Made with FlowPaper - Flipbook Maker
< PreviousFALL 2023 | 11 Generative AI: The Good, the Bad, and the Ugly How I Use (and Don’t Use) AI To Save Time and Improve Efficiency By Pete Fowler Prompt: Write me a one-to-two paragraph magazine ar- ticle introduction about artificial intelligence being a mind extension tool, as defined by Clark and Chalmers’ extended mind theory. ChatGPT 3.5: In the age of rapid technological advancements, artificial intelligence (AI) has emerged as an unparalleled tool, reshaping our understanding of human cognition and pushing the boundaries of what our minds can achieve. Drawing in- spiration from the groundbreaking work of philosophers Andy Clark and David Chalmers, the concept of AI as a mind exten- sion tool has gained momentum, revolutionizing our percep- tion of intelligence. According to the extended mind theory, our cognitive abilities are not confined within the boundaries of our skulls, but rather extend beyond them to include external tools. This article explores the profound implications of AI as a mind extension, highlighting its transformative potential and its capacity to augment and amplify human intelligence to unprecedented heights. ChatGPT, the first Large Language Model (LLM) Arti- ficial Intelligence (AI) chatbot made publicly available, was released on Nov. 30, 2022. It surpassed 1 million users in just five days, and now has over 100 million. I am a highly technical person with a Bachelor of Science in construction management and minor in information systems, but I am not an early adopter of technology. I prefer to wait and see if a tool is useful before I use it. I started using ChatGPT in March 2023, and I am happy to report that it is a useful tool.12 | CONSTRUCTION CLAIMS TheCLM.org/Magazine Mind Extension Tools Prompt: Explain extended mind theory at the high school level. ChatGPT 4: Imagine your mind is like a superhero. Now, superheroes sometimes use gadgets to boost their powers, right? Batman has his utility belt, Iron Man has his suit. These gadgets become a part of who they are, helping them to solve problems and face challenges. The extended mind theory says our minds can work like a superhero with gadgets. It suggests that our minds aren’t limited to just our brains. Instead, they can spread out and use tools and objects in the world to help us think. Take your smartphone, for example. You use it to remember your friends’ phone numbers, remind you about appointments, or calculate sums. The extended mind theory suggests that, in these situations, your smartphone is acting as a part of your mind, helping you remember things or solve problems. So, according to this theory, our minds are not just in our heads. They can extend into the world around us, using tools, objects, and even other people to think and solve problems better. It’s like each of us is a superhero, using our gadgets to boost our powers. Prompt: Give me a list of common mind extension tools, as defined by Clark and Chalmers’ extended mind theory…. Can you give me more examples? Bing Chat: …some objects in the external environment can be part of a cognitive pro- cess and in that way function as extensions of the mind itself. Examples of such objects are written calculations, a diary, or a PC; in general, it concerns objects that store information. In their paper “The Extended Mind,” Clark and Chalmers present the idea of active externalism, in which objects within the environment function as a part of the mind. They argue that the separation between the mind, the body, and the envi- ronment is an unprincipled distinction.... Other examples of such objects include smartphones, tablets, and other digital devices that store information. In addition to these devices, other examples include eyeglasses that correct vision, hearing aids that amplify sound, and even prosthetic limbs that become part of the body. Prompt: What are the oldest mind exten- sion tools? ChatGPT 4: Mind extension tools have been used since prehistoric times. Here are a few examples: (1.) Stone Tools… (2.) Fire… (3.) Cave Paintings… (4.) Writing Systems… (5.) The Abacus…. These tools show that the idea behind the extended mind theory is not new; humans have been using objects in their environment to extend their cognitive capabilities for thou- sands of years. However, modern technol- ogy, from pen and paper to smartphones and AI, allows for cognitive extension on a scale never before possible. It is our company’s job to conduct forensic investigations, often for lawyers and insurance professionals. These inves- tigations include collecting, organizing, and summarizing lots of project data to transform it into information, and then applying a lifetime of subject matter expertise about building and buildings to decide what we think happened versus what should have happened, and how to solve the problem. It is intellectually dif- ficult work with a mindboggling volume of data to consider and synthesize. To do my job effectively and ef- ficiently, I use many mind extension tools, including notes, calculations, and drawings on paper; spreadsheets to organize and analyze data; electronic calendars to coordinate meetings; and my smartphone to take photographs. AI is my newest tool, and it may soon be the most powerful. AI as a Mind Extension Tool I use AI chatbots for simple things, with prompts such as, “Reorganize these into a numbered list in alphabetical order,” “Make this paragraph sound more profes- sional,” “Make this more clear,” and “Make this shorter.” I used AI to help a business- owner friend improve a job description. It is not magic or perfect, but it is better and faster than interrupting a co-worker. I also asked for interview questions for a potential chief operating officer. The ques- tions were good, and, yes, I hired him. So far, I find AI is most useful for writing clearly about what I already know. I have been writing about build- ing and buildings since the 1990s. In 2016 our company published, “Proving the Obvious Using Google,” a process we developed because we must sometimes refute opinions of opposing experts that we think are silly. We search Google using the right prompt and save the first 10 sources, which virtually always tell us what we already knew, and use that as support for our expert opinion. The most time-consuming part is summarizing the information and writing what it means clearly enough for everyone to under- stand. AI can often do this in seconds. For example, I recently testified in a deposition related to a construction site accident. It was clear one of the key play- ers did not have a safety-focused culture. It is well known in construction that the right culture results in far fewer injuries, but how do I prove it? In the past, I would spend hours “proving the obvious using Google” by collecting, organizing, read- ing, summarizing, and drawing conclu- sions. For this matter, AI saved me hours of work, and our client a lot of money. In a fraction of the time, I was able to com- pose a safety culture memo that clearly ar- Generative AI: The Good, the Bad, and the Ugly I started using ChatGPT in March 2023, and I am happy to report that it is a useful tool.FALL 2023 | 13 ticulated what I already knew. Of course, I backed it up with authoritative original sources, but I did not need to agonize over writing out my own summary. Asking Good Questions To Get Good Answers Prompt: I am trying to explain the im- portance of, and how to, ask an AI chat- bot questions to get the best responses. Can you help? Bing Chat: … 1. Be specific: Try to be as specific as pos- sible when asking your question. This will help the chatbot understand what you’re looking for and provide you with more accurate results. 2. Use natural language: Chatbots are de- signed to understand natural language, so try to ask your question in a way that feels natural to you. 3. Avoid jargon: If you’re asking a ques- tion about a specific topic, try to avoid using jargon or technical terms that the chatbot might not understand. 4. Be patient: Chatbots can take a few sec- onds to respond, so be patient and wait for the chatbot to provide you with an answer. 5. Ask follow-up questions: If you’re not satisfied with the chatbot’s response, don’t be afraid to ask follow-up ques- tions to get more information. Since, so far, I am only relying on AI to help me speed the work I already have expertise in, I just keep asking questions until it answers in a way that sounds like me. The marketing professionals in our office are using AI in amazing and creative ways, engaging in “conversation,” including feeding the chatbot information like real client testimonials and having conversations that sound like two market- ing savants brainstorming. It is fascinating and fruitful. Our technology department has described amazing domain-specific tools and capabilities for writing code that are far beyond anything I can use AI for as a building consultant. Like me, some of their tasks are being completed in 10-20% of the time required before AI. They tell me they exclusively use ChatGPT 4 ($20/ month), and that, while 3.5 (free) felt like a toy, 4.0 feels useful. In contrast, I actually prefer many of 3.5’s responses, including for use in this article. Dangers Ahead It may sound like I drank the Kool-Aid after singing AI’s praises in this article, but beware! Prompt: Explain the concept of AI chat- bots “hallucinating facts.” Bing Chat: AI hallucinations in chatbots refer to incorrect results that are vastly out of alignment with reality or do not make sense in the context of the pro- vided prompt. AI chatbots can respond grammatically or logically incorrectly or mistakenly identify an object due to noise or other structural problems. AI models can be convinced of completely untrue facts, responding to queries with made-up answers. For instance, an AI program like ChatGPT can fabricate a historical figure with a full biography and accomplish- ments that were never real. By now, most of us have heard about the New York lawyers who were sanc- tioned in June 2023 for using fake Chat- GPT cases in a legal brief. ChatGPT was “hallucinating facts,” but they sounded so convincing that the lawyers who signed the brief did not think to look up the cited cases. In our work, we must “inspect what we expect.” If we do not know it to be true, then we must verify it. I asked ChatGPT for the applicable building codes for residential site drain- age. Its initial responses were helpful. But, after a bit of back-and-forth to get more specific, a saying my mother taught me came to mind: “Often wrong but never in doubt.” AI is dangerous because it always sounds smart unless you know it is wrong. I have asked AI to summarize books I have read. Sometimes it does great, and sometimes it is dumb—grammatically correct, but dumb. Be very careful asking questions that could have wrong answers that you do not know the answers to. I only rely on it for work where I have domain-specific expertise. Prompt: I am writing an article, pasted in below. Can you draft a conclusion? [Response was too long.] Can you make that shorter? ChatGPT 3.5: In today’s fast-paced world, artificial intelligence (AI) serves as a game- changing mind extension tool, reshaping our perception of intelligence. Inspired by the extended mind theory, AI can amplify human cognition, aiding professionals in various fields like forensic investigations and claims. By asking precise, natural language questions, users can harness AI’s potential effectively. However, prudent evaluation is essential to avoid reliance on AI for critical decisions. Embracing AI is no longer op- tional; it’s a necessity for staying competitive in this technological era. Striking the right balance between human expertise and AI capabilities will lead us to a future of unprec- edented possibilities and innovation. In the late 1700s, steam engines brought a significant change to people’s lives. They improved manufacturing and transportation, allowing cities to be built away from rivers that were previously essential for transport and power. This led to a boost in the economy and better living conditions for many. Today, AI serves as a similar catalyst for the mind, enabling users to become smarter and more productive at an incredible pace. AI holds the potential to revolutionize learning and productivity, ushering in a remarkable era of progress. Of course, modernity has always had its detractors: those who pine for the good old days. But complaining won’t stop AI’s transformative power. K Pete Fowler is chief quality officer of Pete Fowler Construction Consultants. pf@petefowler.com Generative AI: The Good, the Bad, and the Ugly14 | CONSTRUCTION CLAIMS TheCLM.org/Magazine State-By-State NEVADA WILL INSURERS HEAD FOR THE DOOR? New Legislation Alters Liability Insurance Landscape By Elaine Fresch and Eric Freeman The Nevada legislature passed Assembly Bill 398, which prohibits insurers from issuing liability insurance policies with provisions that reduce the limit of liability coverage by the cost of defense and other expenses related to the claim. These policies are often referred to as burning limits or eroding/ depleting policies. Insurers will be prohibited from issuing or renewing such liability policies as a result of this recent legislation. The bill will be added to Nevada Revised Statutes (NRS) 679A, which is part of the Nevada Insurance Code. Nevada Gov. Joe Lombardo signed the bill on June 3, 2023, and it becomes ef- fective on Oct. 1. AB 398 amends NRS 679A by adding the following section: Section 1. Chapter 679A of NRS is hereby amended by adding thereto a new section to read as follows: Notwithstanding any other provision of law, an insurer, including, without limitation, an insurer listed in NRS 679A.160, shall not issue or renew a policy of liability insurance that contains a provision that: 1. Reduces the limit of liability stated in the policy by the costs of defense, legal costs and fees and other expenses for claims; or 2. Otherwise limits the availability of cover- age for the costs of defense, legal costs and fees and other expenses for claims. Elaine Fresch Eric Freeman FALL 2023 | 15 State-By-State NEVADA Section 2. The provisions of this act do not apply to any contract for li- ability insurance existing on October 1, 2023, but apply to any renewal of such a contract. The bill is broad, with very few excep- tions regarding the scope of the new statute. There are many questions about how the statute will be interpreted and implemented. The Nevada Division of Insurance is aware of concerns from both insurers and insureds, so it has issued some initial guidance. The Division of Insurance stated that, while defense costs must not erode limits of liability coverage, defense costs do not have to be unlim- ited and that an insurance policy can include a separate defense cost limit. This could have an interesting impact on how insureds and insurers litigate and defend cases, especially as to their defense posi- tions and incentives. The Division of Insurance is preparing permanent regulations to add more clarity to that new provision, however, at this time, there appear to be more questions than answers, including whether the bill will cause insurers to leave Nevada. With the true scope of the bill unclear, insurers will have difficulties determining coverage requirements and calculating risk. As for Nevada residents and busi- nesses, it may be difficult to find, or afford, liability insurance. Costs will likely increase, perhaps significantly, given the unclear interpretation of the bill. Nevada is a business-friendly state with many companies choosing to incorporate there. It will be interesting to see if companies reconsider that strategy should liability insurance costs rise. The Division of Insurance, through the insurance commissioner, adopted an emergency regulation and published guidance to clarify that the law applies to authorized insurers. This implies non- admitted insurers are exempted from the new law. The guidance also states the bill does not apply to risk-retention groups, for which “liability” is defined to include defense costs pursuant to 15 U.S.C. § 3901, and captive insurance that does not cover third-party liability. Construction Implications In the world of construction, most design professionals typically obtain errors and omissions policies that have burning limits. Historically, this has led to certain settlement strategies for plaintiffs and developers/general contractors as to the amount they can potentially achieve if the design professionals have had to incur significant fees/costs to defend themselves, thereby leaving little left on the policy. These parties can potentially keep construction professionals in the suit until a global settlement is reached or the action is tried, as limits will remain intact. For the design professionals, if the limits are not eroding, they will not have to worry about personal exposure due to potential exhaustion from eroding limits. Historically, counsel for design profes- sionals would limit their participation in discovery and even in mediations to prevent eroding the limits to assist in pre- venting personal exposure of their client if settlement could not be achieved. Now, these parties will not hesitate to aggres- sively defend themselves during the action. The statute seemingly does not impact is- suing policies with SIRs or deductibles for liability limits and/or defense costs. A Look at Other States Two other states have adopted legislation that prohibits insurers from reducing liability coverage by the cost of defense, but these statutes include many exclu- sions and exceptions the Nevada bill does not. Louisiana [La. R.S. 22.1272(B)(3)] enacted such legislation in 2021, however that statute allows the insurance commis- sioner to exclude several liability insur- ance coverages from the requirements. New Mexico (N.M. Code R 13.11.2.8) prohibits defense costs within limits policies, but that statute is also subject to a long list of exceptions that the Nevada statute does not include. Additionally, Oklahoma has had this restriction on defense inside limits for many years. We can only assume there will continue to be more questions once this statute becomes effective and the insurers try to issue policies that comply. K Elaine Fresch, senior partner, and Eric Freeman, partner, are with Hawkins Parnell & Young, LLP. efresch@hpylaw. com, efreeman@hpylaw.com With the true scope of the bill unclear, insurers will have difficulties determining coverage requirements and calculating risk.16 | CONSTRUCTION CLAIMS TheCLM.org/Magazine State-By-State ARIZONA THE IMMOVABLE OBJECT State’s Implied Warranty of Workmanship and Habitability Cannot Be Disclaimed or Waived Under Any Circumstance By Jason Feld and Stephanie Wilson Arizona residential construction and single-family home production is growing at a rapid pace. Just as fast as the homes are sold, homeowners are seeking warranty repairs from their homebuilders. Despite having strong purchase documents with express warranty language, the Arizona Supreme Court, in Zambrano v. M & RC, II LLC, 254 Ariz. 53 (2022), adopted a bright-line rule that, regardless of the contract, the implied warranty of workman- ship and habitability (implied warranty) cannot be disclaimed or waived under any circumstance. The Arizona Supreme Court opinion provides clear guidance of the law in this area on the scope of the implied warranty in contracts between homebuy- ers and builders/vendors, specifically on the issue of whether an express warranty can negate and effectively waive the common law implied warranty, which is a definitive violation of public policy. The Zambrano decision involved a licensed real estate broker who bought a new single-family home for herself in a newly constructed, master- planned community in Surprise, Arizona. Zam- brano, the buyer, entered into a valid sales contract with Scott Homes, the homebuilder. The contract contained a standalone, 45-page pre-printed form express warranty. The express warranty was to be the “only warranty applicable to the home.” The contract further clarified that the buyer was expressly disclaiming (and, thus, waiv- ing) the implied warranty. The sales documents and express warranty were signed and authorized by Zambrano. A short time later, the home developer alleged “design and construction defects” that were “either time barred or outside the coverage” of the express warranty. Zambrano filed suit for the alleged defects based on the implied warranty. Scott Homes filed sum- mary judgment based on Zambrano’s waiver and disclaimer of the implied warranty in the purchase agreement. The trial court granted summary judgment, and the matter was appealed up to the Arizona Supreme Court. State Supreme Court Weighs In The Arizona Supreme Court decided the issue of whether an express warranty can essentially trump the common law implied warranty. The court ad- opted a bright-line rule holding that any disclaimer or waiver of the implied warranty is unenforceable as a matter of law and as a matter of public policy. The court further held that the implied war- ranty could not be disclaimed or waived unless and Jason Feld Stephanie Wilson FALL 2023 | 17 State-By-State ARIZONA until the Arizona legislature expressly declared it to be a right that buyers could waive or disclaim. The court concluded that “[e]nforcing the disclaimer and waiver here would grievously injure homebuyers and the public welfare as doing so would likely spell the end of the implied warranty….” The court acknowledged that it had “considered leaving open the possibility that a sophisticated homebuyer in some settings could negotiate to waive the implied warranty,” but rejected that idea. The court observed that “it would be next to impos- sible for courts to decide whether a home- buyer was sophisticated enough,” and the court nevertheless concluded that “[e]ven sophisticated homebuyers need the protec- tion offered by the implied warranty.” Interestingly, the dissent relied upon long-established public policy behind the freedom to contract, and considered a “sophisticated” homebuyer who “seeks to purchase a customized home that presents specific risks for which the homebuyer prefers to negotiate unique coverage in an express warranty.” The dissent went further to consider “a homebuyer who prefers a contractual term that is less protective than the implied warranty as to one section or component of the home, in exchange for greater and broader protection in another area of the home,” and a homebuyer who “negotiate[s] a reduced purchase price in exchange for a warranty more limited than the implied warranty.” However, the majority of the court emphatically deferred any change in the law on circumventing the common law and public policy implications of implied warranty to the legislature. The major takeaway is that, without legislative intervention, the implied warranty cannot be waived, disclaimed, or modified under any circumstances in Arizona, irrespective of a valid contract and express warranty. K Jason Feld, Esq., partner, and Stephanie Wilson, Esq., of counsel, are with Kahana & Feld. jfeld@kahanafeld.com, swilson@ kahanafeld.com The court adopted a bright-line rule holding that any disclaimer or waiver of the implied warranty is unenforceable. Since 1924 Haag Global Construction Defect Experts Forensic engineering, forensic architecture, and construc�on consul�ng services Construc�on defects and builder’s risk, & related subroga�on experience Expert witness and li�ga�on support in construc�on defect lawsuits Establish cause(s) and du�es & responsibili�es of involved par�es To find the right expert for your assignment, 800.527.0168 or HaagGlobal.com 18 | CONSTRUCTION CLAIMS TheCLM.org/Magazine State-By-State SOUTH CAROLINA THE SQUEAKY WHEEL ELIMINATES THE DAMAGES Part II of Strategies to Determine and Eliminate Potential Damages in Construction Cases By Laura Paris Paton In South Carolina construction litigation, certain strategies can be used to determine and eliminate potential damages for subcontractor clients. In part one of our look into these strategies, which ran in the summer 2023 edition of Construction Claims, we examined the Stoneledge Doctrine and how it may be used to help subcontractor clients escape liability to the general contractor, limiting claims to those brought by the plaintiff. In this article, we look at where to go from there. Once claims have been narrowed to only those that are an actual risk at trial, determining the post-trial set-off will assist in the prediction of how much money may be collected against a client at trial. In South Carolina, a defendant may make a motion for a post-trial set-off, which can curtail or even eliminate client exposure. Under SC Code Ann Sec. 15-38-15, a defendant may move the court to deduct the amount of money the plaintiff collected in pre-trial settlement funds from the jury award against the defendant at trial. Consider this: A plaintiff alleges the siding subcontractor caused $1 million in actual dam- ages, but, pre-trial, the plaintiff managed to collect $900,000 from other parties with overlapping scopes of work. If the jury agrees with the plaintiff and awards the full $1 million against the defen- dant, that defendant may only have to pay the $100,000 difference between the award and the amount the plaintiff did not manage to recover in pre-trial settlements. However, this can also work against defense counsel and claims professionals trying to estimate client exposure. Imagine in the above scenario that the attorney and claims professional do not know how much plaintiff has collected pre-trial, but, for Laura Paris PatonFALL 2023 | 19 State-By-State SOUTH CAROLINA the purpose of analysis, they assume the plaintiff has about $900,000 in settle- ments with other defendants pre-trial. If the plaintiff is unsuccessful in secur- ing significant settlements, counsel and claims personnels’ damages analysis may substantially underestimate exposure at trial. Under those circumstances, the client could be looking at exposure well above the $100,000 that counsel (and the carrier) were banking on. For the pur- poses of ascertaining exposure, knowing the actual settlement amounts is essential. However, this is easier said than done. It is routine for plaintiff’s attorneys to refuse to produce settlement information. Commonly, plaintiff’s attorneys argue that settlement information is “confiden- tial.” But confidentiality is not a privilege and, regardless of what the plaintiff may argue, a defendant has a right to this information in discovery. Plaintiff’s attorneys also like to argue that settlement information is not rele- vant and, therefore, excluded as evidence until such time as there is a verdict. This is also a logical fallacy. However, unless counsel moves to compel this informa- tion, the claims personnel and attorney will never be able to determine the real damages exposure. There are times when the costs of com- pelling this information may seem to out- weigh the benefit of the production. This view can be shortsighted. It is important to remember that the knowledge gained may impact the damages analysis by hundreds of thousands of dollars. Also, there are winning arguments that, if put before the court, can secure this information. Under Rule 26, SCRCP, “It is not ground for objection that the information sought will be inadmissible at the trial if the information sought appears reason- ably calculated to lead to the discovery of admissible evidence.” This counters the idea that the information is not ripe until there is a verdict. Similarly, there is helpful caselaw stat- ing that “[w]hen the settlement is for the same injury, the non-settling defendant’s right to a set-off arises by operation of law.” [See Smith v. Widener, 397 S.C. 468, 472, 724 S.E.2d 188, 190 (Ct. App. 2012), citing Ellis v. Oliver, 335 S.C. at 112, 515 S.E.2d at 271-72]. Thus, the argument that the infor- mation is not “ripe” until there is a verdict is incorrect; the right arises “as a matter of law” at the time of the settlement. Finally, there are situations where there is an assignment of a claim that may impact the ability of the plaintiff to recover additional damages against a defendant. For example, a general contractor may have claims against his subcontractors for indemnity and settle with the plaintiff for $1 million plus an assignment of his contractual indemni- fication claim against the subcontractor to the plaintiff. Under those circum- stances, the plaintiff will likely argue to the subcontractors that he has a right to recoup that $1 million already paid by the general contractor as part of the con- tractual indemnity claim. The defense can argue that it is fundamentally unfair for a plaintiff to hide the amount it is pursuing on the assigned claim. Knowing that your client may be able to escape liability for damages altogether as the result of a massive set-off or, conversely, that they may be held dispro- portionately liable because a plaintiff has released claims for pennies on the dollar, is everything when trying to predict cli- ent (and carrier) exposure at trial. Hav- ing pinpointed the client’s exposure at trial relative to the actual damages, one can turn her attention toward whittling away the claims to minimize actual and punitive damages. Many insurance companies require pre-approval for motion practice, but a little money spent on motion prac- tice may exponentially improve the ability to accurately predict (and thus minimize) damages. To paraphrase one irritated plaintiff’s attorney follow- ing the success of a dispositive motion, “What do I have to do to get you out of this case?” Plaintiff’s attorneys usually work on contingency fees, and dealing with squeaky-wheel attorneys chipping away at their cases and prolonging the process is the last thing they want to deal with. This is particularly the case when one brave attorney winning a motion can lead to other defense counsel trying to copy the success of a trailblazer. The defense attorney who works to eliminate claims and minimize exposure is the first person the plaintiff’s counsel wants out of the case—to the benefit of both the client and the insurer. K Laura Paris Paton is a partner with Gordon & Rees LLP. lpaton@grsm.com Unless counsel moves to compel this information, the claims personnel and attorney will never be able to determine the real damages exposure.Next >