Appellate Advocacy Blog

Editor: Tessa L. Dysart
The University of Arizona
James E. Rogers College of Law

Monday, March 27, 2023

Journal of Appellate Practice and Process Volume 23 Issue 1

The Journal of Appellate Practice and Process – Winter 2023 Issue Now Available

The Winter 2023 issue of The Journal of Appellate Practice and Process (Volume 23, Issue 1) is now available. This special issue focuses on appellate issues in and around Indian country. It features the following pieces:

March 27, 2023 | Permalink | Comments (0)

Sunday, March 26, 2023

Personal Jurisdiction – Messy Jurisprudence that May Be in Even Greater Flux

            Rex Lee, the late Reagan-era solicitor general and president of  Brigham Young University, once wrote that the Supreme Court’s “net contribution” to a “cohesive body of law” applying the First Amendment’s  Religion Clauses “has been zero” and added that “some would say that it has been less than zero.”[1] Personal jurisdiction, a subject of intense interest in the Court over the past dozen years, has suffered a similar fate with the Court making a hash of it.

            If there is one case lawyers remember from their civil procedure class, it is Int'l Shoe Co. v. Washington,[2] which established that due process only required that a defendant have “certain minimum contacts” of a continuous and systematic nature with a jurisdiction sufficient “that the maintenance of the suit does not offend ‘traditional notions of fair play and substantial justice.’”[3] Int’l Shoe overturned Pennoyer v. Neff,[4] which adhered to a rigid territorial limitation that was somehow derived from the Due Process Clause. With the demise of Pennoyer, states began to enact long-arm statutes that enabled them to exercise authority over out-of-state defendants who had caused injury and damage within the state. About a decade after Int’l Shoe, the Court speculated that the law would continue to expand “the permissible scope of state jurisdiction over foreign corporations and other nonresidents,” because of the “increasing nationalization of commerce” and the ease of “modern transportation and communication” to make it “less burdensome for a party sued to defend himself in a State where he engages in economic activity.”[5]

            Yet, more recently, the Court has adopted a more restrictive approach to personal jurisdiction than Int’l Shoe suggests, even as it continues to identify that opinion as the “canonical decision” on personal jurisdiction.[6] Its recent cases have reduced Int’l Shoe’s flexibility into a set of mechanical, bright-line rules that it often claims divides personal jurisdiction into only two forms: “specific” and “general.”[7]

Specific jurisdiction exists when the activity or occurrence that is the subject of the lawsuit takes place in forum State.[8] A defective product is sold or shipped there. Thus, in Bristol-Myers, the Court permitted California consumers of the allegedly defective drug to sue the out-of-state manufacturer for their injuries, but held that non-California plaintiffs alleging the same injuries could not sue in that state, but had to initiate separate lawsuits in their home states, even if the allegations were identical. Those who also sued the distribution company in California had to split their lawsuits, because the distributor was California-based and subject to general jurisdiction in California. As Justice Sotomayor pointed out in dissent, the decision was a substantial “contraction of specific jurisdiction by holding that a corporation that engages in a nationwide course of conduct cannot be held accountable in a state court by a group of injured people unless all of those people were injured in the forum State.”[9] Moreover, she points out that the consequences of the decision is to prevent plaintiffs from banding together from different states to bring a single action based on a defendant's nationwide course of conduct, unless they sue in the defendant’s home state, where the action would likely have to be subdivided into claims for each plaintiff’s home state.[10] Yet, where the defendants are from different states so that no one state will be able to entertain the mass action, there will have to be a multiplicity of lawsuits,[11] including potentially separate lawsuits against each defendant, creating a potential “empty-chair” defense.  

General jurisdiction provides all-purpose authority over a defendant when it is “essentially at home” in the forum because it is either incorporated or has its headquarters there.[12] Under the general jurisdiction rubric, illogically, a corporation can have a broad corporate campus and substantial operations in a state, but not be subject to general jurisdiction there. Yet, incorporation in, say, Delaware, where its only presence is a post office box, is sufficient to subject the corporation to suit in that state because it is deemed essentially at home even if not actually present there.

Yet, specific and general are not the only types of personal jurisdiction that exist, even though the Court has said as much. For example, the Court has also recognized “tag” jurisdiction, which subjects an individual from outside the state to jurisdiction when served in the state.[13] Although being subject to personal jurisdiction when caught passing through a state could pose a hardship to an individual, no similar concept permits jurisdiction over a corporation that maintains a continuous and substantial presence in the state. A second form of personal jurisdiction is consent jurisdiction, where the defendant either agrees to jurisdiction or does not fight it.[14] The Supreme Court has previously approved state statutes that require registration and consent to personal jurisdiction as the price of doing business in a state.[15] Yet, on November 8 of last year, the Court heard argument on whether the Pennsylvania consent statute it upheld more than a century ago violated due process in Mallory v. Norfolk Southern Ry. Co., No. 21-1168, where a decision is expected by June.

And there are congressional grants of personal jurisdiction as well.[16] Yet, a 12-5 en banc decision by the Fifth Circuit last year, for which certiorari was denied this past week, required the use of Rule 4(k)(2), promulgated as a federal long-arm statute at the suggestion of the U.S. Supreme Court to reach foreign defendants, still had to satisfy the general jurisdiction test, so that it could never be used for foreign or domestic defendants. [17] Foreign defendants cannot be “at home” in the U.S. And, if general jurisdiction applies, Rule 4(k)(2) is unnecessary The decision effectively renders the rule unconstitutional as a matter of due process.

Is there a way out of the current messy jurisprudence that has developed recently? Justice Gorsuch, joined by Justice Thomas, has suggested that the current personal-injury regime is looking “quaint” and “a little battered” “when corporations with global reach often have massive operations spread across multiple States,” rather than one or two homes.[18] He added, “[m]aybe, too, International Shoe just doesn’t work quite as well as it once did.”[19] So, while the past dozen years have seen a revolution in personal jurisdiction as the Court embarked on a more restrict approach, leavened a bit by its 2021 decision in Ford, another potentially abrupt change may be in the making. Indeed, originalist scholars contend that due process puts no limitation on federal personal jurisdiction.[20] If the Court, which has taken an originalist approach to a number of constitutional issues, goes down that path, they could untangle the ball they created for personal jurisdiction. Could they also replace it with nothing?

 

[1] Rex. E. Lee, The Religion Clauses: Problems and Prospects, 1986 B.Y.U. L. Rev. 337, 338 (1986).

[2] 326 U.S. 310 (1945).

[3] Id. at 316.

[4] 95 U.S. 714 (1877).

[5] McGee v. Int’l Life Ins. Co., 355 U.S. 220, 222-23 (1957).

[6] Ford Motor Co. v. Montana Eighth Jud. Dist. Ct., 141 S. Ct. 1017, 1024 (2021).

[7] Bristol-Myers Squibb Co. v. Superior Ct. of California, San Francisco Cnty., 582 U.S. 255, 262 (2017).

[8] Goodyear Dunlop Tires Operations, S.A. v. Brown, 564 U.S. 915, 919 (2011).

[9] Bristol-Myers., 582 U.S. at 269 (Sotomayor, J., dissenting).

[10] Id. at 277 (Sotomayor, J., dissenting).

[11] Id. at 278 (Sotomayor, J., dissenting).

[12] Goodyear, 564 U.S. at 919.

[13] Burnham v. Sup. Ct., 495 U.S. 604, 619 (1990) (plurality op.).

[14] Ins. Corp. of Ireland v. Compagnie des Bauxites de Guinee, 456 U.S. 694, 703 (1982).

[15] See, e.g., Pennsylvania Fire Ins. Co. v. Gold Issue Mining & Milling Co., 243 U.S. 93 (1917); Ex parte Schollenberger, 96 U.S. 369, 376-77 (1877).

[16] See, e.g., D'Arcy v. Ketchum, 52 U.S. (11 How.) 165, 176 (1850).

[17] Douglass v. Nippon Yusen Kabushiki Kaisha, 46 F.4th 226 (5th Cir. 2022), cert. denied, No. 22-562, 2023 WL 2563319 (U.S. Mar. 20, 2023). The author was counsel for Petitioners in the Fifth Circuit and in the Supreme Court.

[18] Ford, 141 S. Ct. 1017, 1034 (2021) (Gorsuch, J., concurring).

[19] Id. at 1038 (Gorsuch, J., concurring).

[20] See, e.g., Max Crema & Lawrence B. Solum, The Original Meaning of “Due Process of Law” in the Fifth Amendment, 108 Va. L. Rev. 447, 467 (2022); Lawrence B. Solum & Max Crema, Originalism and Personal Jurisdiction: Several Questions and a Few Answers, 73 Ala. L. Rev. 483, 524 (2022); and Stephen E. Sachs, The Unlimited Jurisdiction of the Federal Courts, 106 Va. L. Rev. 1703 (2020).

March 26, 2023 in Appellate Advocacy, Current Affairs, Federal Appeals Courts, United States Supreme Court | Permalink | Comments (0)

Saturday, March 25, 2023

Revisiting George Orwell and Good Writing

This semester, I am lucky enough to be teaching a seminar I designed on bias in legal analysis and writing.  The class has been a delight, and I am impressed every week by my thoughtful and dedicated students. 

In one of our sessions, I proposed using George Orwell’s writing rules, along with his broader concerns with “Doublespeak” and “Big Brother,” to add clarity and remove bias from writing.  Several of my students have included these ideas in the class papers they are drafting, and I hope these tips help you draft as well.

In his pre-1984 essay, Politics and the English Language, Orwell proposed six rules on using English, and he repeated these in later works as well.  Many commentators have discussed using the rules for clarity, but I believe we can also combat bias with these ideas.

Here are Orwell’s rules, as summarized by Judith Fischer in her article Why George Orwell’s Ideas About Language Still Matter for Lawyers, 68 Mont. L. Rev. 129, 135 (2007): 

(i) Never use a metaphor, simile or other figure of speech which you are used to seeing in print.

(ii) Never use a long word where a short one will do.

(iii) If it is possible to cut a word out, always cut it out.

(iv) Never use the passive where you can use the active.

(v) Never use a foreign phrase, a scientific word or a jargon word if you can think of an everyday English equivalent.

(vi) Break any of these rules sooner than say anything outright barbarous.

See also Austin Wayne Schiess, Writing a Brief the George Orwell Way, 14 App. Advoc. 6, 6-6 (2001). 

How can we use these rules in appellate writing?  

  1. Avoid Cliches. Fischer notes: “Think out of the box” and “avoid cliches like the plague.” 68 Mont. L. Rev. at 137.  But seriously, some cliches are racist and many are unclear.  Remove them from your writing as much as possible.
  1. Prefer Shorter Words. I am old enough to remember when courts imposed motion and brief page limits, long before word limits. I recommend reading your own work as if you have page limits and word limits.  This can help you remove legalese, redundant wording, and unneeded long terms.  In his blog, Demian Farnworth suggests practicing by using only monosyllabic words.  The monosyllabic approach can add many words and decrease clearness, but it is a fun way to practice writing with shorter terms.  See https://copyblogger.com/short-sentences/ (Oct. 19, 2015).

3. Be Concise & 5. Avoid Jargon. (I’ve already blogged about Rule 4, Use Active Voice, often.) Use concision as an enemy of bias and obfuscation.  As Justice Ginsburg reminded us, our readers “simply don’t have time to ferret out one bright idea buried in too long a sentence.”  Remarks on Appellate Advocacy, 50 S.C. L. Rev. at 567 (1999).  One way to practice being concise and removing jargon is by reviewing any manual for a small appliance in your home.  Review these manuals for lengthy clauses and odd technical jargon.  My family’s favorite is our toaster manual, which often uses five words where one will do, and adds confusing technical details like “LED light indicator surround ring” for what is in fact the “toasting” light.  Finding these lengthy and confusing terms around the house will help you edit for concision in your briefing.

  1. Use Common Sense--Break Any of these Rules If they Reduce Clarity.  Recently, I learned there is reasonable debate about exactly what Winston Churchill said regarding ending a sentence in a preposition. Nonetheless, we know he said something close to:  “This is the sort of English up with which I will not put.”  See https://brians.wsu.edu/2016/11/14/churchill-on-prepositions/.  We can follow our own common sense, like Churchill and Orwell.  As another example, sometimes one longer clause reads better than a series of short, choppy sentences.  Let’s follow rules on clarity above all else.

Are these rules enough?  Orwell did not think so, as evidenced by his concern over “Doublespeak” and obfuscation.  To follow Orwell, therefore, we should make sure our words say what we mean.  While this sounds simple, any experienced appellate writer knows editing takes time and effort.  I hope Orwell’s rules help in this editing task.

March 25, 2023 in Appellate Advocacy, Appellate Practice, Books, Law School, Legal Ethics, Legal Profession, Legal Writing | Permalink | Comments (0)

Wednesday, March 22, 2023

The power of contrast

On a deep and fundamental level, we crave contrast. Without different colors in our environment, we would be blind because our vision requires contrast to function. Music is monotonous without variation in tone, pitch, and volume. Diet is unpalatable without a variations in (and mixes of) sweet, salt, fat, and heat. 

Writing that captures and keeps our attention is no different. As Ward Farnsworth explains in is Classical English Style, rhetorical power often flows from "various sorts of oppositions--by the relationship, usually one of friction or contrast, between two things. The two things might be plain and fancy words, long and short sentences, hard and soft syllables, high or rich substance and low or simple style (or vice versa), the concrete and the abstract, the passive and the active, the dignified and the coarse, detachment from the audience and engagement with it." That is, your reader is more likely to pay attention when you change up (within reason) what you're throwing at them. 

Judge Bibas of the Third Circuit showed this in his opinion in Trump for President, Inc. v. Secretary, Commonwealth of Pennsylvania (3d Cir., Nov. 25, 2020)His introduction is chock-full of short sentences and short words--the average sentence, just under 12 words; the average word, 5 letters. But in his last paragraph, the words per sentence jumps to 14, and the average word gets just a bit longer. He saves his biggest words (unprecedented, disenfranchising, disproportionate) to make his biggest point--a point that transcends the case and which he wants to draw the most attention to. None of this happens by accident. Great writers like Judge Bibas know how to use contrast in subtlety persuasive ways.

You can do it too--it just takes some practice. Here are a few exercises. Practice saying things in complicated, multisyllabic words (usually Latinate), and then say those same things in simple, one- or two-syllable words (likely Germanic). There is plenty of material out there to work with. For example, you could start with this verse in Genesis: "And God said, Let there be light: and there was light." (Gen. 1:3). Short sentence, short (one-syllable) words, clear ideas. You could make this more complicated with Latinate terms and a nominalization or two: "And Deity vocalized, I give my permission that illumination may exist: and the illumination initiated its existence." Longer sentence, more complicated words. Perhaps a bit silly of an example, but it at least gets you thinking about different ways to put things.  Play the same game with concrete and abstract terms, passive and active voice, etc. 

For the most part, you'll want to use active, simple, straightforward words and sentences. But as Judge Bibas shows, the change-up can really draw your reader's attention when you want to make an important point. Practice doing that, and you're well on your way to improving your style and persuasiveness.    

March 22, 2023 | Permalink | Comments (0)

Tuesday, March 21, 2023

More than "Frenemies."

Daumier good young man PD

I recently had the honor of running into an old moot court student as opposing appellate counsel. It was in a case where there had been some heated language exchanged by trial counsel over an issue that was of serious concern to our clients. We shook hands, laughed at the irony, and then he said we would just have to be “frenemies.”

I’ve thought a fair bit about that exchange. Not because I don’t know what a frenemy is – I am not yet that old, and I do have access to the urban dictionary in case I need to verify - but because I don’t think that term fits the full relationship of opposing appellate counsel. We should be more than that.

Under the ABA model rules, there are only “shall nots” when it comes to the relationship between counsel. Thus, Rule 3.4, Fairness to Opposing Party & Counsel, provides that an attorney “shall not” unlawfully conceal or obstruct access to evidence, falsify evidence, make frivolous discovery requests or objections, and so on.

The Texas Standards for Appellate Conduct, under which I often operate, are much more aspirational. They provide that counsel will treat opposing counsel with respect, be punctual in communications with counsel, not impute bad motives or make personal attacks against counsel, and will not ascribe to opposing counsel a position they have not actually taken. These standards begin with the idea that “Lawyers bear a responsibility to conduct themselves with dignity towards and respect for each other, for the sake of maintaining the effectiveness and credibility of the system they serve.”

I wish all attorneys subscribed to those standards, but they are, perhaps, particularly well-suited to appellate counsel. We, more than any other lawyer, should be able to focus on the issues. We, more than any other lawyer, should be able to distinguish between attacking an argument and attacking opposing counsel. And we, more than other lawyer, should take that role seriously.

How does that pan out in practice? When we step into a case, we should be able to recognize when these ideals are not being met and we should do our best to fix that. Not only to keep the peace, but because that is how we can best serve our clients, who eventually will have those legal issues determined by an appellate court that has no interest in personal feelings.

So, when we step into a trial court to help with issues we know are going to be on appeal, we should step in with the idea that we aren’t just frenemies with opposing appellate counsel. We are working together to try to get the issues resolved as cleanly as possible, and if necessary, preserved and presented in a way that will help the court, and our clients, focus on the issues that have to be resolved. While we are opposed on the issues, we are allies in a larger sense.

That may sound pollyannish. But the courts of appeal in Texas that have all adopted these standards don’t think so. And I’m willing to bet that most appellate courts in the rest of the country would agree that when we act professionally, and even more, cordially, while still vigorously contesting each other’s arguments, we best serve our clients needs and the needs of the system in which we all work.

(photo credit: Brooklyn Museum - "Vous êtes un jeune homme bien né..." - Honoré Daumier).

 

March 21, 2023 in Appellate Advocacy, Appellate Justice, Appellate Practice, Legal Ethics, Legal Profession | Permalink | Comments (0)

Monday, March 20, 2023

GPT-4 Just Passed the Bar Exam. That Proves More About the Weakness of the Bar Exam Than the Strength of GPT-4.

It's official: AI has passed the Uniform Bar Exam.  GPT-4, the upgraded AI program released earlier this week by Microsoft-backed OpenAI, scored in the 90th percentile of actual test takers. 

"Guess you're out of a job," my wife said when I told her the news. 

Maybe she's right--unless, of course, the bar exam isn't actually an effective measurement of minimum competence to practice law. 

That's the open secret of the legal profession.  Bar exams do test a small handful of core legal skills, such as critical reading and basic legal analysis.  But they're downright abysmal at measuring the multitude of skills that separate competent and incompetent lawyers, such as legal research, writing ability, factual investigation, crisis response, communication, practice management, creative problem solving, organization, strategic planning, negotiation, and client management. 

I am hardly the first commentator to draw attention to this issue.  In Shaping the Bar: The Future of Attorney Licensing--which should be required reading for anyone interested in the attorney-licensing conundrum--Professor Joan W. Howarth says this:

Bar exams are both too difficult and too easy.  The exams are too easy for people who excel at multiple-choice questions.  Wizards at standardized tests can pass the bar with little difficulty, perhaps with a few weeks spent memorizing legal rules, without showing competence in a greater range of lawyering skills or any practice in assuming professional responsibility. 

And, bar exams are too difficult for candidates who do not excel at memorizing huge books of legal rules.  An attorney would be committing malpractice by attempting to answer most new legal questions from memory without checking the statute, rules, or case law.  Leon Greene, the dean of Northwestern Law School in 1939, observed that "there is not a single similarity between the bar examination process and what a lawyer is called upon to do in his practice, unless it be to give a curbstone opinion."  The focus on memorization of books of rules was silly in 1939, but today it is shockingly anachronistic, as attorneys asked for "curbstone opinions" would be carrying a complete law library on their phones.  Extensive rule memorization makes bar exams less valid, meaning that they test attributes not associated with competence to practice law.  Law graduates who would be great lawyers--too many of whom are people of color--are failing bar exams because they cannot drop everything else for two months to devote themselves to memorizing thick books of rules.

Against this backdrop, is it really a surprise that a literal learning machine beat 90% of the human test takers?

Predictably, the National Conference of Bar Examiners quickly issued a press release once the news broke about GPT-4 acing its exam.  The NCBE said that human attorneys have unique skills, gained through education and experience, that "AI cannot currently match."  And, on that score, I wholeheartedly agree.  But that raises the question many of us have been asking for years: If "skills," "education," and "experience" (not mass memorization, regurgitation, and fact-pattern recognition) are what set the best lawyers apart, why aren't we using those qualities to measure minimum competence?

___________________________________________________________

Philip Seaver-Hall is a litigation attorney at Knox McLaughlin Gornall & Sennett, P.C.  The views expressed in this post are the author's alone and are not necessarily shared by the Knox Law Firm. 

March 20, 2023 in Books, Current Affairs, Law School, Legal Profession, Science, Web/Tech, Weblogs | Permalink | Comments (0)

Saturday, March 18, 2023

ChatGPT and Legal Writing

ChatGPT is an artificial intelligence chatbot that can, among other things, compose music, play games, and generate student essays and examination answers. Indeed, ChatGPT has already been studied to assess its efficacy on law school examinations. One study, for example, revealed that ChatGPT passed four law school exams at the University of Minnesota -- earning an average grade of C+ -- and an exam at the University of Pennsylvania’s Wharton School of Business.[1]

The leader of the study examining ChatGPT in the law school performance context stated that “[a]lone, ChatGPT would be a pretty mediocre law student," and emphasized that “the bigger potential for the profession here is that a lawyer could use ChatGPT to produce a rough first draft and just make their practice that much more effective.”[2]

Certainly, in law school and in the legal profession, ChatGPT can have benefits. For example, ChatGPT can enhance efficiency by, for example, producing rough drafts of basic legal documents such as complaints, memorandums, interrogatories, and document requests.  Additionally, ChatGPT can assist individuals who cannot afford legal services in producing competent legal documents.

What ChatGPT cannot do, however, is teach law students how to think, how to write, and how to persuade. That, in a nutshell, is the point – and the problem. Below are two concerns regarding ChatGPT’s effects on law school and the legal profession.

1.    Law students need to learn how to think critically.

Learning how to think critically is among the most important skills needed to be a competent lawyer. And in recent years, many students begin their first year of law school lacking this skill. Thus, during the first year of law school, particularly in doctrinal and legal writing courses, students learn, among other things, how to read cases, understand complex legal concepts, synthesize the law, and apply the law to different fact patterns.

ChatGPT is problematic because, in some contexts, it does the thinking for the students. In so doing, it enables students (to some extent) to avoid the admittedly arduous process of understanding and interpreting complex legal doctrines, and presenting such doctrines (e.g., in a memorandum or a brief) in an understandable, logical, and persuasive manner. Indeed, David Kemp, an adjunct professor at Rutgers Law School, stated that “[i]f you’re asking it to organize several concepts, or are struggling to explain something in a way that’s really understandable, it can help.”[3]

That, again, is the point – and the problem.

Students should not be relying on artificial intelligence to organize complex legal concepts or explain them in a way that readers can understand. They should, through hard work and perseverance, develop critical thinking skills so that they can do it themselves. Otherwise, we are training students to rely not on their minds or their legal training, but on a technology that, at best, produces mediocre results.

Perhaps some would describe this as an “old school” approach to legal education. And they would be right. The quality of law students at many law schools has steadily declined in recent years, and ChatGPT threatens to worsen this problem by doing for law students what they should, after three years of legal training, be able to do for themselves.

2.    Law students need to learn how to write competently and persuasively.

It is no secret that judges and lawyers often criticize law graduates for their poor writing skills.[4] The reasons for this include, but are not limited to, insufficient preparation during students' undergraduate coursework, and insufficient dedication to required legal writing courses in law school.

This fact, however, only underscores the need to train students to think – and write – like lawyers. Students need to learn, for example, how to research the law, how to craft a compelling narrative, how to synthesize legal authority, how to reconcile unfavorable facts and law, and how to draft an organized and well-structured legal argument.

To do so, students need to embrace the writing process, which involves writing, rewriting, and editing. It requires critical thinking. Hard work. Perseverance. And the ability to write effectively and persuasively. ChatGPT is not going to teach students how to do this because, at least to some extent, it will do it for them. That makes the problem worse, not better.

To be sure, ChatGPT may produce the equivalent of a mediocre first draft, which students will then edit and re-edit to improve its quality. But good legal writing is not simply about editing. To be an excellent editor, you must first be an excellent writer and re-writer. That means embracing the writing process and acquiring the skills needed to draft, for example, a persuasive motion or appellate brief. As one professor explains.

Legal writing faculty interviewed by the ABA Journal agree that ChatGPT writing can model good sentence structure and paragraph structure. However, some fear that it could detract from students learning good writing skills. ‘If students do not know how to produce their own well-written analysis, they will not pass the bar exam,’ says April Dawson, a professor and associate dean of technology and innovation at the North Carolina Central University School of Law.’[5]

Professor Dawson may be correct that ChatGPT will reduce bar passage rates. What it will almost certainly do is ensure that students never become excellent persuasive writers. And it will also cause some students to rely on ChatGPT to do the hard work that they should be doing, and that is necessary, to produce quality legal work.  This is the risk that reliance on ChatGPT – particularly for complex legal motions and briefs – engenders.

Ultimately, ChatGPT can certainly have benefits. Among those is increasing efficiency and productivity. But law students still need to have the analytical thinking and writing skills to be able to interpret complex legal texts, draft persuasive legal arguments, and present compelling arguments before a court.  As such, ChatGPT’s benefits must be balanced against the need to train students to think, write, and practice like lawyers.

Perhaps this is an “old school” approach, but that approach has produced extraordinary attorneys who have transformed the law and the legal profession through their advocacy.

Simply put, you cannot replace an intelligent, thinking human being.

 

[1] See Samantha Murphy Kelly, “Chat GPT Passes Exams from Law and Business Schools” (January 26, 2023), available at: ChatGPT passes exams from law and business schools | CNN Business

[2] Reuters, “Chat GPT Passes Law School Exams Despite ‘Mediocre’ Performance” (January 25, 2023) available at: ChatGPT passes law school exams despite 'mediocre' performance | Reuters.

[3] Kelly, supra note 1.

[4] See Ann Nowak, The Struggle with Basic Writing Skills (March 1, 2021), available at: The Struggle with Basic Writing Skills | Published in Legal Writing (legalwritingjournal.org)

[5] Kelly, supra note 1.

March 18, 2023 in Appellate Advocacy, Appellate Practice, Current Affairs, Law School, Legal Ethics, Legal Profession, Legal Writing, Rhetoric | Permalink | Comments (4)

Friday, March 17, 2023

Appellate Advocacy Blog Weekly Roundup Friday, March 17, 2023

WeeklyRoundupGraphic

Each week, the Appellate Advocacy Blog Weekly Roundup presents a few tidbits of news and Twitter posts from the past week concerning appellate advocacy. As always, if you see something during the week that you think we should be sure to include, feel free to send a quick note to either (1) Dan Real at [email protected] or on Twitter @Daniel_L_Real or (2) Catharine Du Bois at [email protected] or on Twitter @CLDLegalWriting.

US Supreme Court Opinions and News

  • West Virginia has asked the Supreme Court to vacate in an injunction in a transgender rights case, West Virginia v. B.P.J. The injunction bans a law that prohibits trans-identified boys from competing on female-only sports teams at the secondary and university level. If the Court reaches the merits, it may be the first case where the Court will determine whether the Constitution protects against anti-trans discrimination. See report from Vox.

  • The United States Courts posted this News Release announcing that the Judiciary’s 2022 Annual Report and Statics is now available.

  • The Supreme Court’s memorial for Justice Ruth Bader Ginsberg was held today, Friday, March 17. See a report from the Associated Press.

Appellate Court Opinions and News

  • The Fifth Circuit has refused to recognize the state-created danger doctrine, which is an exception to the general rule that the government has no duty to protect against privately caused harm. Although recognizing that a majority of federal circuits recognize the doctrine and noting that the “facts giving rise to [the] lawsuit are unquestionable horrific,” the Fifth Circuit found that the state-created danger doctrine was not clearly established in the Fifth circuit and cited the recent Dobbs opinion as a basis for not expanding substantive due process rights without careful consideration, including considering whether the right is “deeply rooted in the Nation’s history and tradition.” Thus, the court ruled that a school enjoyed qualified immunity from liability regarding the repeated sexual assault of a severely disabled public-school student on school grounds. In the case, school officials not only knew in advance of the first assault that the victim required supervision at all times and that her attacker had violent tendencies but also knew about the prior attack on the victim by the same attacker before again allowing victim and her attacker to be unsupervised. A dissent posing as a concurrence urged the Fifth Circuit to hear the case en banc and adopt the doctrine, stating “it is well past time for this circuit to be dragged screaming into the 21st century.” See the ruling and reports in The Volokh Conspiracy, Law.com, Courthouse News Service, and Bloomberg (subscription required).

  • The Eleventh Circuit upheld a Florida law that bans people under 21 from owning a gun. In upholding the ban, the court applied the 2022 Bruen framework that requires the government to demonstrate that the regulation “is consistent with this Nation’s historical tradition of firearm regulation” and cited more than a dozen state law barring people under 21 from buying guns. See the ruling and reports from Reuters and CBS News.

  • The Ninth Circuit refused to rehear the November 2022 case that ruled that the First Amendment protected an Oregon beauty pageant’s “natural born female” eligibility requirement and allowed the pageant to ban a transgender contestant. See the November 2022 ruling and the order denying rehearing.  

State Court Opinions and News

  • The North Dakota Supreme Court upheld a lower court decisions that blocked an abortion ban and held that the state constitution protects the right to “enjoy and defend life and a right to pursue and obtain safety,” including the right to an abortion to preserve life or health. See the ruling and report from The New York Times.

March 17, 2023 in Federal Appeals Courts, State Appeals Courts, United States Supreme Court | Permalink | Comments (0)

Wednesday, March 15, 2023

The substantive importance of punctuation in legal arguments; or, how I learned to stop worrying and love the semicolon

Most (all?) ancient languages lacked punctuation and capitalization. Egyptian heiroglyphs, Homeric Greek, Akkadian, etc. were all written in what amounts to all caps with no spaces and no way to tell (other than training and context) where one word or phrase ended and another began. In the case of heiroglyphs (and older Hebrew texts), they even lacked vowels. For many of these writers, opacity was a feature, not a bug, as it protected knowledge thought too sacred for the uninitiated.

While it's certainly possible to write now--even with our vowels, capital letters, and punctuation--to prevent easy understanding, it's not a good idea if you're a lawyer. The idea is to communicate your ideas clearly, keeping the possibility for misunderstanding to a minimum.  

Part of writing clearly is correctly--even elegantly--using punctuation for pauses. We have five commonly-used marks for this (in general ascending order of pause length): comma, semicolon, dash, colon, and period. Many times, it's just a question of style; how long do you want the reader to absorb what you've said?; do you want to connect the ideas more closely and quickly (comma, semicolon, dash) or have them digest things more slowly (colon, period)? But it can also affect the substance of legal arguments.

Use (and non-use) of the Oxford comma in a contract provides one famous example. In many ways, Marbury v. Madison was a decision about reading a semicolon in the Judiciary Act of 1789 as a period. Because the law is words, the laws governing word use and punctuation often rein supreme (absent some exception like the absurdity canon). I once had a case in which a criminal defendant was challenging his counsel's lack of objection to a jury instruction because it resembled an instruction in a prior case that had been held erroneous. I noticed that it differed from the bad instruction because its clauses were separated by semicolons rather than a colon. In my brief, I discussed the differences between the two marks and why it mattered. The court agreed with me that because the instruction had semicolons, it correctly stated the law, so counsel wasn't required to object. State v. Lopez, 438 P.3d 950 (Utah Ct. App. 2019). 

Punctuation may seem like a small thing, but it can determine the outcome of many legal issues. Use it wisely, and if you don't know the technical (as opposed to merely stylistic) differences, start learning them now. You'll be better off, and the courts will appreciate it.  

March 15, 2023 | Permalink | Comments (0)

Monday, March 13, 2023

Guest Post: Can ChatGPT Prepare Me for Oral Argument?

This is a guest post by Jayne Woods, Associate Teaching Professor of Law at University of Missouri School of Law. All faults in fixing bullets points are Professor Dysart's.

As Spring approaches, many legal writing faculty are gearing up to teach oral advocacy to the 1L students.  While there is much discussion and debate about ChatGPT’s role in legal writing, I began to wonder if ChatGPT has a part to play in oral advocacy as well.

We preach to our students that preparation is the key to success in moot court and oral advocacy generally, and we give them strategies like outlining, summarizing relevant case law, and practicing responses to anticipated questions.  So I decided to let ChatGPT flex its muscles as a preparation assistant.

First, I asked it to create an outline based on the general legal framework of my students’ appellate brief problem, which involves both a facial and an as-applied First Amendment challenge to a municipality’s advertising guideline for its public transit system that bars religious content.  The outline looked very much like the examples we give our students:

I. Introduction

    • Introduce the case and state the issue on appeal
    • Introduce the appellant and their argument
    • Provide a roadmap of the oral argument

II. Standard of Review

    • Explain the standard of review for the district court's decision to deny the preliminary injunction
    • Argue that the district court applied the wrong standard of review and that the appellate court should apply de novo review

III. Facial Challenge

    • Argue that the city's advertising guideline prohibiting religious content is unconstitutional on its face
    • Explain that the guideline is content-based and subject to strict scrutiny
    • Argue that the guideline fails strict scrutiny because it is not narrowly tailored to serve a compelling government interest

IV. As-Applied Challenge

    • Argue that the city's application of the guideline to the church's religious advertisement is unconstitutional
    • Explain that the application of the guideline amounts to viewpoint discrimination
    • Argue that the city has not provided a compelling government interest for the discrimination
    • Provide examples of similar advertisements that were accepted by the city, but were not religious

V. Precedent

    • Discuss relevant precedent that supports the church's argument
    • Distinguish precedent that the city may rely on to support its guideline

VI. Conclusion

    • Summarize the argument and emphasize the importance of protecting the First Amendment rights of the church

This seems pretty good, though it does need some tweaking, as our problem does not involve strict scrutiny.  But this strikes me as a great starting point for our students who will be creating their first-ever outline for an appellate oral argument.  In a similar vein, it could help a new attorney making their first argument before an appellate court.

ChatGPT is also adept at creating concise, brief summaries of case law, and I asked it to create summaries of five of the most apposite cases involved, including the court’s reasoning for each.  Here are two examples:

Rosenberger v. Rector and Visitors of the University of Virginia (1995): The court held that the University of Virginia's refusal to fund a Christian student publication was unconstitutional viewpoint discrimination. The court reasoned that the university's policy of denying funding to religious organizations while funding secular organizations violated the First Amendment's Free Speech Clause by discriminating against religious viewpoints.

Archdiocese of Washington v. Washington Metropolitan Area Transit Authority (2017): The court held that the Washington Metropolitan Area Transit Authority's policy of rejecting an advertisement from the Archdiocese of Washington because of its religious content was unconstitutional. The court reasoned that the policy was viewpoint discrimination, as the transit authority allowed advertisements from secular organizations while excluding advertisements with religious messages.

These summaries are wonderfully concise snippets that could help an advocate quickly and easily recall a case for discussion purposes.  That said, the summary for the Archdiocese case is inaccurate; in fact, the Archdiocese lost that case because it failed to establish viewpoint discrimination. I repeatedly asked ChatGPT if it was sure about the accuracy of that summary and, though, it repeatedly admitted error, it continued insisting that the Archdiocese prevailed.  The inaccuracy was likely a result of how ChatGPT works.  It is based, in part, on the statistical structure of language, meaning its responses involve the most likely words in the most likely sequence in response to the prompt.  See https://www.assemblyai.com/blog/how-chatgpt-actually-works/.  When considering that the Archdiocese case is an outlier, ChatGPT’s response makes more sense; in most cases like Archdiocese, the party in the Archdiocese’s position prevails because it is able to establish viewpoint discrimination.  Even though I knew ChatGPT’s answer was incorrect, it was so certain that it caused me to both question my own recollection of the case and look it up again to verify.  But verifying the accuracy of the cases relied on is also good practice for an advocate.

I next asked it to generate some questions that a court might ask during an appellate argument.  This was where it got really cool.  It generated twenty-eight distinct questions and likely would have generated more had the system not become overloaded at the time.  Here are some examples:

  1. How does the Supreme Court's decision in cases such as Board of Regents v. Southworth and Rosenberger v. Rector and Visitors of the University of Virginia affect the outcome of this case?
  2. Are there any specific regulations or guidelines that the bus company must follow when deciding whether to accept or reject an ad?
  3. Has the bus company previously accepted similar ads from other religious or non-religious groups, and if so, how does it justify the differential treatment in this case?
  4. Did the bus company have a reasonable basis for concluding that the religious ad would be likely to cause disruption or harm, and if so, what evidence supports this conclusion?
  5. If the plaintiff prevails, how might this decision impact other cases involving government-owned or government-operated advertising platforms, such as airports or public transit systems?

After having it pose questions, I tried to simulate an actual oral argument.  Specifically, I asked if we could engage in questions and answers where ChatGPT posed as a court and I posed as the attorney answering questions during an oral argument.  It enthusiastically agreed and then proceeded to simply create a transcript of an oral argument involving both questions from a court and answers from an attorney.  It turns out that, while ChatGPT is very adept at answering questions, it’s not terribly inquisitive.  I did manage to get a very brief back and forth after instructing it to ask me a very specific question, which concluded with ChatGPT thanking me for my argument:

Prompt:  ask me a question about my position that a city's advertising guideline barring religious content amounts to viewpoint discrimination

ChatGPT:  Certainly, counsel. How does your argument that the city's advertising guideline barring religious content amounts to viewpoint discrimination relate to the Supreme Court's holding in Rosenberger v. Rector and Visitors of the University of Virginia?

My response:  In Rosenberger, the Supreme Court indicated that, if the government opens a topic for speech, it may not then prohibit speech on that topic solely because of the viewpoint of the speaker. Here, the city allowed an advertisement promoting a children's Easter egg hunt but precluded my client's ad promoting an Easter worship service. Obviously, the city opened up the topic of Easter; thus, its refusal to accept my client's ad was solely because of my client's nature as a house of worship.

ChatGPT:  Thank you for your response, counsel. Can you further explain how your argument aligns with the Supreme Court's holding in Good News Club v. Milford Central School and Lamb's Chapel v. Center Moriches Union Free School District?

My response:  Yes, your honor. In both Good News Club and Lamb's Chapel, this Court encountered similar scenarios, where the government opened up public buildings for certain purposes but then barred religious entities from using the buildings because those entities were seeking to promote Christian viewpoints on the same topics the buildings were opened up to secular groups.

ChatGPT:  Thank you for your response, counsel. Based on your argument and the relevant Supreme Court precedents, it appears that you are contending that the city's advertising guideline barring religious content amounts to viewpoint discrimination, which is unconstitutional under the Free Speech Clause of the First Amendment. Thank you for your argument, counsel.

              This was great, albeit brief, practice.  I tried getting a longer discussion using some of the questions it had previously generated, but each time, ChatGPT asked a single question, I responded, and it simply agreed with me.  While this was great for boosting my confidence, it was not great at preparing me for hard questions.  So I went back and reviewed the transcript it created of a mock oral argument.  This was great!  It provided not only probing questions but also insightful answers:

Court: Counsel for the appellant, can you explain why you believe the city's guideline prohibiting ads with religious content violates the First Amendment?

Appellant: Yes, your honor. The city's guideline banning religious content in advertisements is not content-neutral because it discriminates against religious speech. Under the Supreme Court's holdings in Rosenberger, Good News, and Lamb's Chapel, any policy that discriminates against religious viewpoints is unconstitutional under the Free Speech Clause of the First Amendment.

Court: Counsel, the city argues that the advertising guideline is neutral and generally applicable, and does not target religious speech or practices. Can you respond to that argument?

Appellant: Your honor, the city's advertising guideline is not neutral and generally applicable. The guideline specifically prohibits religious content in advertisements, while allowing ads with secular content. This is precisely the kind of content-based discrimination that the Supreme Court has held violates the First Amendment.

Court: Counsel, what evidence do you have to show that the city's guideline is not neutral and generally applicable?

Appellant: Your honor, the city's guideline itself is evidence that it is not neutral and generally applicable. The guideline singles out religious content for exclusion, while allowing ads with other types of content. Additionally, the city's decision to reject our client's advertisement for a religious service shows that the guideline is not applied neutrally. If the guideline were truly neutral and generally applicable, our client's advertisement would not have been rejected simply because it contained religious content.

Court: Counsel, the city argues that the guideline is necessary to avoid entanglement between government and religion. How do you respond to that argument?

Appellant: Your honor, the city's argument that the guideline is necessary to avoid entanglement between government and religion is not persuasive. The Supreme Court has repeatedly held that the government may not discriminate against religious speech or practices simply to avoid entanglement with religion. In fact, such discrimination itself constitutes impermissible government entanglement with religion. Therefore, the city's guideline is unconstitutional under the Free Speech Clause of the First Amendment.

I envision a student or advocate using this as a self-evaluation.  The student or advocate could hide the potential answers, provide their own responses, and then check their answers against the samples.  My overall takeaway:  as with most things related to ChatGPT, it provides a great starting point but still needs human eyes to fact-check and finesse.  But I think ChatGPT has great potential to assist advocates in preparing for oral argument.

March 13, 2023 | Permalink | Comments (0)

Sunday, March 5, 2023

Licensing Paid Blogs?

When your appellate practice focuses heavily on constitutional issues, as mine does, it is hard not to look at news stories and imagine the upcoming litigation. I had that reaction when I saw what is only a bill in Florida, but absurdly seeks to license blogs that generate income and mention government officials.

S.B. 1316, introduced by State Sen. Jason Brodeur, seeks to treat bloggers the same way as lobbyists, imposing registration and reporting requirements, although it exempts blogs that appear on a newspaper’s or similar publication’s website. Registration and reporting is required “[i]f a blogger posts to a blog about an elected state officer and receives, or will receive, compensation for that post.” The report must disclose the source and amount of compensation, rounded to the nearest $10.

Presumably, the legislation is being justified on the idea that disclosure can be required “so that the people will be able to evaluate the arguments to which they are being subjected.”[1] Yet, it immediately recalls the early prior restraints that followed registrations of printing presses in the 1600s and licensing of newspapers.

The legislation raises a host of constitutional issues. First, it says nothing about its potential extraterritorial import. Does the sponsor anticipate that a blogger in another state would have to comply with its registration and reporting requirement even though separate and apart from the First Amendment issues such a requirement would violate the Dormant Commerce Clause and due process for its attempt to reach beyond the State of Florida? And, how could it be enforced against an out-of-state blogger? And, if it does not apply, what justification exists for treating an out-of-state blogger differently from one who resides in-state, even though both blogs would be equally available through the Internet.

Still, by exempting newspapers and other publications, the legislation fails to treat all paid publications evenhandedly. The Tenth Circuit found the distinction likely fatal when faced with the same issue at the preliminary-injunction stage. There, Colorado attempted to claim that “a valid distinction exists between corporations that are part of the media industry and other corporations that are not involved in the regular business of imparting news to the public ” in support of a disclosure law that treated mention of a political candidate to constitute electioneering.[2] In fact, the Supreme Court in its controversial Citizens United decision state that “[t]here is no precedent supporting laws that attempt to distinguish between corporations which are deemed to be exempt as media corporations and those which are not. We have consistently rejected the proposition that the institutional press has any constitutional privilege beyond that of other speakers.”[3]

Another distinction in the legislation likely fails to pass constitutional muster: the distinction between paid bloggers and gratis ones. More than three decades ago, the Supreme Court shut down differential treatment of those engaged in expression on public matters based on compensation.[4]

It is difficult to think of a justification for registration and reporting at the mere paid blog mention of a state official. Doing so only facilitates further regulation, scrutiny, or retaliation. If the disclosure has a public purpose, why is that purpose not equally compelling on issues of public concern or non-office holding political candidates? Instead, by tying it to officeholders, the legislation suggests an improper purpose. After all, the First Amendment represents a  “profound national commitment to the principle that debate on public issues should be uninhibited, robust, and wide-open, and that it may well include vehement, caustic, and sometimes unpleasantly sharp attacks on government and public officials.”[5] Thin-skinned politicians need not apply.

S.B. 1316 may never become law. Even if enacted, it seems unlikely to ever take effect.

 

[1] First Nat. Bank of Bos. v. Bellotti, 435 U.S. 765, 792 n.32 (1978).

[2] Citizens United v. Gessler, 773 F.3d 200, 212 (10th Cir. 2014).

[3] Citizens United v. Fed. Election Comm’n, 558 U.S. 310, 352 (2010).

[4] See Meyer v. Grant, 486 U.S. 414, 424 (1988).

[5] New York Times Co. v. Sullivan, 376 U.S. 254, 270 (1964).

March 5, 2023 in Appellate Advocacy, Appellate Practice, Current Affairs | Permalink | Comments (1)

Thursday, March 2, 2023

The Rhetoric of ChatGPT:  What ChatGPT Had to Say About Its Connection to Rhetoric and What We Can Learn from That Response

Thursday’s Rhaw Bar: A Little Bite of All Things Rhetoric and Law—exploring ideas, theories, strategies, techniques, and critiques at the intersection of rhetoric and legal communication.

The Rhetoric of ChatGPT:  What ChatGPT Had to Say About Its Connection to Rhetoric and What We Can Learn from That Response

I’ve been thinking about what ChatGPT might mean for the practice of appellate lawyers and their ability to be persuasive.  So, I typed this as a prompt for ChatGPT:

 I am writing a blog post for an audience of appellate lawyers. What should I tell them about the relationship between rhetoric and ChatGPT?

Here’s what ChatGPT replied:

Rhetoric is the art of using language effectively to persuade or influence an audience. In many ways, ChatGPT can be seen as an extension of this art, as it uses natural language processing to generate persuasive and compelling responses to a wide range of prompts.

One of the key advantages of using ChatGPT for rhetorical purposes is its ability to quickly generate high-quality content in a wide range of styles and formats. This can be particularly useful for appellate lawyers, who need to produce persuasive legal arguments and compelling briefs that are tailored to the specific needs of their clients.

At the same time, it's important to remember that ChatGPT is a machine learning model, and as such, it has limitations. While it can generate persuasive responses based on patterns it has learned from large volumes of text data, it cannot understand the nuances of human emotion, context, or intent in the same way that a human being can.

This means that appellate lawyers who use ChatGPT for rhetorical purposes must be careful to ensure that the responses generated by the model are appropriate and effective for their intended audience. They should also be aware that the use of ChatGPT in legal writing is still a relatively new and evolving area, and that best practices are still being developed.

Overall, ChatGPT can be a valuable tool for appellate lawyers looking to enhance their rhetorical skills and produce high-quality legal content. By using the model in conjunction with their own expertise and insights, lawyers can create persuasive and compelling arguments that effectively convey their clients' positions.

Analyzing ChatGPT’s Response

Not a bad response, generally speaking. But what has ChatGPT revealed about itself?  Here’s a brief analysis of some things we can learn about ChatGPT from this response.

            ChatGPT Might Assume Too Much About the Reader

ChatGPT starts with a correct definition of rhetoric and then asserts that ChatGPT is an extension of rhetoric because it uses natural language processing (NLP). But ChatGPT assumes the reader knows what NLP is.  (And later it assumes that the reader knows what a “language processing model” is.)   If you don’t know (I didn’t) what NLP is, here’s a quick definition sourced from IBM:

NLP combines computational linguistics—rule-based modeling of human language—with statistical, machine learning, and deep learning models. Together, these technologies enable computers to process human language in the form of text or voice data and to ‘understand’ its full meaning, complete with the speaker or writer’s intent and sentiment.

So, one thing we learn about ChatGPT from this passage is that it can wrongly assume a reader’s knowledge, something lawyers know better than to do. While we might think that better engineering of ChatGPT’s prompt would solve the problem, recall that I told ChatGPT the audience for whom I was writing. That specific detail in the prompt did not seem to make a difference in ChatGPT understanding that many members of the intended audience would have limited knowledge of the computer science terms associated with ChatGPT. 

            ChatGPT Thinks of Itself as “Art”

I’m intrigued that ChatGPT chose the term “art” when describing itself as an “extension” of rhetoric.  This characterization seems counterintuitive because ChatGPT is the product of computer, data, and language science.  Yet, ChatGPT suggests that because NLP is a human-like effort to understand the meaning of language (as the definition above reflects), ChatGPT sees itself as an “artistic” endeavor, at least regarding persuasion.  And, at least in some cases, ChatGPT has proven that to be true--there’s something that feels like artistry in ChatGPT’s responses to prompts.  (See, e.g., this poem by ChatGPT and the debate around whether ChatGPT’s poetry is “art.”)

If ChatGPT sees itself as art rather than science, then we should take it at its word and think of it as we do art and artists.  That is, as do artists, ChatGPT brings a particular perspective to its responses.  As such, ChatGPT’s response is a form of art—and only one of many responses available.  Just like painters and sculptors can interpret their objects of study differently, ChatGPT’s interpretation of data in a particular response is one of many.  Thinking of this another way, we might view ChatGPT’s responses to prompts as opinions, subject to issues of perspective, interpretation, accuracy, bias, and incompleteness.

            ChatGPT Speaks Like It Wants to Sell You Something, but Should You Buy It?

Although I asked ChatGPT to describe a relationship between two things, ChatGPT’s response feels more like a sales pitch. It makes grand, authoritative-sounding claims about ChatGPT’s value to the user.  It is confident that it can help lawyers persuade and compel by providing “high-quality content in a wide range of styles and formats.”  ChatGPT reminds us that it has “key advantages,” that it can enhance the lawyer’s persuasive skill, and that it can generate high-quality content that can be tailored to client’s needs.

Why might ChatGPT sound so confident?  Maybe ChatGPT’s confidence comes from the way it generates responses.  ChatGPT generates responses by examining a vast amount of data, looking for the patterns and relationships between words in the sample, and then predicting what response is appropriate for the context.  Perhaps because I told it I was writing a blog post, the texts that ChatGPT accessed for context were blogs, and because many blogs are written in a tone designed to sell something, this caused ChatGPT to adopt the same tone by predicting that I was expecting that tone in the response.

Regardless of the reason, this extra-confident tone of the response should give us a reason to scrutinize ChatGPT’s claims more carefully.  If we read closely, we see that the response doesn’t really explains what “high-quality content” means.  On one hand, commentators point out that ChatGPT cannot tell the difference between true and false information and thus can deliver inaccurate responses.  This aspect of ChatGPT, then, is not “high-quality.”  Moreover, ChatGPT’s ability to sound very confident in its responses can lure readers into believing the responses’ truth.  For lawyers, this inaccurate information expressed in a confident tone is a malpractice minefield.  For example, one would not want to rely at face value on what ChatGPT says about some point of law.  (It’s probably useful to remind those in your office who could use ChatGPT of this important point.)

On the other hand, ChatGPT arguably can offer something of high(er) quality in that it can produce a “wide variety of styles and formats.”  You can prompt ChatGPT to write in a particular style—even your own!  You can request it write content in the style and organization of a brief or a motion, and it will comply.  You can ask it to assist in correcting your grammar.  It’s pretty good at offering examples of different genres, styles, and tones of writing.  This is because it is good at providing an approximation of whatever you’ve asked it to create based upon the patterns it recognizes in the dataset.

But here’s the catch, I think, with using ChatGPT to generate “style and format” content: the user must already understand the style and structure he or she seeks in order to evaluate the quality of ChatGPT’s response.  In other words, if you don’t know already what a case caption for, say, the United States Court of Appeals for the Ninth Circuit looks like, how can you be sure ChatGPT will give you the right format for that caption?  Likewise, if you aren’t sure what a good introduction to an appellate brief looks like, how can you know if ChatGPT has given you a good one in its response?   ChatGPT would be good at giving you examples, but it can’t really tell you which one is “best” in your circumstances.

            ChatGPT Knows Its Rhetorical Limits

Even though ChatGPT is confident in its capabilities, it admits that it has limits.  Specifically, ChatGPT responds that it cannot understand emotion, context, or intent like a human does when crafting responses to persuade. This is a pretty significant admission.  To be limited in these ways is relevant to ChatGPT’s persuasive abilities; understanding emotion, content, and intent are elements of human communication that are central to rhetorical effectiveness.  So, even though ChatGPT sees itself as an “extension” of rhetoric, it is a fairly limited extension.

 ChatGPT reminds us that one of its limitations is that it generates persuasion from finding patterns in large amounts of existing data.  So, that raises the problem of “garbage in,” “garbage out.”  In other words, the quality of ChatGPT’s responses is only as good as the data it can access.  That is, if the dataset has both helpful and unhelpful patterns that inform ChatGPT’s responses, how does one know if what ChatGPT generated is something worth relying on?  The only way to know is to already have the knowledge essential to evaluating the response.

            In the End, ChatGPT is Deferential about Its Writing

ChatGPT says it is the appellate lawyer’s job to ensure what ChatGPT writes is effective for the intended audience.  It talks about itself as a “model” that can help lawyers be persuasive and reminds lawyers that the model should be used in conjunction with lawyers’ expertise and insights.  In other words, ChatGPT does not take the position that it replaces humans in the writing process—particularly where audience analysis and professional expertise is involved.  Here, ChatGPT makes a significant rhetorical move—it reminds you that the technology is only as good as its user and, even after all of its confidence above, disclaims responsibility for the usefulness of its output. Fascinating.

Some Takeaways

ChatGPT notes that it is new enough that “best practices” for using ChatGPT in legal writing are still being developed. I take this as a challenge!  Based upon ChatGPT’s rhetoric (i.e., the way it uses language to talk about itself), I’ll propose some best practices for you:

  • Do not be misled by ChatGPT’s confidence. ChatGPT sounds confident and authoritative in its responses, but users should be skeptical about the legitimacy of that confidence.
  • Rely on your own expertise, not ChatGPT’s. Appellate lawyers (and staff working for them) need to have an existing knowledge base to evaluate ChatGPT’s responses.  In particular, evaluating the appropriateness of the response for an audience is essential.  As with all aspects of outsourcing judgment in legal practice, outsourcing judgment to ChatGPT is dangerous.  At the very least, for appellate lawyers to use ChatGPT effectively, they will need to become familiar with prompt engineering techniques that make ChatGPT more expert in the field and thus arguably improve ChatGPT’s responses.
  • Treat ChatGPT as opinionated, not authoritative. Although ChatGPT is the product of science, ChatGPT should be seen as an artistic process, generating content that is more like opinion than unassailable fact.  Treat ChatGPT as conversation partner, muse, or collaborator than can help you “play” with ideas and text.  (Check out Ian Bogost’s article insightfully concluding that “ChatGPT  . . . doesn’t understand or even compose text. It offers a way to probe text, to play with text, to mold and shape an infinity of prose across a huge variety of domains . . . into structures in which further questions can be asked and, on occasion, answered.)
  • Remember that ChatGPT relies on pattern recognition, a limited mode of persuasion. ChatGPT does not have all the rhetorical capabilities of humans but can recognize patterns in data that might have persuasive impact.  Even if that pattern recognition is persuasive, users must remember to look at persuasion from all aspects of the human experience, not just in the ways that ChatGPT looks at it.
  • Remember that ChatGPT does not guarantee competent writing, you do. At bottom, ChatGPT does not claim it is superior to you in writing ability but rather it remains deferential to your experience and expertise. It disclaims its ability to effectively write for your “local” audience.  No one—not even a computer—knows your clients, your arguments, and your audience better than you do.  Rely on your own judgment about competent writing.

What are your thoughts?

Kirsten Davis teaches at Stetson University College of Law and in the Tampa Bay region of Florida. She is the Co-Director of the Institute for the Advancement of Legal Communication. The Institute’s mission is to study legal communication issues and provide programming and training that improves legal communication skills. Among other things she’s up to right now, she’s currently working on a writing handbook written specifically for trial lawyers. The views she expresses here are solely her own and not intended to be legal advice. You can reach Dr. Davis at [email protected].

March 2, 2023 in Appellate Advocacy, Appellate Practice, Legal Profession, Legal Writing, Rhetoric | Permalink | Comments (1)