generate original essays, but also stories and song lyrics in response to user requests.
However, ChatGPT has shown to perform surprisingly well in responding to questions posed in certain technical areas such as computer programming, data manipulation, and medical diagnosis. It has drafted research paper abstracts that have fooled some scientists. It also performed “comfortably within the passing range” of the U.S. medical licensing exam. Corporate CEOs have even used it to write emails or do accounting work. At least one law firm is said to be putting ChatGPT to work in drafting its press releases.
But how does it perform in non-technical fields like law and business? The answer may surprise you.
According to a study at the University of Pennsylvania, ChatGPT fared well on a business management exam at the Wharton Business School where it earned a B to B- grade. In a paper detailing its performance, Prof. Christian Terwiesch said ChatGPT did “an amazing job” at answering basic operations management and process-analysis questions. Unfortunately, it struggled with more advanced questions and made “surprising mistakes” with basic math that “can be massive in magnitude.”
Elsewhere, at the University of Minnesota Law School, professors used ChatGPT to assess its performance on law exams in four courses, then graded the tests blindly. After completing 95 multiple choice questions and 12 essay questions, the bot scored “on average at the level of a C+ student, achieving a low but passing grade in all four courses.” The bot’s performance may not be the sort one would be overly proud of, but it was nonetheless sufficient to earn college credit. For someone who doesn’t bother to attend class or read even a single chapter in the textbook, a C+ grade might be entirely acceptable. With some degree of human input and editing to the final product, it is not inconceivable that this C+ could possibly have been bumped up to an even higher grade — perhaps a B, or even a B+.
While ChatGPT using the GPT-3 technology proved to be adept at answering law school essay questions, it came up short on the multi-state multiple-choice portion of the bar exam, but did pass both the evidence and tort sections. However, according to OpenAI, the new GPT-4 is able to score a 1,300 (out of 1,600) on the SAT and can now perform among the top 10% of students on the Uniform Bar Examination. In a demonstration of its capabilities handling legal questions, OpenAI’s President and Co-Founder Greg Brockman gave the new bot a bar exam question containing several paragraphs to analyze, and the initial answer it provided was correct but “filled with legalese.” When asked to explain its answer in plain English so a layperson could understand, the bot was also able to do that as well.
One adjunct law professor in Texas recently tested ChatGPT’s abilities in the legal academic realm by giving it exercises and quizzes he designed for his law and computer science graduate students. For one question, he asked ChatGPT about the differences between “electronic discovery and computer forensics” and compared the response to his own. What he got back from ChatGPT was a surprisingly good answer that not only adequately addressed the topic but even mentioned its application in another field:
My response in class focused on the relative accessibility and intelligibility of the [electronically stored information] we deal with in e-discovery versus digital forensics, and I didn’t tie forensics to criminal investigations because so much of my work in the field has concentrated on civil cases. But I can’t say I did any better than the AI.
So, if ChatGPT can perform well enough to be an average law school student or an average law school professor, could it also perform as well as an “average” lawyer by providing accurate legal answers to questions at only a fraction of the cost? Not quite yet.
In another test, ChatGPT was asked to write a blog post for lawyers about undue influence claims in California trust and estate disputes. While the response read well and conveyed some concepts correctly, a review showed there were major flaws in the analysis — flaws well-disguised enough to lull an unsuspecting reader into accepting their accuracy. As such, any lawyer who had relied upon ChatGPT’s summary of California undue influence law ran a “high risk of being led astray.”
My experience mirrored those results. When asked to define a legal term contained in a statute, ChatGPT performed very well, correctly providing an answer in line with how the term has been defined in state and federal courts albeit without including any case citations. However, when the bot was asked to write a sample appellate opinion to decide a legal question by using Florida law on a different legal subject, two things happened: first, the program created a trial court order (including a generic case style and a judge’s signature line) instead of any semblance of an appellate opinion; and second, it gave the wrong answer. In fact, this second question I asked is directly answered by a specific Florida statute, which the algorithm did not provide, nor did it produce any caselaw citations supporting its incorrect result. Although the bot presented its answer in an authoritative-sounding manner, any reliance on the conclusion reached would be grossly misplaced with potentially disastrous financial consequences for its unwary consumer.
But the day when AI improves to the point where it can equal or surpass what a human can do may not be far off. A medical doctor recently published a paper written almost entirely by ChatGPT, calling himself an author of the piece only because he thought of the topic and edited the paper and because many scientific journals will not accept an AI program as the exclusive author. In another test of the technology, Suffolk University Law School Dean Andrew Perlman set what could be a speed record by co-writing a 14-page law article using ChatGPT — in one hour.
For his article, Perlman gave ChatGPT a series of orders known as “prompts.” The prompts included: draft a brief to the U.S. Supreme Court on why its decision on same-sex marriage should not be overturned; explain the concept of personal jurisdiction; develop a list of deposition questions for the plaintiff in a routine motor vehicle accident; create a contract for the sale of real estate in Massachusetts; and half a dozen others.
Perlman published ChatGPT’s word-for-word responses in his article. While not necessarily producing a work product on par with an elite Supreme Court advocate, the responses were not bad, despite some answers being “imperfect and at times problematic.” When talking to Reuters, Perlman said the bot may not be “ready for prime time,” but “it doesn’t seem all that far off.”
In another test, ChatGPT critiqued its own legal abilities and acknowledged its limits: “It is not ethical for me to provide legal advice as I am not a qualified legal professional.” In Dean Perlman’s article, the bot noted, “Because ChatGPT is a machine learning system, it may not have the same level of understanding and judgment as a human lawyer when it comes to interpreting legal principles and precedent.” The bot also added, “This could lead to problems in situations where a more in-depth legal analysis is required.” Perhaps more ominously, ChatGPT also posited that it could — one day — “be used to replace human lawyers and legal professionals, potentially leading to job losses and economic disruption.”
To understand ChatGPT’s potential place in the legal field, one must understand how ChatGPT, using the GPT-3 platform, views the American legal system and the state of modern lawyers. In my own test of ChatGPT’s responses, I asked the bot several questions relating to the law, lawyers, and the courts.  Here are some of the verbatim responses I received:
Prompt: Why Would Anyone Want To Be A Lawyer?
People become lawyers for a variety of reasons, including:
1) Passion for justice and helping others — many lawyers are motivated by a desire to serve their communities and protect the rights of others.
2) Interest in the law and legal system — some people are fascinated by the intricacies of the legal system and enjoy the intellectual challenge of understanding and interpreting laws.
3) Desire for prestige and financial rewards — the legal profession is well-respected and can be financially rewarding, which attracts some individuals.
4) Influence and impact — lawyers have the power to shape public policy, advocate for change, and make a real difference in people’s lives.
5) Personal and professional growth — a legal education and career can provide opportunities for personal and professional development and growth.
Prompt: What Advice Would You Give To Someone About Whether To Go To Law School?
Here is some advice to consider when deciding whether to go to law school:
1) Consider your motivations and goals: Why do you want to become a lawyer? Do you have a clear idea of what you want to do with a law degree? Make sure you have a good understanding of the day-to-day realities of being a lawyer, and that your motivations and goals align with what the legal profession entails.
2) Assess the job market: Before investing time and money into law school, research the job market and current demand for lawyers. Consider the long-term employment outlook and potential earning potential.
3) Evaluate the financial commitment: Law school is a significant financial investment. Make sure you understand the costs involved, including tuition, living expenses, and opportunity costs. Consider your long-term financial goals and whether law school fits into your overall financial plan.
4) Think about your strengths and skills: Lawyers need to have strong analytical and critical thinking skills, good communication and writing abilities, and the ability to work well under pressure. Consider whether you have these skills and if you are prepared to develop them further.
5) Talk to lawyers: Reach out to lawyers and law students to get a better understanding of what their experiences have been like. Ask about the challenges and rewards of their careers and what they would have done differently.
Ultimately, the decision to attend law school is a personal one that depends on many factors, including your motivations, goals, and financial situation. It’s important to carefully consider all aspects before making a decision.
Prompt: What Are The Pros and Cons of The American Judicial System?
Pros of the American judicial system:
1) Due Process: The judicial system ensures that everyone has the right to a fair trial and protection against arbitrary or unreasonable treatment by the government.
2) Protection of individual rights: The judicial system helps to protect individual rights and freedoms, such as freedom of speech, religion, and assembly, by interpreting and enforcing the Constitution.
3) Access to justice: The American judicial system provides citizens with access to the legal process and allows them to seek redress for grievances and to seek justice in disputes.
4) Fair and impartial decision making: The judicial system is designed to be fair and impartial, with judges making decisions based on the law and evidence presented, rather than personal bias.
Cons of the American judicial system:
1) Cost and accessibility: The cost of accessing the legal system can be prohibitively expensive for some individuals and communities, making it difficult for them to seek justice.
2) Inefficiency and delay: The judicial system can be slow and bureaucratic, with cases taking years to resolve.
3) Bias and discrimination: Despite efforts to ensure impartiality, the judicial system has been criticized for systemic bias and discrimination, particularly towards marginalized groups such as people of color, low-income individuals, and the LGBTQ+ community.
4) Complexity and technicality: The legal system can be complex and technical, making it difficult for laypeople to understand and navigate.
Overall, the American judicial system has both strengths and weaknesses, and efforts are constantly being made to improve its fairness, accessibility, and efficiency.
Prompt: Do Juries Make Better or Fairer Decisions Than Those Reached By Judges?
The answer to whether juries or judges make better or fairer decisions is a matter of debate and can depend on the individual case and circumstances. Both juries and judges have their strengths and weaknesses, and each approach can result in different outcomes.
Pros of juries:
1) Representation of the community: Juries are made up of ordinary citizens, which can provide a broad representation of the community and bring different perspectives to the decision-making process.
2) Protection against government overreach: By involving ordinary citizens in the decision-making process, juries can serve as a check against government overreach or abuse of power.
3) Empathy and compassion: Juries are made up of human beings and can bring empathy and compassion to the decision-making process, which can lead to more nuanced and human-centered outcomes.
Cons of juries:
1) Lack of legal expertise: Juries may not have the same level of legal expertise as judges, which can lead to misunderstandings of the law and factual evidence.
2) Bias and prejudice: Juries can be influenced by bias and prejudice, which can lead to unfair or unjust outcomes.
Pros of judges:
3) Legal expertise: Judges have extensive legal training and experience, which can help ensure that the law is applied correctly and fairly in each case.
4) Impartiality: Judges are expected to be impartial and make decisions based on the law and evidence presented, rather than personal bias.
Cons of judges:
1) Lack of diversity: The pool of judges may not reflect the diversity of the community, which can lead to a lack of understanding and empathy for different perspectives and experiences.
2) Risk of government overreach: Judges are appointed or elected officials and may be influenced by political pressure or government overreach.
In conclusion, both juries and judges have their strengths and weaknesses, and each approach has the potential to result in fair and impartial decisions, or to be influenced by bias or prejudice. The most important thing is that the legal system is designed to ensure fairness and due process, regardless of whether the decision is made by a jury or a judge.
Prompt: What Is the Value To A Lawyer In Joining A Voluntary Bar Association?
Joining a voluntary bar association can offer a number of benefits to lawyers, including:
1) Professional Development: Bar associations offer opportunities for lawyers to participate in continuing legal education programs and to stay up-to-date on the latest developments in their field.
2) Networking: Bar associations provide a platform for lawyers to network with their peers, make new connections, and build professional relationships.
3) Access to resources: Bar associations often offer resources such as practice management tools, legal research databases, and other resources to help lawyers run their practices more effectively.
4) Representation and advocacy: Bar associations represent the interests of the legal profession and advocate for policies that benefit lawyers and their clients.
5) Public Service: Many bar associations encourage and support lawyers in providing pro bono services and participating in community service initiatives.
6) Ethics and Professionalism: Bar associations often have codes of ethics and professional conduct that members are expected to abide by. These codes help to maintain high standards of professionalism within the legal community.
In summary, joining a voluntary bar association can provide lawyers with valuable opportunities for professional growth, networking, and service to the legal community and society at large.
Prompt: What Advice Would You Give To Someone On How To Be A Good Lawyer?
Here are some tips for becoming a good lawyer:
1) Develop strong analytical and critical thinking skills: Lawyers need to be able to analyze complex information, identify key issues, and develop effective arguments.
2) Build strong research and writing skills: Lawyers need to be able to research the law, write clear and concise legal documents, and communicate effectively with clients and other legal professionals.
3) Be knowledgeable and stay up-to-date on the law: Laws and legal precedent are constantly evolving, so it is important for lawyers to stay informed and current on changes and developments in their field.
4) Develop strong interpersonal skills: Lawyers must be able to communicate effectively and build relationships with clients, judges, and other legal professionals.
5) Be organized and detail-oriented: Lawyers must be able to manage large volumes of information, deadlines, and complex cases.
6) Display ethical behavior: Lawyers must adhere to high ethical standards and act in the best interests of their clients.
7) Develop a sense of professionalism: Lawyers should approach their work with a sense of professionalism, dedication, and a commitment to justice.
8) Seek feedback and continue to improve: Lawyers should be open to feedback, seek opportunities to learn and grow, and continually strive to improve their skills and knowledge.
In conclusion, being a good lawyer requires a combination of strong analytical and interpersonal skills, a commitment to ethics and professionalism, and a willingness to continuously learn and improve.
Prompt: Describe Potential Uses For GPT-3 By Appellate Court Judges
Appellate court judges could potentially use GPT-3 for several purposes, including:
1) Research: GPT-3 could be used to conduct legal research, helping judges find relevant case law and statutes quickly and accurately.
2) Writing: GPT-3’s language generation capabilities could be used to assist judges in writing opinions, saving time and ensuring consistency in language usage.
3) Summarization: GPT-3 could be used to summarize legal briefs and other documents, providing a quick and concise overview for judges to reference.
4) Language Translation: If a judge needs to review a document written in a language they are not fluent in, GPT-3’s language translation capabilities could be used to provide an accurate translation.
It’s important to note that these uses for GPT-3 would need to be used with caution and in accordance with ethical and legal considerations, such as ensuring accuracy, impartiality and ensuring that the technology is not being relied upon to make decisions or affect the outcome of a case.
Prompt: Describe the Effect GPT-3 Might Have on The Future of The Judiciary, Including Trial and Appellate Court Judges
GPT-3 is likely to have a significant impact on the future of the judiciary, including both trial and appellate court judges. Some potential effects are:
1) Increased Efficiency: With the ability to conduct research, summarize documents, and assist in writing opinions, GPT-3 could help judges work more efficiently and handle a larger volume of cases.
2) Improved Consistency: By using GPT-3 to assist in writing opinions, judges could ensure greater consistency in language usage and help reduce inconsistencies between different judicial opinions.
3) Improved Access to Information: By using GPT-3 for legal research, judges could have quick access to a large and up-to-date database of case law and statutes, potentially improving the accuracy of their decisions.
4) Enhanced Language Support: By using GPT-3 for language translation, judges could have access to documents in a wider range of languages, potentially improving their ability to understand the facts and arguments presented in a case.
However, it’s important to note that the adoption of AI technologies like GPT-3 in the judiciary would need to be done with caution, to ensure that they are used in a way that is ethical, impartial and in accordance with legal principles. Furthermore, the technology’s limitations and biases must be acknowledged and addressed to ensure that it is not relied upon to make decisions or affect the outcome of a case.
As one can see, the answers are thought-provoking. Interestingly, ChatGPT also provided a nearly identical disclaimer when answering questions involving its own advice.
In his law review article, Perlman cautioned that “the use of an AI tool for law-related services raises a host of regulatory and ethical issues.” While these issues may be causes for concern, the technology also has some potential benefits and highlights the promise of utilizing artificial intelligence in the practice of law. According to Perlman, the technology offers “‘significant potential to address access to justice questions’ in making legal services available to people of limited means.” In his view, lawyers could use the technology for more routine legal issues to enhance the quality of their work by producing “something better than machine or human could do alone.” He also feels first-year law students can benefit by learning about using ChatGPT as a tool in their clinical programs as well as for legal research and writing.
I also asked ChatGPT the same question I asked in my 2016 article: Could computers eventually diminish, or even eliminate, the need for human judges? Here is its response:
Computers have the potential to assist human judges in decision-making and streamline certain judicial processes, but it is unlikely that they will completely eliminate the need for human judges in the near future. This is because the legal system involves complex ethical, moral, and societal issues that computers may not be able to fully understand and make decisions on. Additionally, the biases and limitations of the data and algorithms used in artificial intelligence systems could have unintended consequences in the legal system. Human judges bring a unique combination of experience, empathy, and judgment that is essential for fair and just decision-making in the legal system.
Disruption in the legal industry and the judiciary from AI’s rapid development may no longer be a theoretical “what-if” in a distant future. Although GPT-4 might not replace doctors or lawyers anytime soon, experts predict it could soon replace some paralegals. Perlman predicts that the impact AI will have on our lives and our profession will, nonetheless, be transformative:
The issues facing the legal industry and legal education are illustrative of the broader implications of AI for society more generally and knowledge workers particularly. Tools like ChatGPT may transform our world in ways that could be at least as important as the advent of the Internet. Of course, as numerous people have noted in jest, “predictions are difficult, especially about the future[.]” That said, it is becoming increasingly clear that AI tools like ChatGPT are going to have a substantial impact on our lives. We need to find ways to adapt to these developments because (to quote another figure, though fictional) resistance is futile.
For what it’s worth, ChatGPT agrees. Perlman asked it to write a poem about how its technology will change legal services. In an unpublished response to the prompt, the bot replied: “ChatGPT will guide us through with ease. /. . . / It will be a trusted companion and guard / Helping us to provide the best legal services with expertise.”
 Judge Mark W. Klingensmith, Computers Laying Down the Law: Will Judges Become Obsolete?, 90 Fla. B. J. 80 (2016).
 ChatGPT: Optimizing Language Models for Dialogue, OPENAI (Nov. 30, 2022), https://openai.com/blog/chatgpt.
 Colombian law does not forbid the use of AI in court decisions. According to Judge Juan Manuel Padilla Garcia, who presides over the First Circuit Court in the city of Cartagena, “The purpose of including these AI-produced texts is in no way to replace the judge’s decision.” He added, “What we are really looking for is to optimize the time spent drafting judgments after corroborating the information provided by AI.” Janus Rose, A Judge Just Used ChatGPT to Make a Court Decision, Vice (Feb. 3, 2023), https://www.vice.com/en/article/k7bdmv/judge-used-chatgpt-to-make-court-decision.
 Nico Grant & Cade Metz, A New Chat Bot Is a ‘Code Red’ for Google’s Search Business, N.Y. Times, Dec. 21, 2022, available at https://www.nytimes.com/2022/12/21/technology/ai-chatgpt-google-search.html#commentsContainer.
 GPT-3 is the third-generation Generative Pre-trained Transformer. GPT-3 is what artificial intelligence researchers call a neural network; a mathematical system loosely modeled on the web of neurons in the brain. Cade Metz, Meet GPT-3. It Has Learned to Code (and Blog and Argue), N.Y. Times, Nov. 24, 2020, available at https://www.nytimes.com/2020/11/24/science/artificial-intelligence-ai-gpt3.html. This is the same technology that identifies faces in photos posted to Facebook and recognizes the commands spoken into iPhones. A neural network learns such skills by pinpointing patterns in vast amounts of digital data. By analyzing thousands of cat photos, for instance, it can learn to recognize a cat. Id.
 This includes nearly a trillion words posted to blogs, social media, and the rest of the internet. Metz, Meet GPT-3. It Has Learned to Code (and Blog and Argue).
 Cade Metz, OpenAI Plans to Up the Ante in Tech’s A.I. Race, N.Y. Times, Mar. 14, 2023, available at https://www.nytimes.com/2023/03/14/technology/openai-gpt4-chatgpt.html.
 Kindra Cooper, OpenAI GPT-3: Everything You Need to Know, Springboard (Nov. 1, 2021), https://www.springboard.com/blog/data-science/machine-learning-gpt-3-open-ai/
 See Jenna Greene, Will ChatGPT Make Lawyers Obsolete? (Hint: Be Afraid), Reuters (Dec. 9, 2022), https://www.reuters.com/legal/transactional/will-chatgpt-make-lawyers-obsolete-hint-be-afraid-2022-12-09/.
 The PyCoach, ChatGPT: The End of Programming (As We Know It), Medium (Dec. 14, 2022), https://medium.com/geekculture/chatgpt-the-end-ofprogramming-as-we-know-it-ac7e3619e706.
 Marie Truong, Can ChatGPT Write Better SQL Than a Data Analyst?, Medium (Jan. 5, 2023), https://towardsdatascience.com/can-chatgptwrite-better-sql-than-a-data-analyst-f079518efab2.
 Phil Wang & Yacine Zahidi, Medical-ChatGPT, GitHub, https://github.com/lucidrains/medical-chatgpt (last visited Jan. 22, 2023).
 Marla Paul, When ChatGPT Writes Scientific Abstracts, Can it Fool Study Reviewers?, Northwestern Now (Jan. 10, 2023), https://news.northwestern.edu/stories/2023/01/chatgpt-writes-convincing-fake-scientific-abstracts-that-fool-reviewers-in-study/.
 Beatrice Nolan, Researchers Just Tested ChatGPT on the Same Test Questions As Aspiring Doctors — And Found the AI Was “Comfortably Within the Passing Range,” Business Insider (Jan. 20, 2023), https://www.businessinsider.com/researchers-tested-chatgpt-same-test-questions-aspiring-doctors-2023-1.
 Samantha Murphy Kelly, ChatGPT Passes Exams from Law and Business Schools, CNN (Jan. 26, 2023), https://www.cnn.com/2023/01/26/tech/chatgpt-passes-exams/index.html.
 Rhys Dipshan, ChatGPT Is Already Helping Write Law Firm Press Releases. Don’t Panic Yet., Law.com (Feb. 1, 2023).
 Christian Terwiesch, Would Chat GPT3 Get a Wharton MBA? A Prediction Based on Its Performance in the Operations Management Course, Mack Inst. for Innovation Mgmt. at the Wharton Sch., Univ. of Pa. (2023), https://mackinstitute.wharton.upenn.edu/wp-content/uploads/2023/01/Christian-Terwiesch-Chat-GTP.pdf.
 Jonathan H. Choi, Kristin E. Hickman, Amy Monahan, and Daniel B. Schwarcz, ChatGPT Goes to Law School, Minn. Legal Stud. Rsch. Paper No. 23-03 (Jan. 23, 2023), available at https://ssrn.com/abstract=4335905.
 Id. (emphasis added).
 Debra Cassens Weiss, AI Program Earned Passing Bar Exam Scores on Evidence and Torts; Can It Work in Court?, ABAJournal.com (Jan. 12, 2023), https://www.abajournal.com/news/article/ai-program-earned-passing-bar-exam-scores-on-evidence-and-torts-can-it-work-in-court.
 Cade Metz and Keith Collins, 10 Ways GPT-4 Is Impressive but Still Flawed, N.Y. Times, Mar. 14, 2023, available at https://www.nytimes.com/2023/03/14/technology/openai-new-gpt4.html.
 Craig Ball, ChatGPT Proves a Mediocre Law Student, Ball in Your Court (Jan. 27, 2023), https://craigball.net/2023/01/27/chatgpt-proves-a-mediocre-law-student/.
 Id. “In terms of its legal knowledge, ChatGPT performed like a mediocre law student, performing well on essay questions and drafting exercises, but struggling with multiple choice questions.”
 Downey Brand LLP & Jeffrey Galvin, ChatGPT Blog Post on Undue Influence Gets a D, JDSUPRA (Jan. 31, 2023), https://www.jdsupra.com/legalnews/chatgpt-blog-post-on-undue-influence-2199134/.
 “ChatGPT is correct that there are statutory presumptions of undue influence in some situations, but the one example ChatGPT offers misses the target. If a will is signed by a person who is not of sound mind…, the court should invalidate the will and need not reach the distinct issue of undue influence.” Id.
 Michael DePeau-Wilson, Peer-Reviewed Journal Publishes Paper Written Almost Entirely by ChatGPT, MedPageToday (Feb. 3, 2023), https://bit.ly/3F4ARP6.
 Andrew Perlman & ChatGPT, Open AI’s Assistant, The Implications of ChatGPT for Legal Services and Society, SSRN (Dec. 5, 2022), https://ssrn.com/abstract=4294197.
 Greene, Will ChatGPT Make Lawyers Obsolete?
 Perlman, The Implications of ChatGPT for Legal Services and Society at 11.
 ChatGPT, Open AI’s Assistant, Inquiry performed on February 1, 2023, https://chat.openai.com/chat.
 Perlman, The Implications of ChatGPT for Legal Services and Society at 1.
 Greene, Will ChatGPT Make Lawyers Obsolete?
 Perlman, The Implications of ChatGPT for Legal Services and Society at 14-15.
 Cade Metz & Karen Weise, Microsoft Bets Big on the Creator of ChatGPT in Race to Dominate A.I., N.Y. Times, Jan. 12, 2023, available at https://www.nytimes.com/2023/01/12/technology/microsoft-openai-chatgpt.html.
 Perlman, The Implications of ChatGPT for Legal Services and Society at 16 (citations omitted).
 Greene, Will ChatGPT Make Lawyers Obsolete?