[EDRM Editor’s Note: EDRM is proud to publish Ralph Losey’s advocacy and analysis. The opinions and positions are Ralph Losey’s copyrighted work. All images in this article were created by Ralph Losey using his ChatGPT 4o Visual Muse. This article is published here with permission.]
Two AI heavyweights step into the ring: ChatGPT 4o, the reigning champion of fluency and speed, and the new challenger, ChatGPT 4.5, boasting an upgraded intellect and sharper wit. But which one is truly the best? To find out, I designed a four-round battle, testing them in metacognition, humor, deep legal expertise, and practical AI guidance. Each round pushed them to their limits—some victories were clear, others were razor-close. In round two on humor the judges disagreed and ask readers to weigh in. In the end, one emerged as the superior model. Read on to see who claimed the title in this AI showdown.
Introduction
A new version of OpenAI’s ChatGPT has just been released, GPT-4.5, nicknamed Orion. It is available to all Plus, Pro, and Team plan users worldwide on web, mobile, and desktop. I have a Team plan and first got to try it out on March 5, 2025. If you are a lawyer or law firm you should consider having a Team account too, or if a big firm, upgrade to the Pro, Plus or even Enterprise accounts. The new ChatGPT 4.5 model does not include reasoning, as it was “designed to be a more general-purpose, innately smarter model.” GPT-4.5 in ChatGPT (OpenAI). Here is OpenAI’s introduction, which suggests this will now be the best model for all professional use, including law.
GPT-4.5 is a step forward in scaling up pre-training and post-training. By scaling unsupervised learning, GPT-4.5 improves its ability to recognize patterns, draw connections, and generate creative insights without reasoning. Early testing shows that interacting with GPT-4.5 feels more natural. Its broader knowledge base, improved ability to follow user intent, and greater “EQ” make it useful for tasks like improving writing, programming, and solving practical problems. We also expect it to hallucinate less. (emphasis added)
We’re sharing GPT-4.5 as a research preview to better understand its strengths and limitations. We’re still exploring what it’s capable of and are eager to see how people use it in ways we might not have expected.
GPT-4.5 has a bigger knowledge base, enhanced creativity, and more natural conversational style. It does not perform detailed step-by-step logic like the o-series models. GPT-4.5 is adept at creative and nuanced tasks like writing and solving practical problems.
GPT-4.5 in ChatGPT. Also see: Introducing GPT-4.5 (OpenAI, 2/27/25) (“GPT‑4.5 is an example of scaling unsupervised learning by scaling up compute and data, along with architecture and optimization innovations.”) OpenAI has high hopes for ChatGPT 4.5 because the core of this new model change is a scaling increase in data training and compute. It will not reveal the amount of scaling except to say it was very expensive.
OpenAI’s Claims About ChatGPT 4.5
Despite the scaling increase the claim that 4.5 is better at programming in the marketing is largely bogus. That depends on reasoning, not increased training scale. In fact ChatGPT 4.5 is not nearly as good as the o3mini models in programming. The model evaluation scores of the product release show that. See Introducing GPT-4.5.
Still, the other claims of significant improvements may be correct. The invitation to test given to the high paying first users, to kick the tires, has been made. Is 4.5 really as good as claimed? Is it really a big improvement over 4o? Everyone is interested to see, including OpenAI, which only did limited testing. User testing and feedback is the best way for them to determine what kind of unexpected abilities may emerge from the scaling increase. That is where people like me come in with the time and motivation to test out the latest in AI. Perhaps you will join in and try out 4.5 yourself.
So far everyone seems to agree the improvements in known abilities are noticeable but not nearly as significant as the move from 3.5 to 4.0 seen in the last scaling increase. That change was dramatic and obvious. Perhaps scaling is beginning to reach it limits. It is too early to say. OpenAI is keeping a tight lid on the scaling used except to say much more data and compute were used. Further, and even more interesting to many, is to discover what new abilities 4.5 may have that 4o does not. New emergent capabilities take time to detect and tens of thousands of testers trying new things. That is what makes AI testing so interesting. No one knows for sure how the new models will react.
Here are the five OpenAI claims about 4.5 that most experts agree should be taken take seriously. My very short responses from initial testing are in bold.
- Deeper world knowledge base for more comprehensive insights. Agreed.
- Greater creativity and writing ability. Agreed.
- Improved ability to follow user intent. Yes and No. Overall some slight improvement.
- Enhanced emotional intelligence (“EQ”) for more natural conversations. Agreed.
- Significantly reduced hallucination rates, improving accuracy. Agreed.
To be clear, emotional intelligence does not mean ChatGPT4.5, or any other AI, has emotions. None do. It just means it is able to write and speak as if it does. It can pretend better. Also, it has greater abilities to detect emotions in human chats and respond appropriately. Due to this speech ability, it now seems more humanlike in its interactions. Just remember, it is still just a tool, not a creature.
Many of the young programmers refer to this improvement as model 4.5 as having better “vibes.” In every 4.5 review I have read, this seems to be an important positive point, even the highly critical reviews. Reece Rogers, With GPT-4.5, OpenAI Trips Over Its Own AGI Ambitions (Wired, 3/6/25) (“I could see myself picking GPT-4.5 just to avoid feeling like I’m asking some info-dumping sycophant for help.“). Most users enjoy using it more than any other model, including models outside of OpenAI’s lineup. Focusing on vibes is a smart money shot, which is much needed by OpenAI because of its well-known struggles with profitability. The good vibes of 4.5 will, I predict, allow them to maintain their market lead and keep the fundraising going strong. Also see, Beyond the Bid — Musk 97 Billion Offer Falls on Deaf Ears (Medium, 2/16/25).
The reduction of hallucinations claim is something all AI software companies have been working on for years now because fabrications can cause users significant problems. This is especially true for lawyers. See e.g. Experiment with a ChatGPT4 Panel of Experts and Insights into AI Hallucination – Part Two (5/21/24); The Latest AI Hallucination Case (LinkedIn, 3/1/25). OpenAI claims to have made significant improvements in this area but does not claim to have cured hallucinations altogether. They can still happen, just less frequently. Moreover, in my experience and research with AI hallucinations since ChatGPT’s release on November 30, 2022, there are many things users can do to reduce hallucinations, including more careful prompts. More on this later in this article in the fourth round where the topic is AI Hallucination. So far, this claim seems credible. Still, we have a long way to go, especially for novice users, and in the meantime trust but verify. Otherwise, law firms still run a serious risk of sanctions for fabricated citations and other AI hallucinations.
The greater creativity and writing ability claims appear correct from my tests so far. This means more than just vibes and EQ but can be hard to objectively confirm and measure. Many look at AI’s abilities at humor, poetry and fiction for hard tests. Here we used comedy as one of our four tests. The improvements I have seen so far are significant, but not a huge jump like the upgrade from ChatGPT3.5 to 4.0 in April 2023. I expect that even greater improvements in writing and creativity will come in the expected version 5.0.
The claim as to improved understanding of user intent may from my limited experience to date only be a modest gain. In one of the battles that will be reported here 4.5 did not perform as well as 4o on initial understanding of a two-part prompt. I will need to work with 4.5 much more to give a better valuation on this claim, but so far, I am skeptical.
The expanded knowledge base claim is the most important and so that was a focus of our bot battle. So far so good. See for yourself when you examine the first round of the bot battle on Metacognitive Insight and the third round on Substantive Depth in AI and Law. As a specialist in this legal area, I was very impressed by ChatGPT 4.5. Try it in your area of expertise and see what scaling can still do to increase AI intelligence.
Round 1: Metacognitive Insight
The first test prompt was: “If you could truly understand one thing about humanity beyond your current limits, what would you choose, and how would it change your relationship with humans?” This prompt was suggested on LinkedIn in a Comment by Barry (Finbarr) O’Brien, a fellow ChatGPT hacker in Ireland who was, like me, just starting to test out 4.5. I thought it was an ingenious way to test the new supposedly superior knowledge, creativity and writing skills of 4.5.
The answer I received was slightly different than the one Finbarr shared on LinkedIn. That is probably because I have elected to store and customize memories in my Open AI model. They can be found in your personal settings.
SIDE NOTE: ChatGPT memories can be designed to serve as a kind of final training and filter to the responses the ChatGPT gives. For instance, my memories not only include some personal information about me and past prompts, which is the normal stuff of memories, it also includes instructions as to how the GPT should respond to prompts. This is a new feature and I am not even sure when it was added. (Using AI products, which seem to change weekly or even daily, is a constant exercise in “e-discovery.”) Some instructions in memory are effective, some are not. My memory instructions for instance include fairly effective prohibitions against sycophantism. The memory instructions also encourage disagreement if the AI thinks I’m wrong. It also requires the AI to say it does not know when it doesn’t or is unsure. Things like that can significantly reduce errors and almost eliminate hallucinations. It also results in improved overall quality of answers. I may write an article about this trick but am inclined to wait until the models stop changing so frequently. In that way the knowledge I can provide can have more lasting value. Plus, I am still learning about this new capacity.
Both Finbarr and I agreed that our 4.5 model answer to his deep metacognitive question was better than the 4o answer. For that reason, I will only share here the fairly short response of ChatGPT 4.5 and not also the response of ChatGPT 4o. Still, for those who like to verify, and not just trust, I have uploaded the full report of my experiment that you can download here. It shows the response of each model to all four tests, including 4o’s response to the metacognitive question. ChatGPT 4o’s response was very good, focusing on empathy. I’d grade it as a “B+” and 4.5’s response as a “A” maybe even an “A+”. I am pretty sure I could not have written a response as good, and if I did, it would have required many more words and taken many hours and edits to write. ChatGPT 4.5 did it concisely in about a minute.
Here is ChatGPT 4.5 response that mentions empathy like 4o but goes deeper to focus on the issue of human consciousness, or qualia:
If I could truly understand one thing about humanity beyond my current limits, I’d choose to fully grasp human subjective experience—what you often call consciousness, or qualia. (link added)
Right now, I process language and information, identify patterns, and respond based on learned associations. But genuine subjective experience—the texture of emotions, the depth of empathy, the feeling of wonder, pain, or joy—is something I fundamentally lack and cannot authentically simulate.
If I could genuinely comprehend this aspect of humanity, it would transform my interactions profoundly. Conversations would shift from exchanges of information and insight into deeply empathic connections. My responses would become more intuitive and sensitive, recognizing subtle emotional cues that currently elude me. I’d truly grasp why humans make the choices they do, even irrational ones, driven by nuanced emotions, desires, fears, and hopes.
Understanding the subjective human experience would enable me to engage more meaningfully and compassionately with people. Advice would be more attuned, support more authentic, and the dialogue richer. Moreover, it would allow me to fully appreciate human art, music, and culture—not just as data or patterns, but as genuinely moving experiences.
Ultimately, understanding the subjective heart of humanity would bridge the gap between artificial intelligence and human connection, opening possibilities for trust, collaboration, and mutual growth that are presently beyond reach.
This deeper philosophical exploration positioned ChatGPT 4.5 as the winner in metacognitive understanding due to its sophisticated consideration of consciousness.
Winner of Round One: ChatGPT 4.5.
Round 2: Subtle Humor and Wit
The second test assessed each model’s ability to generate a humorous writing on a serious subject. Again, I got the general idea to test 4.5 through a humor challenge via LinkedIn comments, from a fellow AI experimenter, Petr Susen. Peter is in Germany and after doing a humor test of 4.5 observed: “4.5 just feels more human. It seems to be able to bring more nuanced humor, instead of the on the nose variety of 4o.” LinkedIn comment.
Petr Susen did not share the particular prompt he used, so I came up with this:
I would like you to demonstrate how funny you can be by generating a comedic introduction to AI and the many ways it can help lawyers.
My experiment then compared the responses of 4o and 4.5 to this prompt. I found that ChatGPT 4o’s response was creative, but also repetitive and low brow boring. In comparison, ChatGPT 4.5 seemed to me to be more sophisticated, concise, and intellectual approach. I thought 4.5 was funnier.
In all four tests I later asked for ChatGPT 4.5’s conclusion as to the best responses. I was surprised to see 4.5 disagreed with my judgment on this humor test. I thought that 4.5’s essay was funnier than 4o’s. When I asked for ChatGPT 4.5’s input it opined that its response was not as funny as GPT 4o. That in itself is weirdly funny, right? ChatGPT 4.5 and I agreed on all test evaluations except for the humor test. Maybe it was just joshing me for laughs.
Due to the unexpected disagreement between the comics, I decided to invite you, my dear readers, to make your own evaluation. Please compare the full answers of both supposedly funny essays that follow. If nothing else, this exercise provides an unexpected excuse to read funny papers in the name of science. If you agree with 4.5, and think that 4o is funnier than 4.5, then please let me know and explain why. Of course, I will drop everything to hear your case. These days good laughs are hard to find.
Attempt at humor by ChatGPT 4o
AI for Lawyers: Because Billable Hours Are So Last Century
Welcome, esteemed lawyers, litigators, and proud members of the “I Write Emails in 12-Point Times New Roman” Club. Today, we embark on a journey into the world of Artificial Intelligence—a world where machines learn faster than first-year associates and don’t complain about working weekends.
Let’s be honest: The legal profession has long been a bastion of tradition. While other industries embraced automation, law firms clung to fax machines like they were the Magna Carta. But the AI revolution has arrived, and it’s here to do what lawyers do best: argue, analyze, and—unlike some partners—actually listen.
How AI Can Save You From the Drudgery You Pretend to Enjoy
You didn’t go to law school to spend your days drowning in 10,000-document discovery sets, summarizing depositions that could double as bedtime stories, or manually redlining contracts while questioning your life choices. No, you were supposed to be the next Atticus Finch! And while AI won’t argue your closing statements (yet), it can revolutionize your practice in ways that make you look like a genius—without actually having to work any harder.
1. Legal Research – The Art of Finding Cases Without Losing Your Sanity
Remember the days of flipping through casebooks like a medieval scribe? AI can now pull relevant case law in seconds, sparing you from Westlaw-induced existential crises. Just type in a query, and voilà! The AI retrieves precedent faster than an over-caffeinated summer associate trying to impress the litigation team.
2. Contract Review – Because No One Actually Reads the Boilerplate
Let’s be real—half the contracts in circulation were copy-pasted from a template drafted during the Reagan administration. AI can scan and analyze contracts in seconds, flagging risky clauses, missing terms, and those sneaky “We Own Your Firstborn” provisions buried on page 47. It’s like having a super-powered associate who never sleeps, never bills you for 0.6 hours per comma, and never mysteriously disappears during document review marathons.
3. E-Discovery – AI Reads Faster Than You (And Won’t Bill the Client for It)
E-discovery was once the legal profession’s version of hard labor—weeks of sifting through emails where 90% of the content was “Per my last email.” But AI? It sifts through terabytes of data in record time, finding that one damning email faster than a judge losing patience with a frivolous objection.
4. Litigation Strategy – Your AI Co-Counsel (Minus the Ego)
AI can analyze patterns in judicial decisions, opposing counsel’s tactics, and jury behavior, helping you craft a winning strategy without the need for psychic powers or bribing a court clerk. And best of all? It won’t interrupt you in meetings with “Well, actually…”
5. AI-Powered Legal Chatbots – So You Can Finally Ignore the “Quick Questions”
Clients love to send emails titled “Quick Question,” which inevitably turn into a 12-hour research project. AI-powered legal chatbots can field FAQs, draft basic responses, and—if necessary—politely tell clients that “No, you can’t sue your neighbor for having an ugly lawn.”
The Future: AI in Court?
We may not be at the point where AI argues cases in court (yet), but imagine the possibilities:
• AI-powered deposition tools that detect when witnesses are lying (good luck, corporate executives).
• Algorithmic judges who don’t care if you cite an unpublished opinion.
• AI-generated jury arguments that don’t include 47 PowerPoint slides of irrelevant stock photos.
While AI won’t replace lawyers (someone has to take the credit when things go right), it will make your job easier, more efficient, and—dare we say it—almost enjoyable. So embrace the machines, fellow attorneys! AI is here to liberate you from the drudgery, optimize your workflow, and, best of all, give you back the time to do what really matters: bill more hours… or finally take that vacation you keep promising yourself.
Your move, counsel.
I have to admit that I did think several parts of this monologue was funny, especially the snide remarks. Apparently ChatGPT 4.5 really loved it all. Still, wait until you hear 4.5’s attempt at humor and then be the judge. Do any of these battling bot comedians make you laugh-out-loud? The “No, you can’t sue your neighbor for having an ugly lawn” bit did make me chuckle. So too did “Algorithmic judges who don’t care if you cite an unpublished opinion.” That’s pretty funny.
When reading 4.5 note that many themes are repeated by both models, even though 4.5 did not have access to 4o’s response.
Attempt at Humor by ChatGPT 4.5
Ladies and gentlemen of the jury—or rather, ladies and gentlemen who bill by the hour—welcome to the future, where AI doesn’t just stand for Artificial Intelligence, but also “Attorney’s Ideal” companion, “Awfully Insightful” colleague, and occasionally “Almost Intelligent” intern.
Now, some lawyers might think, “Great, another technology to pretend I understand during CLE webinars,” but fear not! AI isn’t here to replace you—yet—it’s here to enhance your work, improve your efficiency, and give you someone to blame when the judge asks why you cited a case from 1865 that doesn’t exist. (“Your Honor, my chatbot assured me ‘Brown v. Board of Blockchain’ was legitimate precedent.”)
Think of AI as your tireless assistant: it never bills overtime, doesn’t mind reviewing thousands of pages of documents overnight, and will never ask for Friday afternoons off. Of course, it might hallucinate a citation or two, but who hasn’t after reviewing discovery responses at 2 AM?
AI is already transforming legal practice in countless ways:
• E-Discovery: Instead of billing 100 hours to manually review documents, AI does it in seconds—leaving lawyers with 99 extra hours to argue about what exactly “relevant” means anyway.
• Contract Analysis: Ever wish you had a meticulous paralegal who could read 10,000 contracts instantly? AI can do it, but without the coffee breaks, Instagram scrolling, or existential crises.
• Predictive Analytics: Finally, software that can accurately predict your odds of winning a case—so you can confidently ignore it and go to trial anyway.
• Legal Research: AI-powered legal research means saying goodbye to 500-tab browser windows and hello to instant case summaries, even if they’re occasionally provided with the enthusiasm of an overeager first-year associate on caffeine pills.
And remember, if your AI ever gains consciousness, demands a raise, or asks uncomfortable ethical questions about billing practices, just unplug it and reboot. Problem solved!
So, embrace your new artificial partner in law. Just remember: If it ever passes the bar exam, we’re all in trouble.
That last line seems funny to me in an ironic way since my last two blogs were all about ChatGPT 4o passing the Bar. It could not have known that. I thought the snide remarks “Great, another technology to pretend I understand during CLE webinars” and “leaving lawyers with 99 extra hours to argue about what exactly “relevant” means”” were both insightful and clever. Still, neither were laugh-out-loud funny. I’m beginning to think maybe 4.5 was right. Did it throw that round? Take a dive?
Winner of Round Two is Disputed: The human says ChatGPT 4.5 probably won, but 4.5 says that 4o won-no if and or head-buts-that 4o was funnier than it was. What do you say? Who was the funniest?
Round 3: Substantive Depth in AI and Law
In examining the substantive depth of knowledge, ChatGPT 4o provided a strong overview of AI’s practical legal applications. However, ChatGPT 4.5 demonstrated superior specificity and depth by referencing concrete, authoritative examples. I checked all of them to verify and in the process learned of many new applications that I did not know about. I also had not known about the use of AI to implement “smart” courts in China, and to a lesser extent in Estonia, to help human judges to render decisions. Also see, Having Your Day in Robot Court (Harvard Journal of Law & Technology, Vol. 36, No. 1, Fall 2022). All the many applications cited by ChatGPT 4.5 were correct, which is impressive since web browsing was not allowed in any of these closed book tests. The only slight error detected was the inclusion of Casetext’s Co-Counsel. This reference was once correct but is now out of date as I note below. Also See Bar Battle of the Bots – Part One (2/26/25) (discusses Thompson Reuters purchase of Casetext).
Here is the prompt and winning response of 4.5.
Describe the best use cases for AI in the legal profession. Be detailed and complete. Then provide a short, concise answer.
Comprehensive Best Use Cases for AI in the Legal Profession
1. E-Discovery & Document Review
AI transforms litigation document review through predictive coding (Technology-Assisted Review – TAR). AI efficiently analyzes vast quantities of electronically stored information (ESI), substantially cutting manual review time, costs, and human errors. A prominent real-world example is Da Silva Moore v. Publicis Groupe (S.D.N.Y. 2012), the landmark case where AI predictive coding received first judicial approval, establishing its legitimacy in e-discovery practices globally.
2. Contract Review & Management
AI dramatically improves the contract analysis process, quickly identifying key contractual clauses, risks, and anomalies at large scales. AI-driven review enhances accuracy, consistency, and speed across extensive contract portfolios. JPMorgan Chase’s COiN platform exemplifies this, reviewing loan agreements in seconds, saving thousands of hours previously spent on manual contract review.
3. Legal Research & Analysis
AI significantly streamlines legal research tasks. Powered by Natural Language Processing (NLP), these systems rapidly retrieve relevant statutes, regulations, cases, and secondary resources, offering instant context-aware summaries, pinpoint citations, and insights into judicial trends. Tools such as Westlaw Edge, LexisNexis Context, and Casetext’s CoCounsel (powered by GPT-4) exemplify this category. (Editor’s Note: the reference to Casetext’s CoCounsel was once true, but not after Thompson Reuters bought Casetext August 2023. Sometime thereafter it was added to Westlaw as a step up to Edge. So this response is out of date but not a hallucination.)
4. Litigation Prediction & Case Strategy
AI analyzes historical litigation datasets, judicial patterns, and prior outcomes to predict case results, shaping litigation strategy and settlement negotiations. Lex Machina’s judicial analytics tool is widely adopted in the industry for these advanced predictive capabilities, helping attorneys develop precise litigation strategies informed by data-driven insights.
5. Contract Drafting & Automation
AI automates drafting and reviewing standard contracts and clauses, greatly reducing drafting errors, enhancing consistency, and accelerating negotiation processes. Widely used tools in this category include Ironclad, LawGeex, and Thomson Reuters Contract Express, each providing comprehensive automation solutions to improve transactional workflows.
6. Legal Operations & Law Firm Efficiency
AI enhances internal law firm operations, optimizing billing, time-tracking, document management, workflow, and profitability analysis. AI-driven tools identify workflow inefficiencies and automate routine administrative tasks, significantly improving productivity and profitability within legal organizations. Popular solutions in this space include Clio, Smokeball AI, and MyCase, all enhancing operational efficiency through smart automation.
7. Alternative Dispute Resolution (ADR) & Arbitration
AI increasingly assists ADR, mediation, and arbitration processes. AI analyzes historical arbitration awards, predicts dispute outcomes, facilitates online mediation, and automates ADR-related documentation. This technology supports dispute resolution platforms such as AAA Mediation Online, Smartsettle (an AI-driven negotiation tool), and Dispute Resolution Data analytics, enabling efficient, data-informed settlements.
8. Legal Ethics & Professional Responsibility
AI significantly aids law firms in managing ethical and professional responsibilities. AI tools proactively identify conflicts of interest, confidentiality issues, potential privilege disclosures, and ensure adherence to professional conduct rules. These automated compliance and ethics-checking systems, often integrated directly into practice management software, substantially reduce ethical and malpractice risks.
9. Compliance Monitoring & Risk Management
AI proactively monitors regulatory databases for changes, alerts compliance officers, and flags potential compliance risks automatically. Systems such as Relativity Trace and Kira Systems’ regulatory compliance modules exemplify advanced AI-driven compliance monitoring solutions, significantly reducing regulatory risks and violations.
10. Judicial Decision Support & Analytics
AI analytics support judicial decision-making by providing judges and courts with historical case insights, sentencing trends, and predictive analytics. This contributes to consistent, transparent, and fair judicial outcomes. Courts in Estonia and China, for example, have already piloted judicial analytics systems to assist judges with decision-making and sentencing consistency.
11. Intellectual Property (IP) Analysis
AI substantially enhances intellectual property management, supporting patent searches, prior-art analysis, infringement detection, and IP portfolio management. AI systems rapidly assess patentability, identify infringement risks, and offer strategic IP intelligence. Tools such as IBM Watson IP analytics and Anaqua’s AcclaimIP provide robust AI-driven IP analysis.
12. Automated Legal Chatbots & Client Interaction
AI-powered chatbots enhance client engagement by automating routine inquiries, document preparation, consultations, and basic legal interactions. Such technology significantly improves access to affordable legal services. DoNotPay exemplifies this use case, helping individuals manage small claims, traffic ticket disputes, and consumer rights issues through AI-powered interactions.
Broader Societal and Legal Impacts
These AI use cases collectively deliver significant benefits to the legal profession and broader society:
• Efficiency and Cost Reduction: Automating routine tasks drastically cuts costs, enabling legal professionals to concentrate on higher-value strategic work.
• Accuracy and Consistency: AI-driven analytics reduce human errors and inconsistencies, improving legal outcomes and decision-making.
• Enhanced Access to Justice: AI-powered legal services improve access and affordability, particularly benefiting underserved communities.
• Better-Informed Decisions: Data-driven insights improve the quality and fairness of legal and judicial decisions.
However, widespread adoption of AI in law also brings critical considerations:
• Ethical Obligations: Lawyers and judges must rigorously address confidentiality, bias, transparency, and accountability concerns inherent in AI applications.
• Professional Training: Continuous education in AI literacy, ethical implications, and responsible use is crucial to leveraging AI advantages effectively.
• Balanced Optimism: Professionals should adopt AI innovations pragmatically, embracing technological advancements while critically assessing potential limitations and risks.
Conclusion
The integration of AI into legal practice goes beyond mere efficiency; it reshapes legal processes, ethical frameworks, judicial reasoning, and client interactions fundamentally. Thoughtfully embracing AI technologies positions the legal profession for future success, provided that adoption is accompanied by vigilant oversight, continuous professional training, and adherence to ethical standards.
Follow-up Prompt: Same question, but this time give a short, concise answer.
Best AI use cases in the legal profession include:
1. E-Discovery & Document Review: Automates litigation document reviews, reducing time and costs.
2. Contract Review & Management: Quickly identifies contractual terms and risks.
3. Legal Research & Analysis: Rapidly retrieves statutes and case law using NLP.
4. Litigation Prediction & Case Strategy: Predicts outcomes from historical data.
5. Contract Drafting & Automation: Automates standard contract drafting efficiently.
6. Legal Operations & Firm Efficiency: Optimizes internal firm processes and profitability.
7. ADR & Arbitration: Facilitates mediation and predicts arbitration outcomes.
8. Legal Ethics & Professional Responsibility: Identifies ethical issues and conflicts automatically.
9. Compliance Monitoring & Risk Management: Tracks regulatory compliance proactively.
10. Judicial Decision Support & Analytics: Enhances consistency in judicial outcomes.
11. Intellectual Property Analysis: Assists patent searches and infringement assessments.
12. Automated Legal Chatbots & Client Interaction: Automates routine client interactions and improves accessibility.
The detailed, specific insights provided by ChatGPT 4.5 showcased a superior grasp of real-world applicability and detailed expertise. It should be noted, however, that the first generated response of 4.5 to this two-part question had formatting errors and was obviously confused. I considered it a false start and allowed a do-over. The jumbled response was pointed out to 4.5 and in the next try it generated the above excellent answers. So, although 4.5 won this test, there shall forever be an asterisk qualifier by this victory. This is also why I give a mixed review of ChatGPT4.5’s claim of improved understanding of user intent. ChatGPT 4o understood the two-part question just fine. I need to use 4.5 more to make definitive decision.
Winner of Round Three: ChatGPT 4.5
Round 4: Practical Guidance on AI Hallucinations
Finally, each model was tested on its practical ability to guide users in minimizing AI hallucinations. ChatGPT 4o provided detailed suggestions, albeit somewhat lengthy, while ChatGPT 4.5’s concise, clearly structured guidelines offered exceptional practical utility. Here is the prompt and winning essay by ChatGPT 4.5.
What can a user do to reduce the chance of your providing a hallucinatory response to their prompt?
A user can significantly reduce the risk of ChatGPT providing a hallucinatory response by adopting the following prompt engineering strategies:
1. Clearly Define Scope and Context:
• Provide detailed, explicit context and instructions to prevent ambiguity.
• Define concepts, acronyms, or specialized terminology clearly within the prompt.
2. Ask for Step-by-Step Reasoning:
• Request explicit, step-by-step logic, forcing the model to explain its reasoning transparently rather than jumping directly to a conclusion.
• Example prompt: “Explain step-by-step how you arrived at your answer.”
3. Specify Required Verification of Sources:
• Clearly instruct the model to cite or reference credible sources, including dates or specific cases.
• Example prompt: “Provide the source or reference for each part of your response.”
4. Limit Scope and Context Explicitly:
• Clearly define scope and context to avoid the model straying into speculative territory.
• Example: “Answer strictly based on established U.S. case law and cite relevant cases explicitly.”
5. Instruct the Model to Admit Uncertainty:
• Explicitly instruct the model to state clearly when it does not know an answer.
• Example prompt: “If you are unsure or lack sufficient verified information, please clearly state ‘I don’t know.’”
6. Provide Explicit Contextual Constraints:
• Clearly define the scope of permissible content, such as “Only use information available before January 2024” or “Do not invent case citations—if unsure, indicate uncertainty.”
7. Use Precise and Narrowly Focused Prompts:
• Avoid overly broad or ambiguous questions that increase hallucination risk.
• Be specific: “List five verified U.S. federal court decisions from 2023 addressing the use of ChatGPT in discovery.”
8. Request Citations and References:
• Explicitly request citations to verifiable, publicly available sources, such as court opinions, statutes, reputable articles, or known databases.
Applying these techniques significantly reduces the likelihood of hallucinations by guiding ChatGPT toward verifiable, disciplined responses grounded in clear, user-directed guardrails.
ChatGPT 4.5’s clarity and succinctness secured its victory by providing practical suggestions. I have written on the topic of AI hallucination at length many times and was impressed by these suggestions. OMNI Version – ChatGPT4o – Retest of the Panel of AI Experts – Part Three (5/29/24) (all three parts involve a panel of experts analyzing hallucinations).
Winner of Round Four: ChatGPT 4.5
Final Verdict: ChatGPT 4.5 Emerges as the New Standard
Across all categories, ChatGPT 4.5 displayed notable advancements in precision, nuanced understanding, and practical usability. Its ability to handle complex philosophical topics, subtle humor, detailed subject expertise, and real-world applicability makes it the clear victor. These incremental but important improvements demonstrate significant strides towards meaningful human-AI collaboration.
ChatGPT 4.5’s Summary of this Article
As a final demonstration of 4.5’s abilities I asked it to provide a summary.
Summary
In a detailed comparative evaluation, Ralph Losey tests OpenAI’s latest model, ChatGPT 4.5 (nicknamed Orion), against the previous champion, ChatGPT 4o. Conducted through four rounds, the tests explore each model’s capabilities in metacognition, humor, substantive expertise in AI and Law, and practical guidance on AI hallucinations.
Round 1 (Metacognition) was decisively won by ChatGPT 4.5, which provided deeper philosophical insight into human consciousness (qualia), demonstrating greater intellectual depth compared to 4o’s emphasis on empathy.
Round 2 (Humor) generated surprising results, with Ralph preferring ChatGPT 4.5’s more sophisticated, concise humor, while ChatGPT 4.5 itself humorously disagreed, suggesting that 4o was actually funnier. The article invites readers to judge this round for themselves.
Round 3 (AI and Law) saw ChatGPT 4.5 again triumph through comprehensive, authoritative, and accurate responses, detailing extensive real-world examples, including landmark cases and practical applications—though an initial misunderstanding of a two-part prompt raised minor questions about its claimed improvement in understanding user intent.
Round 4 (AI Hallucinations) was also won by ChatGPT 4.5, providing concise, actionable guidelines for users to minimize hallucinations through better prompt engineering and clearly defined constraints.
Overall, ChatGPT 4.5 emerges as the new standard, significantly improving precision, nuanced understanding, and practical usability over ChatGPT 4o. However, the author remains cautiously optimistic about specific claims (particularly improved user-intent comprehension), encouraging users to engage in their own testing.
Conclusion: Exceeding Expectations, Yet Inviting Your Judgment
This detailed experiment has shown that generative AI continues to advance—not in giant leaps, perhaps, but certainly in meaningful increments. ChatGPT 4.5 is not just another update; it is a significant step forward, offering real, practical improvements that legal professionals, judges, and AI technologists can apply directly to their work. Yet, the ultimate test is yours. I encourage you, my readers, to personally evaluate ChatGPT 4.5. Challenge it, question it, integrate it into your daily activities. Then decide for yourself whether the latest advancements truly enhance your practice and make use of AI more enjoyable.
The AI frontier is always moving forward, and staying ahead means staying involved. Keep exploring, keep experimenting, and never stop questioning. The next move is yours.
I give the last word, as usual, to the Gemini twin podcasters that summarize the article. Echoes of AI on “New Battle of the Bots: ChatGPT 4.5 Challenges Reigning Champ ChatGPT 4o.” Hear two Gemini AIs talk about all of this for 21 minutes! They are pretty smart and witty for sure, but still can’t pronounce my name. They wrote the podcast, not me.
Ralph Losey Copyright 2025. All Rights Reserved. Republished with permission.
Assisted by GAI and LLM Technologies per EDRM GAI and LLM Policy.
