Consider craftspeople. To be competent, they must know what tools they have, how they work, when to use them and when not to use them. Critically, they must also know how to apply their experience with and knowledge of their tools to achieve the best results for their clients. Tools of the trades change.
Tools of the legal trade change. Just as craftspeople have adapted to computer numerical control machines, commonly called CNCs, so too have lawyers adapted to new tools that have helped them be more productive, from word processors to e-discovery tools to intuitive software that automates contract and other document assembly processes.
Consider Shepard’s Citations. Before online and electronic research became common, lawyers would have to refer to the main hardbound volume of Shepard’s relating to whatever courts and cases they were searching for to discover the latest decisions relating to their subjects. After reviewing the main volume, lawyers would review the many “pocket parts” released with updated references. The process was tedious and had to be done for every case relevant to the matter. Worse, Shepard’s print users were always worried about “missing” something.
It took time for many lawyers to adopt the electronic version of Shepard’s. Nowadays, no one uses the print version. All researchers do now is enter the citation and click a button to see every subsequent case or another source that refers to the authority, easily formatted to display positive, negative and other treatments.
In many ways, artificial intelligence (AI) is the Shepard’s Citations of the 21st century. Many lawyers have heard about it, and some have used it. In my experience, however, only a handful of lawyers admit to using AI, with the overwhelming majority saying they have not. Like the days of print Shepard’s Citations, this too shall pass, and most lawyers will ultimately use generative AI in their practices.
Consequently, this article will discuss what generative AI is and the ethical implications of using (or perhaps not using) it. For most lawyers, generative AI is a new tool they have learned about, but for many, it is the CNC machine they haven’t plugged in.
One recent article explained, "Generative AI refers to machine learning algorithms that can create new content, such as text or images. By leveraging this technology, attorneys can automate much of the initial research and drafting of documents, freeing up their time to focus on more interesting and high-value tasks. For example, [research] platforms . . . use AI to assist with legal research tasks and brief drafting.”
AI compiles a broad range of information that is input into it from various sources, including case law, statutes, contracts, pleadings and transcripts. AI then analyzes the data and responds to queries for information. Perhaps the most well-known AI platform is ChatGPT, also known as OpenAI. Primarily funded by Microsoft, ChatGPT is the poster child for much of what is written about generative AI.
I asked ChatGPT to “explain in one paragraph the types of information AI can learn from and the ways it can use this information to assist lawyers.” It provided the following reply:
AI can learn from various sources of information, including legal documents, case law databases, court records, and legal textbooks, to understand the intricacies of the legal system and specific areas of law. It can use this knowledge to assist lawyers by providing quick and accurate legal research, identifying relevant precedents, drafting legal documents like contracts or pleadings, and even predicting case outcomes based on historical data. Additionally, AI can help automate routine administrative tasks, manage large volumes of legal documents, and assist in compliance and due diligence processes, ultimately enhancing a lawyer's productivity, reducing errors, and enabling them to focus on higher-value strategic tasks.
In other words, AI can improve lawyers' lives and free them from some of the drudgery to focus on more substantive aspects of their client matters. There are, however, ethical implications of using AI. The primary ethical implication is competence, defined in Model Rule of Professional Conduct 1.1: “A lawyer shall provide competent representation to a client. Competent representation requires the legal knowledge, skill, thoroughness and preparation reasonably necessary for the representation.”
Comment 5 to Model Rule 1.1 addresses the required level of thoroughness and preparation lawyers must have: “Competent handling of a particular matter includes inquiry into and analysis of the factual and legal elements of the problem, and use of methods and procedures meeting the standards of competent practitioners. It also includes adequate preparation.”
Comment 8 to Model Rule 1.1 addresses technological competence: “To maintain the requisite knowledge and skill, a lawyer should keep abreast of changes in the law and its practice, including the benefits and risks associated with relevant technology, engage in continuing study and education and comply with all continuing legal education requirements to which the lawyer is subject.”
Thus, Model Rule 1.1, when read in conjunction with the relevant comments, requires lawyers to do what they have always done: evaluate the client’s situation and employ the tools that will best permit them to obtain the desired results efficiently and effectively. Generative AI can be an important tool for reaching that goal.
As with any tool, however, competence first requires an understanding of AI and then requires using it to assist lawyers in achieving the desired results without “hallucinations.” This term describes what happens when AI fabricates results rather than providing accurate answers. According to Ashley B. Armstrong, assistant clinical professor of law at the University of Connecticut School of Law, “Experimenting with these models is both terrifying and fun. When I asked research-related questions, ChatGPT spit back something that sounds very intelligent [and] provided a conglomeration of citations that look real but don’t actually exist.” Armstrong noted that the more obscure the topic is, the more likely it was that ChatGPT would “hallucinate.”
Thus, AI does not and cannot replace the analytical expertise that arises from a lawyer’s experience handling particular matters. It also cannot replace the obligation to verify the accuracy of information, including quotations and citations. Even in the days of paper Shepard’s, lawyers were obligated to review the sources they included in briefs and confirm the accuracy of their quotations.
With Model Rule 1.1 as the foundation for using generative AI (and everything else lawyers do), other Model Rules are also relevant. To assist me, I asked ChatGPT to list the Model Rules of Professional Conduct applicable to a lawyer's use of ChatGPT, and it explained:
“The Model Rules of Professional Conduct, as formulated by the American Bar Association (ABA), do not explicitly address the use of AI tools like ChatGPT. However, several existing rules may be relevant to a lawyer's use of such technology, including:
“Competence (Rule 1.1): Lawyers must provide competent representation to clients, which may include using AI tools responsibly and effectively within their practice area.
“Confidentiality (Rule 1.6): Lawyers must maintain the confidentiality of client information, and when using AI tools, they must ensure that client data remains secure and protected.
“Reasonable Diligence (Rule 1.3): Lawyers should act diligently in representing clients, and when using AI, they should exercise reasonable diligence to ensure the accuracy and reliability of AI-generated advice or documents.
“Communication (Rule 1.4): Lawyers must keep clients informed about the status of their matters and explain matters sufficiently for clients to make informed decisions, which may include explaining the use of AI in their legal services.
“Unauthorized Practice of Law (Rule 5.5): Lawyers should ensure that their use of AI tools does not inadvertently constitute the unauthorized practice of law, particularly when AI generates legal documents or advice.
“Supervision of Nonlawyer Assistants (Rule 5.3): Lawyers who use AI tools should supervise nonlawyer assistants (including AI systems) to ensure they comply with the Rules of Professional Conduct.”
This summary is remarkably accurate and parallels my outline for this article. In addition, ChatGPT added the following caveat:
It's important for lawyers to exercise professional judgment and ethical responsibility when integrating AI tools into their practice, ensuring that their use aligns with these rules and maintains the highest standards of legal ethics and client representation. However, specific interpretations and applications of these rules may vary by jurisdiction, so lawyers should consult with their state or local bar association for guidance.
Where do lawyers go from here so that, once they discover the benefits and risks of generative AI, they can begin using it in an ethical manner that enhances their practices:
Use AI but do so in a manner consistent with the Model Rules of Professional Conduct. A wise computer known as OpenAI recently said, “It's important for lawyers to exercise professional judgment and ethical responsibility when integrating AI tools into their practice, ensuring that their use aligns with these rules and maintains the highest standards of legal ethics and client representation. However, specific interpretations and applications of these rules may vary by jurisdiction, so lawyers should consult with their state or local bar association for guidance.”
