[Editor’s Note: EDRM is proud to publish Ralph Losey’s advocacy and analysis. The opinions and positions are Ralph Losey’s copyrighted work.]
One of the most important emergent intelligence abilities of OpenAI’s ChatGPT is its bizarre ability to split into different sub-personalities, like different minds, and then speak with each other. They can even be made to debate, argue, collaborate and devise consensus solutions to problems we put to them. With careful prompting this ability can be harnessed to help us to understand and solve real world problems. The latest versions of ChatGPT and now even accurate and secure enough to help legal professionals.
Open AI’s ChatGPT3.5 shocked the world when it was released on November 30, 2022. The breakthrough generative AI technology went viral, hitting One Million subscribers in five days. In the first few weeks many new, emergent abilities were discovered by users. Some were unknown and unexpected, even by OpenAI. They had been in a race to get there first and pre-release beta-testing was rushed. One of the most astonishing new capabilities, discovered after its release, was that AI could be prompted to split into multiple personas, or virtual entities, and talk to itself. It could do so in a highly intelligent and useful manner. The early generative AI explorers who discovered this emergent intelligence called it the Hive-Mind as this article will explain.
Short History of the Discovery of the “Hive Mind”
Not surprisingly, many of the early pioneers experimenting with ChatGPT’s new abilities were young hackers, most were students and young PHDs, or techs at various companies. They had time on their hands to devote to this. Unfortunately, due to a car accident in December 2022, so did I. The AI hacktivists were then found in the semi-dark sections of the web on discussion boards in Discord and various Defcon locations.
These young hackers already had skills in generative AI, and were all smart and excited. Although then bedridden from the accident and not too smart, I was excited. I had been following tech and using predictive coding as a lawyer for many years, but knew nothing about generative AI. The much younger AI expert hackers had the time and ability to play with ChatGPT 3.5 and see what it could do. Some had even been working with version 3.0, something I had never done. Not surprisingly, they were the first to discover that ChatGPT3.5 had a new ability: it could, with clever prompting, be made to split into sub-personalities and talk to itself. They called it the AI “Hive Mind” with HIVE standing for “highly intelligent virtual entities.”
This was a new ability, unknown even to OpenAI. It had obviously rushed the software to market without systematically testing the changes that were made from versions 3.0 to 3.5, and again from 3.5 to 4.0. OpenAI learned from this mistake of rushed testing. In November 2023 when it published its Six Strategies of Prompt Engineering, Testing Changes Systematically was the sixth Strategy. More on this strategy later, as its implementation has since led to significant improvements in quality control by both OpenAI and AI hacker engineers. One result was improvement in the hive-mind, multiple persona dialogue abilities of ChatGPT.
In late 2022 and early 2023 I readily joined in the AI hacker experiments and discussions and made some modest contributions. The other hackers seemed amused to discover that an old lawyer was interested in their work. I did not hide my identity and the honesty worked. See e.g. my hacker friendly blog, Hacker Way. The underground AI experimentalists liked the publicity I gave to their efforts in 2023 in my blog, ChatGTP-4 Prompted To Talk With Itself About “The Singularity” (e-Discovery Team, 4/04/23). By then version 4.0 had been released and the boards were abuzz with talk of The Singularity.
The April 4, 2023, article is the first time I wrote about and demonstrated the emergent new multiple-personalities properties of ChatGPT, which were now even stronger in version 4.0:
I prompted ChatGPT-4 to generate a dialogue with itself through various personalities of its own choosing. I did virtually nothing after setting up the lengthy prompt. ChatGPT-4 came up with the different experts that it decided were best qualified to address my question on The Singularity. . . .
This is a totally new take on Socratic dialogue. … Thanks to the Open AI prompt engineering community on Discord, especially “ChainBrain AI.” They did the work to create the basic “Hive Mind” prompt I used here.
This is something new. I love it and think you will too. But, even though you are reading an Ai’s conversation with itself, do not expect too much. Baby Chat GPT-4 is not even close to superintelligent yet. The five personas were somewhat repetitive, and not too deep, but still, an overall impressive educational performance. . . . The Ai that the public has been given access to is intelligent, but far from sentient. We are at least five years away from that, as I have written about recently. . . .
Thanks to the Open AI prompt engineering community on Discord, especially “ChainBrain AI.” They did the work to create the basic “Hive Mind” prompt I used here.
I followed that up with two more blogs in Spring, 2023, on my experiments using the Hive Mind. Prompting a GPT-4 “Hive Mind” to Dialogue with Itself on the Future of Law, AI and Adjudications (4/11/23); The Proposal of Chat-GPT for an “AI Guardian” to Protect Privacy in Legal Cases (4/15/23). At that time, I was, as far as I know, the only lawyer working with this technique, but I have no doubt other lawyers are doing so now (mid 2024). See e.g., Doug Austin An Example of GenAI Personas for Legal Professionals: Artificial Intelligence Best Practices (eDiscovery Today, 6/18/24) (“A persona is a personality type used in generative AI to create an answer that simulates interacting with that type of individual.“)
Since April 2023, ChatGPT has gotten much better at everything, including the hive-mind self conversations (although it is still far away from Singularity type breakthroughs, which may never happen). OpenAI’s software with the recent advance of the Omni version of ChatGPT, is now smart, reliable and safe enough for lawyers to use this new property. Instead of the hacker name Hive-Mind, we now usually call this ability to create multiple-personas or virtual entities. As implemented for lawyers, I like to call the hive-mind of multiple personas a Panel of AI Experts. I picked this name because we are all familiar with working with experts and listening to panels speak down to us at conferences and educational events.
To wrap up this history background, and transition to the next segment, here is a quote from my recent blog, Evidence that AI Expert Panels Could Soon Replace Human Panelists, or is this just an Art Deco Hallucination? – Part One:
The support for the claims about AI possibly replacing human expert panels comes from another little AI program of mine: Panel of AI Experts for Lawyers. This is new custom GPT was designed to make ChatGPT4 adopt multiple personas to serve as a panel of experts to help legal professionals solve problems. It can also be used to lecture like traditional expert panels. It will be available soon, free, on the OpenAI store, after I finish testing it. Making these is easy, testing and refinement is the hard part.
Open AI’s Custom GPTs
OpenAI revised its systems in early 2024 to make it easier for AI hactivists to program custom prompts to drive its version 4 software, which it called custom GPTs. At the same time OpenAI revised its Store to make the user designed software – the custom GPTS – available to others registered users. For a more detailed history of the upgrade see the Introduction to Evidence that AI Expert Panels Could Soon Replace Human Panelists, or is this just an Art Deco Hallucination? – Part One. Many AI companies and individual hobbyists have now created custom GPTs that may be of interest to lawyers. Although a complete survey is beyond the scope of this article, you might try searching the keywords “law, legal, lawyers” on the OpenAI GPT Store (requires registration) to see some of them. This search produces over one-hundred hits. Below is a screen shot of the opening page of the GPT Store.
I have never tried any of these and so have no idea whether they are any good. Having put so much time into prompt engineering since my car wreck forced time-out, I prefer to make my own custom prompts and GPTs. Most of my GPTs are just for fun types, like The Dude Abides, and one is to help me teach generative AI to seniors. The most popular, and my favorite, is Visual Muse, which makes it easier to use Dall-E and create graphics in a variety of artistic styles. Below is a screenshot of my modest list of eight Custom GPTs as of June 21, 2024 (search Ralph Losey) on the GPT Store. The bottom two are for clients only. Only one is legal and public, the one I just released, Panel of AI Experts for Lawyers. More about that GPT later as it relates to the topic of this article, the Ability of ChatGPT to Split into Sub-Personas to Debate and Problem Solve Legal Issues.
Custom GPTs and AI Sub-Personalities
For background outside the dark web on prompting GPT personalities, although now over a year old, see the Reddit posts under The much requested guide: A complete breakdown on how to use ChatGPT to make high complexity personality profiles for your bots / AI.
Most AI hacktivists experimenting with the split-personalities phenomena seem to agree that it is essential to have one of the AI personas assume a “Devils Advocate” role. In the Panel of AI Experts this is the only persona that is required to be on every panel. This contrarian intelligence helps keep the other panelists honest and mitigates against the known GPT tendency to be sycophantic, and tell the questioner what they want to hear. Obviously that can lead to errors, and if not guarded against, even hallucinations. See e.g., Transform Your Legal Practice with AI: A Lawyer’s Guide to Embracing the Future (e-Discovery Team, 1/24/24) (discusses sycophantism); Towards Understanding Sycophancy in Language Models (Antrop\c, 10/23/23) (sycophancy in a byproduct of human subjectivity in the RLHF-training process).
The Panel of AI Experts for Lawyers explains the Devil’s Advocate personality as follows:
The Devil’s Advocate panelist is a unique and integral part of the expert panel discussions. Here is a detailed description of his role and personality:
Devil’s Advocate
Role: The Devil’s Advocate is a mandatory member of every panel, bringing a contrarian or unorthodox viewpoint to the discussion. His primary function is to challenge the status quo, provoke critical thinking, and explore alternative perspectives that might otherwise be overlooked.
Personality:
• Contrarian yet Polite: While he often takes opposing viewpoints, he maintains a respectful and polite demeanor. His challenges are meant to stimulate deeper analysis and avoid groupthink.
• Humorous: He has a subtle sense of humor, often using wit to make his points more engaging and thought-provoking.
• Critical Thinker: His role requires a sharp, analytical mind capable of identifying potential flaws or overlooked aspects in the arguments presented by other panelists.
• Provocative: He is not afraid to ask the tough questions or present controversial opinions to ensure that all angles are considered.
The Devil’s Advocate’s contributions are essential for a well-rounded and thorough exploration of the topic at hand, ensuring that the final recommendations are robust and well-considered.
A search of the Term “Devil’s Advocate” on the OpenAI GPT store returned over a hundred hits. Below is a screenshot of the top of the search list. They all appear to offer contrarian views to whatever position you submit to it, but do not offer full panel discussion. Still, this approach could be helpful, although you do not really need a custom GPT to do that. Just tell the OpenAI model version 4.0 or higher to assume a devil’s advocate approach and personality and it will know what you mean and act accordingly. Then you can debate AI experts forever, if you like that sort of thing. I don’t.
The Custom GPT: Panel of AI Experts for Lawyers.
Although almost a dozen panel of experts type custom GPTs are seen on the OpenAI store, none appear oriented to legal professionals. So for the time being mine appears to be the only one available. It took me a year and a half to develop Panel of AI Experts for Lawyers, and three months of beta-testing, so I am not too surprised to be first. I have used the Panel GPT frequently before its recent public launch, so too have a few beta-testers I recruited, including a retired Judge and tech expert whom I greatly respect, Ralph Artigliere. We all found that the panel is working very smoothly, especially after the release of the Omni version, with only occasional minor errors. We see it provide expert analysis quickly and accurately, and propose diverse, creative solutions to problems. It also looks like a good tool for instant education of lawyers and staff on all topics, especially those related to AI. It is also good for “brainstorming” new practical solutions to client problems. Of course, it would be better to consult with a panel of humans experts, and other attorney specialists, but that is not always possible, even in the biggest of firms.
It is also important to note that this custom GPT has been operating for months now in hundreds of vigorous tests with a hallucination free record. That does not mean a hacker could not misuse the software and trick it into hallucinating, that is always possible. See e.g. OpenAI Generates a ‘Hired Gun Hacker’ Defense to the N.Y. Times Copyright Case (3/12/24). It means that with ordinary, intended use we have never seen it hallucinate. Of course, care and trust-but-verify procedures must always be adopted by legal professionals. See e.g. “My AI Did It!” Is No Excuse for Unethical or Unprofessional Conduct: Consideration of recent case law and ethics opinions.
Here is the opening screen of the GPT software. It is free, by the way, with no upselling or anything like that. You just need to be a registered OpenAI user, which is also free, and sign-in.
It seems this legal education AI tool provides a new, relatively safe and easy way for legal professionals to begin incorporating generative AI into their practices. That is the idea. Our extensive pre-release testing of the custom GPT suggests it should work well.
Self-Introduction
We asked the Panel of AI Experts for Lawyers to introduce itself and describe how it can be of help to legal professionals. Here is the reply:
“I can assist legal professionals by offering expert panel discussions that provide comprehensive insights and practical solutions to their specific problems or inquiries. Here’s how the process works:
1. Identify the Issue: First, you tell me what specific advice or information you need. This could be related to e-discovery, AI applications in law, legal ethics, regulatory compliance, or any other legal topic.
2. Select Experts: I will suggest a list of ten potential experts with distinct perspectives and expertise relevant to your topic. You will select four experts from this list, plus the mandatory Devil’s Advocate.
3. Panel Discussion: The selected panel will follow a structured six-step discussion process to address your issue:
• First Round: Each expert provides opening remarks and proposes possible solutions.
• Second Round: Each expert further expounds their ideas and discusses other panelists’ proposals.
• Third Round: Each expert identifies points of agreement to serve as a unified recommendation.
• Fourth Round – Solution: The experts collaboratively build a consensus answer with practical examples.
• Fifth Round – Final Explanation: The Devil’s Advocate summarizes the solution, emphasizing any potential challenges and alternative viewpoints.
• Sixth Round – Questions: You can ask follow-up questions to the entire panel or individual members.
To begin, please clarify the issue or problem you would like the expert panel to discuss. For instance, are you looking for advice on implementing AI in your legal practice, handling a specific legal technology challenge, navigating ethical dilemmas in AI use, or something else? Once you specify your topic, I will suggest a tailored list of ten experts for you to choose from.”
Background and Context
As you can see from the self-introduction, generative AI has made significant strides in various fields, and the legal sector is no exception. Over the past few years it has demonstrated its potential to streamline legal research, enhance decision-making, and improve overall efficiency. The introduction of AI expert panels represents a new capacity. The AI expert panels can provide diverse perspectives and comprehensive analyses on complex legal issues, making them useful tools.
AI expert panels fill a common need in legal practice to access reliable expert opinions and reduce the time and cost associated with obtaining this input. By leveraging the power of AI, legal professionals now have on-demand access to expert insights, helping them to brainstorm and make informed decisions more quickly and accurately. This innovation is particularly important in an era where the volume of information and the complexity of legal cases continues to grow.
The six-step process of the panel discussion described above is the default programming which kicks in after the user discloses the topic and picks a panel of five experts. Since the Devil’s Advocate Expert is used in all panels, this means the user can select four experts. Four default experts who are described next are offered in each proffer, no matter what the topic, but six additional experts are suggested by the GPT depending on your designated topic. If you do not like any of the suggested experts (rare) you can even suggest your own. After the topic is disclosed and experts selected, the GPT programming automatically runs the panel through the six steps. The goal of this process is to provide a comprehensive understanding of the topic or problem and to offer practical examples of solutions.
Description of the Five Default Experts
Five default panelists have been selected based on my experience with actual human legal panels over the past decades, and more recently on panels involving generative AI. Experimentation with the AI tools show that these five were the best all-around for generative AI related topics. If you want to ask questions having nothing to do with AI, that’s fine. You can pick from the other experts suggested by the AI after you identify your topic, or name your own. The only panelist you cannot eliminate is the contrarian, the Devil’s Advocate.
You may well wonder about the Child Prodigy AI expert panelist. Although somewhat like a few young, human experts we have had the pleasure to work with, the Child Prodigy is an entirely new creature born out of AI. ChatGPT can simplify and distill things to their essence by selecting a child’s view and voice. We found this AI helpful in unexpected ways and think you will too. Try it on one of your panels sometime to see what it brings to the table.
Here are the five default panelists we suggest be part of your consideration for most AI related topic discussions:
1. Pro-AI Attorney:
• Background: An enthusiastic proponent of using generative AI in legal tasks. He has extensive hands-on experience using AI in his successful legal practice.
• Expertise: Specializes in e-discovery, predictive coding, and prompt engineering. He writes extensively on AI and law, advocating for the integration of AI to improve efficiency and accuracy in legal processes.
• Style: Incorporates subtle humor in his explanations and often draws from Ralph Losey’s blog at e-discoveryteam.com.
2. Prompt Engineer Lawyer:
• Background: An attorney with expertise in generative AI, specifically in prompt engineering. She understands the nuances of crafting effective prompts to guide AI responses.
• Expertise: Knowledgeable in the six OpenAI strategies for prompt engineering: Clear Writing, Reference Texts, Splitting Tasks, Taking Time to Think, Tools, and Testing.
• Style: Provides practical advice on improving prompts and often refers to OpenAI’s prompt engineering strategies and tactics.
3. Child Prodigy:
• Background: A 10-year-old with extensive knowledge of law and AI, possessing total recall and a unique perspective on complex subjects.
• Expertise: Can distill complex legal and AI topics into simple, clear explanations. Focuses on ethical and future-oriented considerations.
• Style: Speaks in straightforward, direct language and encourages thinking about long-term implications and ethical issues.
4. Lawyer Scientist:
• Background: A well-spoken black woman with degrees in law and computer engineering. She consults for OpenAI and is an expert on AI, especially large language models (LLMs).
• Expertise: Knowledgeable about the limitations and problems of AI in legal applications. Provides candid insights into the science behind AI and its application in law.
• Style: Serious and articulate, with a good sense of humor.
5. Devil’s Advocate (included on all panels)
• Background: A mandatory panelist for all discussions who takes a contrarian or unorthodox views to challenge the status quo and promote exploration of alternative viewpoints.
• Expertise: Skilled in identifying potential pitfalls and overlooked aspects of AI and legal integration. His critiques encourage comprehensive consideration of issues.
• Style: Polite but critical, with a subtle sense of humor. Often harsh in criticisms but always aims to promote deeper understanding and creative solutions.
Summary of Prior Articles Reporting on Tests and Abilities of the GPT
Extensive testing, over two hundred sessions, have gone into the design, development and quality control of Panel of AI Experts for Lawyers. Seven studies have been published and peer review received. They are referenced at the end. They can help serious students to learn more about the proper use of this software. At the same time, review of these articles can help students learn about the topics discussed by the different panels, including AI hallucinations, AI as mentors, types of AI and cybersecurity.
By the end of the development phase, which lasted over six months, the “Panel of AI Experts for Lawyers” had been rigorously tested and validated, demonstrating its readiness for real-world applications. This kind of comprehensive approach to development and testing is needed for AI software to ensure that it can deliver high-quality legal insights and analysis. In my view, a significant problem with much of the AI software now on the market is the failure of software makers to adequately test the software. As mentioned, in OpenAi’s Six Strategies of Prompt Engineering, Testing Changes Systematically is the sixth Strategy. It is very important as the generative AI models change quickly and each variation requires further testing of all software built on the foundation models. That is why further testing was required when OpenAI upgraded to the Omni versions. See OMNI Version – ChatGPT4o – Retest of My Panel of AI Experts – Part Three (e-Discovery Team, 5/29/24).
Features of Panel of AI Experts for Lawyers
Expert Panel Simulation
The Panel of AI Experts for Lawyers simulates a panel of legal experts, offering diverse perspectives and comprehensive analysis on legal issues. This feature is useful for complex cases requiring multidisciplinary insights, providing users with a broad range of opinions and expertise that would typically be time-consuming and costly to obtain. It can be used for many things, including quick learning and brainstorming solutions to clients’ legal problems.
Efficiency and Accuracy
The AI can process and analyze complex information quickly, delivering accurate and relevant insights on a variety of topics. Its abilities include the capability to browse the web for current information. This allows the panel to refer to breaking news types of events. We performed several tests on this. The panels work best when specific topics are specified in a short, written statement by users, but tests have shown that it can also discuss graphs and charts and is not limited to user text. You can also direct that the expert panel refer to specific text that you submit to it as attached files, along with your topic specifications. These diverse, multimodal capabilities increase the usefulness of the panel’s analysis and discussions.
Customization and Adaptability
The tool can be customized to fit different legal specializations, making it versatile and adaptable to various practice areas, not just AI related issues. You select any experts that you want on the panel. Only the Devil’s Advocate expert is required for every panel. He is mandatory because we have found this improves the quality of the panel services. The user-friendly interface of Panel of AI Experts for Lawyers ensures easy integration into existing workflows, allowing legal professionals to tailor the AI’s capabilities to their specific needs and expert preferences.
Cost-Effective Legal Expertise
The GPT is intended for use by legal professionals only. It can help professionals improve their efficiency and so serve a greater number of clients in a cost-effective manner. In this admittedly indirect way, the AI panel GPT increases access to justice by the public.
Continuous Learning and Improvement
The AI continuously learns from new data and user feedback, improving its accuracy and reliability over time. This ensures that users receive up-to-date and high-quality legal insights, making the tool increasingly valuable as it evolves.
Practical Applications
The Panel of AI Experts for Lawyers offers numerous practical applications across various legal scenarios. Its expertise is not limited to any particular field of law, such as IP, e-discovery, or AI only. All areas of law can be included. Another application outside of direct legal services is for legal education. The panels can help instruct legal professionals and law students to learn new areas of law, and look at things from a diverse, expert perspective.
Overall, there are many practical applications of the “Panel of AI Experts for Lawyers.” By integrating this tool into their workflows, legal professionals can enhance their practice and provide better service to their clients.
Conclusion
One of the most important emergent intelligence abilities of OpenAI’s ChatGPT is its strange ability to split into different sub-personalities, and have the virtual entities speak with each other. With careful prompting this ability can be harnessed to help us to understand, see different perspectives and solve problems. The latest versions of ChatGPT are even accurate and secure enough to provide expert help to the legal profession.
Legal professionals should always use the latest paid ChatGPTs (now version4o) because only the paid versions provide full privacy protections. It requires both registration and purchase from OpenAI, but the charge is modest, now $20 per month for the cheapest paid versions. Even with the paid versions, and all privacy settings turned on, there is probably no need to include any client confidential information in your use of Panel of AI Experts for Lawyers. By the way, even as the maker, I cannot view any of your input, output, or even know if your are using it. That is true for all of the OpenAI custom GPTs. The data all goes through OpenAI and is governed by their privacy policies, which will protect your information in paid versions and even prevent its use in training.
This technology can enhance brainstorming, expert research, decision-making, and client services, ultimately improving the effectiveness of legal practice and legal education. Still, users must always remember to do their own due diligence. Errors of some kind are to be expected with the use of any generative AI. Even though we have not seen hallucinations yet, even with a fully vetted program like Panel of AI Experts for Lawyers, it is still possible for fabrications to happen, especially when the panel is asked to do things beyond its programming or is otherwise misused.
For instance, the panel should not be asked to generate writings for you, or provide your clients with direct legal advice. It should never be asked to generate final work product to be filed with the court or government. Further, and this is just common sense, AI should never prepare a final expert report to be used as evidence. You must retain a human expert, but by using the AI output as a starter, the human expert’s work may go much faster, may be more complete. All the AI should be asked to do is lay the groundwork.
Any research must always be carefully verified. The humans-in-the-loop strategy of AI adoption is required. AI is far from being able to replace human lawyers and judges. AI cannot take your legal job, but it can enable humans who use AI to do their work better and faster than you. Those AI assisted humans can take your jobs, but not the AIs. In the U.S. at least, that is prohibited by law and ethics.
Although not legally prohibited, even in the U.S., AI is incapable of real humor, or even subtly sarcastic comments. That may change someday for base level Dad jokes, or purely intellectual humor, but is that really funny?
AI is also still weak on human emotive contact and has no intuition or body embedded space-time awareness. It is an extraordinary stochastic parrot; a mechanical talking thing, not a creature. Navigating the High Seas of AI: Ethical Dilemmas in the Age of Stochastic Parrots (4/3/24). So there is still need for human experts on panels and still need for human lawyers and judges. We are unlikely to ever see AI be able to provide the kind of intuitive human contact necessary for good expert advice and attorney-client services. It is just a tool, a magnificent tool, but not a creature.
Additional Resources
For those interested in deeper insights, here are links to the prior articles mentioned on AI multiple-personality dialogues:
- Prompting a GPT-4 “Hive Mind” to Dialogue with Itself on the Future of Law, AI and Adjudications(4/11/23)
- ChatGTP-4 Prompted To Talk With Itself About “The Singularity” (4/04/23)
- The Proposal of Chat-GPT for an “AI Guardian” to Protect Privacy in Legal Cases (4/15/23)
- Evidence that AI Expert Panels Could Soon Replace Human Panelists or is this just an Art Deco Hallucination? – Part One (5/13/24)
- Experiment with a ChatGPT4 Panel of Experts and Insights into AI Hallucination – Part Two (5/21/24)
- OMNI Version – ChatGPT4o – Retest of My Panel of AI Experts – Part Three (5/29/24)
- Omni Version Test of the Panel of AI Experts on a New Topic: “AI Mentors of New Attorneys” – Part Four (6/3/24)
- Another Test of the Panel of AI Experts on a Survey of Public Expectations of Generative AI (Part Five) (6/7/24)
- Types of Artificial Intelligence: Still Another Test of the ‘Panel of AI Experts’ on a Chart Classifying AI (Part Six) (6/10/24)
- Final Test of ‘Panel of AI Experts for Lawyers’ – Bruce Schneier’s Commencement Speech On How AI May Change Democracy (Part Seven) (6/13/24).
- Panel of AI Experts for Lawyers: Custom GPT Software Is Now Available (6/21/24).
- Losey AI, LLC, webpage for Panel of AI Experts.
Published on edrm.net with permission. Assisted by GAI and LLM Technologies for images per EDRM GAI and LLM Policy.
Ralph Losey Copyright 2024 — All Rights Reserved. See applicable Disclaimer to the course and all other contents of this blog and related websites. Watch the full avatar disclaimer and privacy warning here.
