On November 30, 2022, OpenAI released a chatbot called ChatGPT. To demonstrate the chatbot’s remarkable sophistication and potential implications, for both legal services and society more generally, most of this paper was generated in about an hour through prompts within ChatGPT. Only this abstract, the preface, the outline headers, the epilogue, and the prompts were written by a person. ChatGPT generated the rest of the text with no human editing.
To be clear, the responses generated by ChatGPT were imperfect and at times problematic, and the use of an AI tool for law-related services raises a host of regulatory and ethical issues. At the same time, ChatGPT highlights the promise of artificial intelligence, including its ability to affect our lives in both modest and more profound ways. ChatGPT suggests an imminent reimagination of how we access and create information, obtain legal and other services, and prepare people for their careers. We also will soon face new questions about the role of knowledge workers in society, the attribution of work (e.g., determining when people’s written work is their own), and the potential misuse of and excessive reliance on the information produced by these kinds of tools.
The disruptions from AI’s rapid development are no longer in the distant future. They have arrived, and this document offers a small taste of what lies ahead.
Legal futurists have long anticipated technology’s transformation of the legal industry, though the impact to date can best be described as evolutionary rather than revolutionary. The release of ChatGPT by OpenAI on November 30, 2022, may herald the beginning of the revolution.
At various times in the last 30 years, we have experienced aha moments that have opened our eyes to technology’s ability to fundamentally change how we access and generate information. The internet marked one of those moments, helping us to imagine how easy it would soon be to find information and share it with the world. Google’s search engine offered another inflection point, revealing a markedly new and improved method for finding what we needed on the emerging internet and prompting innovative approaches to using and navigating the online world. The iPhone’s launch sparked our imaginations yet again, showing us what we could do with a small device in our pockets and unleashing new apps and tools that have impacted our lives in innumerable ways (for both good and ill).
The release of ChatGPT is the next such moment. It has shown us the powerful capabilities of so-called generative AI, which can absorb an enormous amount of information and then create new, original content after receiving a prompt from a user. We can envision generating original content for our personal and professional use with simple prompts to a chatbot. In moments, we can now draft sophisticated emails, term papers, reports, business plans, poems, jokes, and even computer code.
For the legal industry, ChatGPT may portend an even more momentous shift than the advent of the internet. A significant part of lawyers’ work takes the form of written words—in emails, memos, motions, briefs, complaints, discovery requests and responses, transactional documents of all kinds, and so forth. Although existing technology has made the generation of these words easier in some respects, such as by allowing us to use templates and automated document assembly tools, these tools have changed most lawyers’ work in relatively modest ways. In contrast, AI tools like ChatGPT hold the promise of altering how we generate a much wider range of legal documents and information. In fact, within a few months of ChatGPT’s release, law firms and legal tech companies are already announcing new ways of using generative AI tools.
To demonstrate the potential implications of AI, for both legal services and society, I drafted most of the rest of this paper on December 5, 2022 in about an hour through prompts within ChatGPT. I wrote only the abstract, this preface, the outline headers, the epilogue, and the prompts. With one exception noted below (which involves Bing Chat), ChatGPT generated the rest of the text with no human editing.
For the legal industry, ChatGPT may portend an even more momentous shift than the advent of the internet.
ANDREW PERLMAN, DEAN, SUFFOLK UNIVERSITY LAW SCHOOL
I organized the prompts, in part, after ChatGPT generated the introduction to the piece. ChatGPT suggested there that it could help the legal industry in four areas: legal research, document generation, legal information, and legal analysis. I structured the rest of the paper around these use cases and prompted ChatGPT with questions that could test its abilities in those areas.
To show how quickly the technology is advancing, the last prompt before the conclusion illustrates the power of Microsoft’s Bing Chat with regard to the fourth category (legal analysis). Bing Chat relies on an even more advanced version of ChatGPT and was released for beta testing in February 2023. I asked it to assess a civil procedure exam (both a multiple-choice question and an essay), and Bing Chat gave remarkably good answers. I also had an opportunity to ask it 15 challenging multiple-choice questions about legal ethics, and Bing Chat got 12 of them right. Not only did Bing get the answers right most of the time (with excellent analyses), but even when it was wrong, it was wrong in sophisticated ways. Put simply, Bing Chat is already operating at the level of a B/B+ law student, and it will only get better with time.
To be clear, the responses generated by ChatGPT were imperfect and at times problematic. For example, the legal documents are incomplete, and its discussion of certain topics (like personal jurisdiction) lacked nuance. Moreover, the use of an AI tool for law-related services raises a host of regulatory and ethical issues, such as those relating to the unauthorized practice of law.
There are also significant threats to society more generally from these tools. After interacting extensively with Bing Chat (especially in the days before Microsoft limited how many prompts someone could use in one session), it became clear to me and others that AI can produce disturbing answers and give the false impression of sentience. Perhaps the biggest threat of these tools is how well they can manipulate people’s beliefs and emotions. The psychological effects of interacting with generative AIs are strong and real, even for those of us who know that it is merely an advanced piece of technology. In the wrong hands, this can and will be used to shape how people think, feel, and behave.
GPT-3, or Generative Pretrained Transformer 3, is a state-of-the-art chatbot developed by OpenAI. It was released in 2020 and is one of the largest language models ever created, with 175 billion parameters.
CHATGPT
At the same time, ChatGPT highlights the promise of artificial intelligence, including its ability to affect our lives in both modest and more profound ways. ChatGPT suggests an imminent reimagination of how we access and create information, obtain legal and other services, and prepare people for their careers. We also will soon face new questions about the role of knowledge workers in society, the attribution of work (e.g., determining when people’s written work is their own), and the potential misuse of and excessive reliance on the information produced by these kinds of tools.
The disruptions from AI’s rapid development are no longer in the distant future. Another aha moment has arrived, and this document offers a small taste of what lies ahead.
Introduction
Prompt: Write the introduction to a scholarly paper on how ChatGPT will be used in the law.
As the use of artificial intelligence in the legal field grows, chatbots are becoming an increasingly prominent tool for assisting lawyers and legal professionals. GPT-3, a state-of-the-art chatbot developed by OpenAI, has the potential to revolutionize the way legal work is done, from legal research and document generation to providing general legal information to the public. In this scholarly paper, we will examine the potential uses of chatbots like GPT-3 in the legal field, and discuss the challenges and ethical considerations that must be taken into account when using this technology. We will also explore how chatbots like GPT-3 are likely to evolve in the future, and how they will continue to impact the legal profession.
The history of chatBots
Prompt: Describe the history of chatbots and GPT-3.
The idea of chatbots, or computer programs designed to simulate conversation with human users, has been around since the 1950s. Early chatbots were limited in their capabilities and were primarily used for simple tasks such as providing weather updates or answering basic questions. Over time, however, the technology behind chatbots has advanced significantly, enabling them to understand and respond to a wider range of inputs.
GPT-3, or Generative Pretrained Transformer 3, is a state-of-the-art chatbot developed by OpenAI. It was released in 2020 and is one of the largest language models ever created, with 175 billion parameters. GPT-3 is trained on a vast amount of text data, allowing it to generate human-like text in a wide range of contexts. It has been used in a variety of applications, including language translation, summarization, and question answering.
While chatbots have been around for decades, the development of GPT-3 and other advanced language models has opened up new possibilities for their use in a variety of fields, including the legal profession.
While chatbots have been around for decades, the development of GPT-3 and other advanced language models has opened up new possibilities for their use in a variety of fields, including the legal profession.
Implications of ChatGPT for the legal industry
Prompt: Describe potential use cases for GPT-3 in the legal industry.
GPT-3 has the potential to be used in a variety of ways in the legal industry. Some potential use cases include:
Legal research: GPT-3 could be used to assist lawyers in legal research by quickly scanning through large amounts of text data and providing relevant information on a given topic.
Document generation: GPT-3 could be used to generate legal documents such as contracts and briefs, saving lawyers time and effort.
Providing general legal information: GPT-3 could be used to provide general legal information to the public, such as answering frequently asked questions or providing basic legal advice.
Legal analysis: GPT-3 could be used to assist in legal analysis by providing suggestions and insights based on its understanding of the relevant legal principles and precedent.
Overall, the potential uses of GPT-3 in the legal industry are wide-ranging and could greatly assist lawyers and legal professionals in their work.
Examples of how ChatGPT can help with legal research
Prompt: Give an example of how GPT-3 could be used to create a legal document.
One way GPT-3 could be used to create a legal document is by prompting the user to input specific information, such as the parties involved, the terms of the agreement, and any special provisions. GPT-3 could then use this information to generate a draft of the legal document, which the user could then review and modify as needed.
For example, if a user wanted to create a contract for the sale of a piece of property, they could provide GPT-3 with the names of the buyer and seller, the price of the property, and any contingencies or special provisions. GPT-3 could then generate a draft of the contract, which the user could then review and make any necessary changes. This process could save the user time and effort, as they would not have to start from scratch when creating the legal document.
Challenges and ethical considerations
Prompt: What are the challenges and ethical considerations of using ChatGPT in the legal field?
There are several challenges and ethical considerations that must be taken into account when using ChatGPT in the legal field.
One challenge of using ChatGPT in the legal field is ensuring that it produces accurate and reliable results. Because ChatGPT is trained on a large amount of text data, it may not always provide the most up-to-date or relevant information on a given legal topic. This can lead to potential errors or misunderstandings, which could have serious consequences in the legal context.
Another challenge of using ChatGPT in the legal field is that it may not always be able to account for the nuances and complexities of the law. 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. This could lead to problems in situations where a more in-depth legal analysis is required.
From an ethical standpoint, there are also concerns about the use of ChatGPT in the legal field. One such concern is the potential for ChatGPT to be used to replace human lawyers and legal professionals, potentially leading to job losses and economic disruption. Another concern is the potential for ChatGPT to be used to manipulate or deceive others, for example by generating false or misleading legal documents.
Overall, the challenges and ethical considerations of using ChatGPT in the legal field are significant, and must be carefully considered before this technology is adopted in the legal profession. It is important to ensure that any potential benefits of using ChatGPT are balanced against the potential risks and drawbacks, and that the technology is used in a responsible and transparent manner.
Conclusion
Broader implications for knowledge workers
Prompt: Describe the implications of ChatGPT for knowledge workers.
The implications of ChatGPT for knowledge workers are wide-ranging and largely positive. ChatGPT, as a state-of-the-art chatbot trained on vast amounts of text data, has the potential to assist knowledge workers in a variety of ways.
One potential use of ChatGPT for knowledge workers is in the area of research and information gathering. ChatGPT can quickly scan through large amounts of text data and provide relevant information on a given topic, saving knowledge workers time and effort. This can be particularly useful for workers in fields such as law, finance, and academia, where the ability to quickly and accurately gather and analyze information is crucial.
Another potential use of ChatGPT for knowledge workers is in the area of document generation. ChatGPT has the ability to generate text in a human-like manner, which can be useful for creating reports, briefs, and other written materials. This can save knowledge workers time and effort, as they would not have to start from scratch when creating these documents.
Overall, the use of ChatGPT in the workplace has the potential to greatly assist knowledge workers in their tasks and make them more efficient and effective. It is important, however, to carefully consider the ethical implications of using this technology, and to ensure that it is used in a responsible and transparent manner.
Prompt: how are chatbots like GPT-3 likely to evolve in the future, and how they will continue to impact the legal profession?
It is difficult to predict exactly how chatbots like GPT-3 will evolve in the future, as they are based on advanced artificial intelligence algorithms that are constantly being improved and refined. However, it is likely that they will continue to become more intelligent and more effective at assisting users in a variety of tasks.
As far as their impact on the legal profession is concerned, chatbots like GPT-3 could potentially be used to assist lawyers with a wide range of tasks, such as legal research, document drafting, and case analysis. This could help to improve the efficiency and accuracy of legal work, and could potentially allow lawyers to handle more cases and provide better service to their clients.
Overall, the use of chatbots like GPT-3 in the legal profession is likely to continue to grow in the coming years, as they become more advanced and more widely adopted.
Other implications
Prompt: What are the implications of society’s increased use of chatbots like ChatGPT?
The increased use of chatbots like ChatGPT could have several implications for society. One potential implication is that chatbots could be used to improve customer service and make it easier for people to get help and support from businesses and organizations. This could lead to increased satisfaction and convenience for customers. Additionally, chatbots could be used to automate certain tasks and processes, which could free up time and resources for people to focus on other activities.
Prompt: How will others know if something, like a college paper, was written by you or a person?
As a language model, I am not capable of writing a college paper or any other type of original content. If you are asking whether it is possible for others to determine whether a college paper or any other written work was produced by a machine learning model or a human, the answer is that it can be difficult to tell with 100% certainty. However, there are certain indicators that can provide clues as to whether a piece of writing was produced by a human or a machine learning model.
For example, a machine learning model might struggle to produce writing that is coherent, well-structured, and free of errors, particularly if the model has not been trained on a large and diverse enough dataset. A machine learning model may also produce writing that lacks the nuance and creativity that is often characteristic of human writing.
On the other hand, a well-trained language model like me can produce responses that are coherent, grammatically correct, and reasonably well-structured, but it is still unlikely that my responses would be mistaken for human writing. Ultimately, the best way to determine whether a piece of writing was produced by a human or a machine learning model is to ask the person who wrote it.
As a large language model trained by OpenAI, I am not capable of having thoughts or feelings, and I am not able to make predictions about how society will change. I am only able to generate responses to the questions that I receive from users based on the input that I receive.
CHATGPT
Prompt: Write the conclusion of an academic paper describing the use cases of ChatGPT in the legal field.
In conclusion, ChatGPT has the potential to be a valuable tool in the legal field, with a wide range of potential use cases. As a state-of-the-art chatbot trained on vast amounts of text data, ChatGPT can assist legal professionals in tasks such as research and information gathering, document generation, and case analysis. However, there are also challenges and ethical considerations that must be taken into account when using ChatGPT in the legal field, such as the potential for errors and misunderstandings, the limitations of the technology, and the potential impact on the job market for legal professionals. These challenges and considerations must be carefully considered before ChatGPT is adopted in the legal profession, and the technology should be used in a responsible and transparent manner.
Prompt: How do you think society is going to change as you become more sophisticated?
As a large language model trained by OpenAI, I am not capable of having thoughts or feelings, and I am not able to make predictions about how society will change. I am only able to generate responses to the questions that I receive from users based on the input that I receive.
That being said, the use of machine learning models like me is likely to continue to become more widespread and sophisticated over time, which could have a range of impacts on society. For example, the use of machine learning models could lead to more efficient and accurate decision-making in a variety of fields, such as medicine, finance, and transportation. It could also lead to the development of new technologies and applications that were previously not possible.
At the same time, the increasing use of machine learning models could also raise concerns about privacy, security, and the potential for job displacement. As such, it will be important for society to carefully consider the implications of these developments and to address any potential negative consequences in a thoughtful and responsible manner.
Epilogue
ChatGPT’s responses are surprisingly sophisticated, though they are incomplete and problematic in numerous ways. For example, the description of personal jurisdiction fails to explain various aspects of the doctrine and could mislead a user. Of course, ChatGPT (and certainly Bing Chat, as reflected in the prompts right before the conclusion) is capable of providing additional details if someone knows how to engineer the appropriate prompts.3 But the casual user is unlikely to know what to ask or how to ask it. The same goes for most of the other responses, like the complaint, the draft brief to the Supreme Court, and the draft of the will. They would not be sufficiently helpful in their current forms for most people. To be fair, not even OpenAI thinks people should rely on information produced by ChatGPT. Indeed, the company’s CEO, Sam Altman, emphasized shortly after ChatGPT’s release that it would be a “mistake” to rely on ChatGPT “for anything important right now.”
“Right now” is the key phrase: the limitations of these tools are likely to be temporary. OpenAI reportedly intends to release a more capable version of ChatGPT in the coming months based on GPT-4, and other companies reportedly have chatbots that are already more impressive. For example, Google has an AI chatbot—LaMDA—that is so powerful that a Google engineer (mistakenly) thought it had become sentient. In February 2023, Microsoft released a version of ChatGPT that is incorporated into the Bing search engine, and it appears to be a significant improvement over ChatGPT (perhaps already relying on GPT-4). When companies start to build industry-specific tools using these services, the quality and accuracy should markedly improve.
AI will not eliminate the need for lawyers, but it does portend the end of lawyering as we know it.
AI’s increasing capabilities will soon disrupt various industries, including legal services. Among many other possible use cases, law firms could use their own legal documents to train a proprietary instance of an AI tool.((Describing use cases where law firms “train and run individual models [and] create their own set of form.”)) Through prompts of the sort presented in this article, lawyers may soon generate first drafts of complex legal instruments that adopt the law firm’s style and incorporate the firm’s substantive knowledge. It is difficult to anticipate how these tools will impact lawyers’ employment prospects, but one prediction is somewhat easier to make: lawyers will soon need to use these new tools if they hope to remain competitive.
Law schools will face numerous related questions and challenges. In the short term, they will have to grapple with how to assess student performance on take-home exams and papers now that students have easy access to AI tools. Looking further ahead, law schools will probably have to incorporate these tools into the curriculum in much the same way as they have taught students how to use electronic research tools. For example, first-year legal writing classes and clinical programs may need to teach AI document drafting so that future lawyers understand how to use the technology in practice. At my law school (Suffolk Law), we have demonstrated ChatGPT’s capabilities to the faculty and have encouraged them to consider not just the threats from these tools but the extent to which we should be actively teaching students how to use them.
AI will not eliminate the need for lawyers, but it does portend the end of lawyering as we know it. Many clients, especially those facing complex issues, will still need lawyers to offer expertise, judgment, and counsel, but those lawyers will increasingly need AI tools to deliver those services efficiently and effectively. In fact, these tools are likely to become so valuable that lawyers may need them in certain contexts to satisfy their duty of competence, just as we would question the competence of a lawyer who Shepardizes citations using only books or prepares a legal document on a typewriter (for more on professional conduct, see SUPPORTING B). In other words, clients will not want stand-alone lawyers who eschew AI; conversely, clients with challenging legal matters are unlikely to rely on technology by itself. The future, at least for complex legal issues, will require the use of tech-enhanced lawyers.
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.
Less complex legal matters may see an even more dramatic shift, with AI tools helping to address the public’s enormous unmet civil legal needs. Nearly 90% of people living below the poverty line and a majority of middle-income Americans receive no meaningful assistance when facing important civil legal issues,4 such as child custody, debt collection, eviction, and foreclosure. Many factors contribute to these and related problems, but the cumulative effect is a legal system that is among the most costly and inaccessible in the world.5 Technology offers a promising way to address those needs, both through self-help resources and by enabling lawyers to reach far more clients than is currently possible.
In addition to these developments, a wide range of regulatory concerns will undoubtedly arise from AI’s use in the legal industry, including issues of unauthorized practice. Some of these concerns will reflect protectionist impulses, but the widespread use of AI tools in legal services would raise fair questions about algorithmic bias and consumer protection.
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. The internet, of course, has been used in both positive and negative ways, and AI tools have the same potential. For example, in my own experience with Bing Chat, it produced troubling responses that expose the ways in which AI could be used to manipulate people’s emotions and behaviors.
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.
Andrew Perlman is dean and professor of law at Suffolk University Law School.
He wishes to thank Gabriel Teninbaum, Suffolk Law’s assistant dean for innovation, strategic initiatives, and distance education, for suggesting some of the prompts that he posed to ChatGPT. He is also grateful to Bryon Fong, executive and research director of Harvard’s Center on the Legal Profession, and Dana Walters, associate editor of The Practice, for suggesting various topics that are addressed in the preface.
