The Oklahoma Bar Journal December 2024

Given that attorneys primarily rely on published authority to craft rules and arguments, there could be an increased risk that a gener ative AI detector will assign to a legal piece a higher percent prob ability that it was AI-generated. Therefore, if you are a judge or a supervising attorney wondering if someone used generative AI, we would caution against solely relying on AI detection tools. Furthermore, by uploading doc uments or pasting text into an AI detection tool, you are sharing that data with a third-party company that may not be under a confiden tiality obligation. Depending on the terms of service for the specific tool, that third-party company may even claim ownership rights over the data and use it to train future generative AI models. This could bring up some serious concerns regarding confidentiality obliga tions, attorney-client privilege or a potential violation of the author’s intellectual property rights. Q: Briefly explain what it means for a generative AI model to “hallucinate.” ChatGPT: When a generative AI model “hallucinates,” it means that the model generates informa tion that is incorrect, made-up or nonsensical, even though it sounds plausible. This can include invent ing facts, creating fake references or producing responses that are logically flawed. The AI doesn’t intentionally lie – it simply predicts text based on patterns, but without understanding the accuracy or truth of what it’s generating. Authors : There are different ways in which generative AI can hallucinate when used for legal

In sum, don’t be surprised when more and more of the prod ucts you use on a daily basis start integrating elements of generative AI. Ultimately, some use of gener ative AI may be inevitable, mak ing it that much more important to understand how it works and what its limitations and risks are. Q: In one paragraph, how can an attorney tell if someone ( e.g. , a young associate at the attor ney’s firm or opposing counsel) has used generative AI to draft a document? ChatGPT: An attorney can identify if someone has used gen erative AI to draft a document by looking for certain indicators, such as a lack of nuanced legal reason ing, unusual phrasing, or incon sistencies in style and tone that differ from the person’s typical writing. Additionally, the docu ment may contain generic lan guage, over-reliance on templates, or fail to address specific legal issues pertinent to the case. Tools that analyze text patterns or detect AI-generated content can also assist in this evaluation. Engaging in a conversation about the docu ment’s content can further reveal whether the writer possesses the necessary depth of understanding expected from a human author. Authors: Generative AI “detec tors,” like GPTZero, have some serious drawbacks. For one, they can be wrong. On its FAQ page, GPTZero admits, “There always exist edge cases with both instances where AI is classified as human, and human is classified as AI.” 3 For that reason, GPTZero dis courages educators from punish ing students based on its results.

Q: Can you explain that on an eighth-grade level?

ChatGPT: Sure! Generative AI models like ChatGPT use a special kind of computer program called a transformer. They are trained on a lot of written text, like books and articles to learn how words fit together. During training, the model gets really good at guess ing what word comes next in a sentence based on the words that came before it. After training, when you give it a prompt, it uses what it learned to come up with sentences that make sense and sound like a real person talking. This way, it can answer questions and have conversations! Authors: Importantly, not all AI is considered generative AI. For example, social media and other entertainment apps may use AI to curate suggested content based on usage patterns, and search engines may use AI to retrieve already- created content. These uses would not be considered generative AI. That said, the line is getting increasingly blurred. Take Google, for instance, which recently started including an “AI Overview” sec tion in its search results that relies on generative AI to summarize the content of search results (with varying degrees of accuracy and helpfulness). Also, some chatbots and virtual assistants have moved beyond predefined scripts and now utilize generative AI to pro duce answers. In fact, Microsoft now has an AI-powered chatbot, Copilot, that can “help with creat ing, understanding, and editing documents” in Word and “draft ing a presentation, adding or edit ing slides, and even summarizing decks” in PowerPoint. 2

Statements or opinions expressed in the Oklahoma Bar Journal are those of the authors and do not necessarily reflect those of the Oklahoma Bar Association, its officers, Board of Governors, Board of Editors or staff.

8 | DECEMBER 2024

THE OKLAHOMA BAR JOURNAL