Epiphanies or Illusions? Testing AI’s Ability to Find Real Knowledge Patterns – Part One

August 4, 2025

Ralph Losey, August 4, 2025.

Humans are inherently pattern-seeking creatures. Our ancestors depended upon recognizing recurring patterns in nature to survive and thrive, such as the changing of seasons, the migration of animals and the cycles of plant growth. This evolutionary advantage allowed early humans to anticipate danger, secure food sources, and adapt to ever-changing environments. Today, the recognition and interpretation of patterns remains a cornerstone of human intelligence, influencing how we learn, reason, and make decisions.

Pattern recognition is also at the core of artificial intelligence. In this article, I will test the ability of advanced AI, specifically ChatGPT, to uncover meaningful new patterns across different fields of knowledge. The goal is ambitious: to discover genuine epiphanies—true moments of insight that expand human understanding and open new doors of knowledge—while avoiding the pitfalls of apophenia, the human tendency to perceive illusions or false connections. This experiment probes an age-old tension: can AI reliably distinguish between genuine breakthroughs and compelling yet misleading illusions?

Video by Ralph Losey using SORA AI.

We will begin by exploring the risks of apophenia, understanding how this psychological tendency can mislead human and possibly AI perception. Throughout, videos created by AI will help illustrate key points and vividly communicate these ideas. There are twelve new videos in Part One and another fourteen in Part Two.

Are the patterns real? Video by Ralph Losey using SORA AI.

Apophenia: Avoiding the Pitfalls of False Patterns

We humans are masters of pattern detection, but we do have hinderances to this ability. Primary among them is our limited information and knowledge, but also our tendency to see patterns that are not there. We tend to assume the stirring we hear in the bushes is a tiger ready to pounce when really it is just the breeze. Evolution tends to favor this phobia. So, although we can and frequently do miss real patterns, fail to recognize the underlying connections between things, we often make them up too.

Here it is hoped that AI will boost our abilities on both fronts. It will help us to uncover true new patterns, genuine epiphanies, moments where profound insights emerge clearly from the complexity of data. At the same time, AI may expose illusions, false connections we mistakenly believe are real due to our natural cognitive biases. Even though we have made great progress over the millennia in understanding the Universe, we still have a long way to go to see all of the patterns, to fully understand the Universe, and to free ourselves of superstitions and delusions. We are especially weak at seeing patterns and intertwined with different fields of knowledge.

Apophenia is a kind of mental disorder where people think they see patterns that are not there and sometimes even hallucinate them. Most of the time when people see patterns, for instance, faces in the clouds, they know it cannot be real and there is no problem. But sometimes when people see other images, for instance, rocks on Mars that look like a face, or even images on toast, they delude themselves into believing all sorts of nonsense. For instance, the below 10-year old grilled cheese sandwich, which supposedly bears the image of the Virgin Mary, sold to an online casino on eBay in 2004 for $28,000.

In a similar vein, some people suffering from apophenia are prone to posit meaning – causality – in unrelated random events. Sometimes the perceptions of new patterns is a spark of genius, which is later verified, think of Einstein’s epiphany at age 16 when he visualized chasing a beam of light. The new pattern recognitions can lead to great discoveries or detect real tigers in the bush. Epiphanies are rare but transformative moments, like Einstein’s visualization of chasing a beam of light, Newton’s realization of gravity beneath the apple tree, or the insights behind Darwin’s theory of evolution. They genuinely advance human understanding. Apophenia, by contrast, deceives with illusions—patterns that seem meaningful but lead nowhere.

It is probably more often the case that when people “see” new connections and then go on to act upon them with no attempts to verify, they are dead wrong. When that happens, psychologists call this apophenia, the tendency to see meaningful patterns where none exist. This can lead to strange and aberrant behaviors: burning of witches, superstitious cosmology theories, jumping at shadows, addiction to gambling.

Unfortunately, it is a natural human tendency to think you see meaningful patterns or connections in random or unrelated data. That is a major reason casinos make so much money from poor souls suffering from a form of apophenia called the Gambler’s Fallacy. Careful scientists look out for defects in their own thinking and guide their experiments accordingly.

In everyday life, apophenia can also cause some people, even scientists, academics and professionals, to have phobic fears of conspiracies and other severe paranoid delusions. Think of John Nash, a Nobel Prize winning mathematician, and the movie A Beautiful Mind, that so dramatically portrayed his paranoid schizophrenia and involuntary hospitalization in 1959. Think of politics in the U.S today. Are there really lizard people among us? In some cases, as we’ve seen with Nash, apophenia can lead to severe schizophrenia.

A man looking distressed, surrounded by glowing numbers and mathematical symbols, evoking a sense of confusion and complexity.
Mental anguish & insanity from severe apophenia. Image by Losey using Sora inspired by Beautiful Mind movie.

The Greek roots of the now generally accepted medical term apophenia are:

  • Apo- (ἀπο-): Meaning “away from,” “detached,” “from,” “off,” or “apart”.
  • Phainein (φαίνειν): Meaning “to show,” “to appear,” or “to make known”.

The word was first coined by Klaus Conrad, an otherwise apparently despicable person whom I am reluctant to cite, but feel I must, due to the general acceptance of word and diagnosis today. Conrad was a German psychiatrist and Nazi who experimented on German soldiers returning from the eastern front during WWII. He coined the term in his 1958 publication on this mental illness. Per Wikipedia:

He defined it as “unmotivated seeing of connections [accompanied by] a specific feeling of abnormal meaningfulness”.[4] [5] He described the early stages of delusional thought as self-referential over-interpretations of actual sensory perceptions, as opposed to hallucinations.

Apophenia has also come to describe a human propensity to unreasonably seek definite patterns in random information, such as can occur in gambling.

Apophenia can be considered a commonplace effect of brain function. Taken to an extreme, however, it can be a symptom of psychiatric dysfunction, for example, as a symptom in schizophrenia,[7] where a patient sees hostile patterns (for example, a conspiracy to persecute them) in ordinary actions.

Apophenia is also typical of conspiracy theories, where coincidences may be woven together into an apparent plot.[8]

Video by Ralph Losey using SORA AI.

Can AI Be Infected with a Human Illness?

It is possible that generative AI, based as it is on human language, may have the same propensities. That is unknown as of yet, and so my experiments here were on the lookout for such errors. It could be one of the causes of AI hallucinations.

In information science a mistake in seeing a connection that is not real, an apophenia, leads to what is called a false positive. This technical term is well known in e-discovery law, where AI is used to search large document collections. When the patterns analyzed suggest a document is relevant, and it is not, that mistake is called a false positive. It is like a human apophenia. The AI can also detect patterns that cause it to predict a document is irrelevant, and in fact the document is relevant, that is a false negative. There as a pattern, a connection, that was not seen. That can be bad thing in e-discovery because it often leads to withholding production of a relevant document, which can in turn lead to court sanctions.

In e-discovery it is well known that AI consistently has far lower false positives and false negative rates than human reviewers, at least in large document reviews. Generative AI may also be more reliable and astute that we are, but maybe not. This is a new field. Se we should always be on the lookout for false positives and false negatives in AI pattern recognition. That is one lesson I learned well, and sometimes the hard way, in my ten years of working with predictive coding type AI in the e-discovery (2012-2022). In the experiments described in this article we will look for apophenic mistakes.

Video by Ralph Losey using SORA AI.

It is my hope that Advanced AI, properly trained and validated, can provide a counterbalance to human gullibility by rigorously filtering of signal from noise. Unlike the human brain, which often leaps to conclusions, AI can be programmed to ground its pattern recognition in evidence, statistical rigor, and cross-validation—if we build it that way and supervise it wisely.

Still, we must beware that the pattern-recognizing systems of AI may suffer from some of our delusionary tendencies. The best practices discussed here will consider both the positive and negative aspects of AI pattern recognition. We must avoid the traps of apophenia. We must stay true to the scientific methods and verify any new patterns purportedly discovered. Thus all opinions reached here will necessarily be lightly held and subject to further experimentation by others.

Video by Ralph Losey using SORA AI.

From Data to Insight: The Power of New Pattern Recognition

Modern AI models, including neural networks and transformer architectures like GPT-4, excel at uncovering subtle patterns in massive datasets far beyond human capability. This ability transforms raw data into actionable insights, thereby creating new knowledge in many fields, including the following:

Protein Structures: Models like Google’s DeepMind’s AlphaFold have already revolutionized protein structure prediction, achieving high success rates in predicting the 3D shapes of proteins from their amino acid sequences. This ability is crucial for understanding protein function and designing new drugs and medical therapies. The 2024 Nobel Prize in Chemistry was awarded to Demis Hassabis and John Jumper of DeepMind for their work on AlphaFold.

A scientist analyzes molecular structures and data visualizations related to AlphaFold 2 on a futuristic screen, featuring protein models and DNA sequences.
Image by Ralph Losey using his Visual Muse AI tool.

Medical Science. Generative AI models are now being used extensively in medical research, including analysis and proposals of new molecules with desired properties to discover new drugs and accelerate FDA approval. For example, Insilico Medicine uses its AI platform Pharma.AI, to developed drug candidates, including ISM001_055, for idiopathic pulmonary fibrosis (IPF). Insilico Medicine lists over 250 publications on its website reporting on its ongoing research, including a recent paper on its IPF discovery: A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial (Nature Medicine, June 03, 2025). This discovery is especially significant because it is the first entirely AI-discovered drug to reach FDA Phase II clinical trials. Below is an infographic of Insilico Medicine showing some of its current work:

Infographic displaying the statistics and achievements of Insilico Medicine, an AI-driven biotech company, detailing development candidates, IND approvals, study phases, and global presence.
Insilico PDF infographic, found 7/23/25 in its 2-pg. overview.

Also see, Fronteo, a Japanese based research company, and its Drug Discovery AI Factory.

Materials Science. Google DeepMind’s Graph Networks for Materials Exploration (“GNoME”) has already identified millions of new stable crystals, significantly expanding our knowledge of materials science. This discovery represents an order-of-magnitude increase in known stable materials. Merchant and Cubuk, Millions of new materials discovered with deep learning (Deep Mind, 2023). Also see, 10 Top Startups Advancing Machine Learning for Materials Science (6/22/25).

Climate Science and Environmental Monitoring. Generative AI models are beginning to improve climate simulations, leading to more accurate predictions of climate patterns and future changes. For example, Microsoft’s Aurora Forecasting model is trained on Earth science data to go beyond traditional weather forecasting to model the interactions between the atmosphere, land, and oceans. This helps scientists anticipate events like cyclones, air quality shifts, and ocean waves with greater accuracy, allowing communities to prepare for environmental disasters and adapt to climate change. See e.g., Stanley et al, A Foundation Model for the Earth System (Nature, May 2025).

Video by Losey using Sora AI.

Historical and Artistic Revelations

AI is also helping with historical research. A new AI system was recently used to analyze one of the most famous Latin inscriptions: the Res Gestae Divi Augusti. It has always been thought to simply be an autobiographical inscription, which literally translates from Ancient Latin as “Deeds of the Divine Augustus.”  But when a specialty generative AI, Aeneas (again based on Google’s models) compared this text with a large database of other Latin sayings, the famous Res Gestae Divi Augusti inscription was found to share subtle language parallels with other Roman legal documents. The analysis uncovered “imperial political discourse,” or messaging focused on maintaining imperial power, an insight, a pattern, that had never seen before. Assael, Sommerschield, Cooley, et al. Contextualizing ancient texts with generative neural networks (Nature, July 2025).

The paper explains that the communicative power of these inscriptions are not only shaped by the written text itself “but also by their physical form and placement2,3” and that “about 1,500 new Latin inscriptions are discovered every year.” So the patterns analyzed not only included the words, but a number of other complex factors. The authors assert in the Abstract that their work with AI analysis shows.

… how integrating science and humanities can create transformative tools to assist historians and advance our understanding of the past.

Roman citizens reacting to propaganda. A Ralph Losey video.

In art and music, pattern detection has mapped the evolution of artistic styles in tandem with technological change. In a 2025 studio-lab experiment reported by Deruty & Grachten, a generative AI bass model (“BassNet”) unexpectedly rendered multiple melodic lines within single harmonic tones, exposing previously unnoticed structures in popular music bass compositions. This discovery was written up by Deruty and Gratchen, Insights on Harmonic Tones from a Generative Music Experiment (arXiv, June 2025). Their paper shows how AI can surface new musical patterns and deepen our understanding of human auditory perception.

As explained in the Abstract:

During a studio-lab experiment involving researchers, music producers, and an AI model for music generating bass-like audio, it was observed that the producers used the model’s output to convey two or more pitches with a single harmonic complex tone, which in turn revealed that the model had learned to generate structured and coherent simultaneous melodic lines using monophonic sequences of harmonic complex tones. These findings prompt a reconsideration of the long-standing debate on whether humans can perceive harmonics as distinct pitches and highlight how generative AI can not only enhance musical creativity but also contribute to a deeper understanding of music.

Video by Losey using Sora AI.

Legal Practice: From Precedent to Prediction

The legal profession has benefited from traditional rule-based statistical AI for over a decade, with predictive coding and similar applications. It is now starting to apply the new generative AI models in a variety of new applications. For instance, it can be used to uncover latent themes and trends in judicial decisions that human analysis has overlooked.

This was done in a 2024 study using ChatGPT-4 to perform a thematic analysis on hundreds of theft cases from Czech courts. Drápal, Savelka, Westermann, Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies (arXiv, February 2024).

The goal of the analysis was to discover classes of typical thefts. GPT4.0 analyzed fact patterns described in the opinions and human experts did the same. The AI not only replicated many of the human expert identified themes, but, as report states, also uncovered a new one that the humans had missed – a pattern of “theft from gym” incidents. This shows that generative AI can sift through vast case datasets and detect nuanced fact patterns, or criminal modus operandi, that were previously undetected by experts (here, three law students under supervision of a law professor).

Video by Losey using Sora AI.

Another study in early 2025 applied Anthropic’s Claude 3-Opus to analyze thousands of UK court rulings on summary judgment, developing a new functional taxonomy of legal topics for those cases. Sargeant, Izzidien, Steffek, Topic classification of case law using a large language model and a new taxonomy for UK law: AI insights into summary judgment (Springer, February 2025). The AI was prompted to classify each case by topic and identify cross-cutting themes.

The results revealed distinct patterns in how summary judgments are applied across different legal domains. In particular, the AI found trends and shifts over time and across courts – insights that allow new, improved understanding of when and in what types of cases summary judgments tend to be granted. These patterns were found despite the fact that U.K. case law lacks traditional topic labels. This kind of AI-augmented analysis illustrates how generative models can discover hidden trends in case law for improved effectiveness by practitioners.

Surprising abilities of Ai helping lawyers. Video by Losey.

Even sitting judges have begun to leverage generative AI to inform their decision-making, revealing new analytical angles in litigation. The notable 2023 concurrence by Judge Kevin Newsom of the Eleventh Circuit admitted to experimenting with ChatGPT to interpret an ambiguous insurance term (whether an in-ground trampoline counted as “landscaping”). Snell v. United Specialty Ins. Co., 102 F. 4th 1208 – Court of Appeals, (11th Cir., 5/28/24). Also See, Ralph Losey, Breaking News: Eleventh Circuit Judge Admits to Using ChatGPT to Help Decide a Case and Urges Other Judges and Lawyers to Follow Suit (e-Discovery Team, June 3, 2024) (includes full text of the opinion and Appendix and Losey’s inserted editorial comments and praise of Judge Newsom’s language.)

After querying the LLM, Judge Newsom concluded that “LLMs have promise… it no longer strikes me as ridiculous to think that an LLM like ChatGPT might have something useful to say about the common, everyday meaning of the words and phrases used in legal texts.” In other words, the generative AI was used as a sort of massive-scale case law analyst, tapping into patterns of ordinary usage across language data to shed light on a legal ambiguity. This marked the first known instance of a U.S. appellate judge integrating an LLM’s linguistic pattern analysis into a written opinion, signaling that generative models can surface insights on word meaning and context that enrich judicial reasoning.

A digital illustration of a judge in a courtroom setting, seated at a desk with a gavel. The judge, named Judge Newsom, is shown in a professional attire with glasses, and a holographic display behind him showing data and AI-related graphics, conveying a futuristic legal environment.
Image by Ralph Losey using his Visual Muse AI.

My Ask of AI to Find New Patterns

Now for the promised experiment to try to find at least one new connection, one previously unknown, undetected pattern linking different fields of knowledge. I used a combination of existing OpenAI and Google models to help me in this seemingly quixotic quest. To be honest, I did not have much real hope for success, at least not until release of the promised ChatGPT5 and whatever Google calls its counterpart, which I predict will be released the following week (or day). Plus, the whole thing seemed a bit grandiose, even for me, to try to get AI to boldly go where no one has gone before.

Absurd, but still I tried. I won’t go through all of the prompt engineering involved, except to say it involved my usual a complex, multi-layered, multi-prompt, multimodal-hybrid approach. I tempered my goals by directing ChatGPT4o, when I started the process, to seek new patterns that were useful, not Nobel Prize winning breakthroughs, just useful new patterns. I directed it to find five such new patterns and gave it some guidance as to fields of knowledge to consider, including of course, law. I asked for five new insights thinking that with such as big ask I might get one success.

Note, I write these words before I have received the response, but after I have written the above to help guide ChatGPT4o. Who knows, it might achieve some small modicum of success. Still, it feels like a crazy Quixotic quest. Incidentally, Miguel de Cervantes (1547-1616) character, Don Quixote (1605) does seem to person afflicted with apophenia. Will my AI suffer a similar fate?

Don Quixote in modern world. Video by Losey using Sora.

I designed the experiment specifically with this tension in mind between epiphanies, representing genuine insights and real advances in knowledge, and illusions, which are merely plausible yet misleading patterns. One of my goals was to probe AI’s capacity to distinguish one from the other.

Overview of Prompt Strategy and Time Spent

First, I spent about a hour with ChatGPT4o to set up my request by feeding it a copy of the article as written so far. I also chatted with it about the possibility of AI finding new patterns between different fields of knowledge. Then I just told ChatGPT4o to do it, find a new inter connective pattern. ChatGPT4o “thought” (processed only) for just a few minutes. Then it generated a response that purported to provide me with the requested five new patterns. It did so based on its existing training and review of this article.

As requested, it did not use its browser capabilities to search the web for answers. It just “looked within” and came with five insights it thought were new. Almost that easy. I lowered my expectations accordingly before read the output.

That was the easy part, after reading the response, I spent about 14-hours over the next several days doing quality control. The QC work used multiple other AIs, both by OpenAI and Google, to have them go online and research these claims, evaluate their validity – both good and bad, engage in “deep-think,” look for errors, especially signs of AI apophenia, and otherwise invited contrarian type criticisms from them. After that, I also asked the other AIs for suggested improvements they might make to the wording of the five clams and rank them by importance. The various rewordings were not too helpful, but the rankings were, and so were many of the editorial comments.

The 14-hours in QC does not include the approximate 6-hours of machine time by the Gemini and OpenAI models to do deep think and independent research on the web to verify or disprove the claims. My actual 14-hour time included traditional Google searches to double check all citations as per my “trust but verify” motto. My 14-hours also included my time to read (I’m pretty fast) and skim most of the key articles that the AI research turned up, although frankly some of the articles cited were beyond my knowledge levels. I tried to up my game, but it was hard. These other models also generated hundreds of pages of both critical and supportive analysis, which I also had to read. Finally, I probably put another 24-hours into research and writing this article (it took over a week), so this is one of my larger projects. I did not record the number of hours it took to design and generate the 26 videos because that was recreational.

Surrealistic depiction of time in robot space by a Ralph Losey video.

Part Two of this article is where I will make the reveal. Was this experiment another comic story of a Don Quixote type (me) and his sidekick Sanchez (AI), lost in an apophenia neurosis? Or perhaps it is another story altogether? Neither hot nor cold? Stay tuned for Part Two and find out.

PODCAST

As usual, we give the last words to the Gemini AI podcasters who chat between themselves about the article. It is part of our hybrid multimodal approach. They can be pretty funny at times and provide some good insights. This episode is called Echoes of AI: Epiphanies or Illusions? Testing AI’s Ability to Find Real Knowledge Patterns. Part One. Hear the young AIs talk about this article for 25 minutes. They wrote the podcast, not me.

An illustration featuring two anonymous AI podcasters sitting in front of microphones, discussing the theme 'Epiphanies or Illusions? Testing AI’s Ability to Find Real Knowledge Patterns.' The background has a digital, tech-inspired design.
Click here to listen to the podcast.

Ralph Losey Copyright 2025 – All Rights Reserved.


Panel of Experts for Everyone About Anything – Part Three: Demo of 4o as Panel Driver on New Jobs

July 18, 2025

by Ralph Losey, July 18, 2025

This is the conclusion to the article, Panel of Experts for Everyone About Anything – Part One and Part Two. Here we give another demonstration of the software described in Part One. Part Two provided a demonstration where the software used the advanced reasoning model of OpenAI, ChatGPT 4.5. The demonstration included expert discussion of the hot issue of future employment. Here we use the free version, ChatGPT 4o, to see how it does and get another perspective about new jobs that will be needed with AI. The results are surprising.

Expert panels debating. All images in article are in Steampunk style this time and by Ralph Losey using AI.

Introduction

In Panel of Experts for Everyone About Anything – Part Two, we demonstrated how the Panel software works to analyze an article. We picked a NYT Magazine article that predicted 24 new jobs that would be created by AI. The demonstration used ChatGPT 4.5 as the engine. OpenAI now allows a user to select any model to which they have access, to drive a custom GPT. (For reasons unknown, this feature currently does not work on the Mac desktop version of ChatGPT.) The 4.5 model used in Part Two now requires an upgraded subscription, whereas model 4o is still free.

The cost of 4.5 may be beyond the reach of legal aid groups and some in the public using it for non-law-related questions. Thus, to be consistent with the public service intent behind the free software mentioned in Part One, we here demonstrate the software using ChatGPT 4o. For ease of comparison, and because the question of new jobs created by AI is so important, we repeat the issue again but throw in a few variations to keep it interesting.

Panels of Experts do battle to see who is the best. Image by Ralph Losey using AI.

How well will the ChatGPT 4o expert team do against the allegedly better 4.5 model? Will we learn anything new about jobs created by AI in Part Three that we did not already know from Part Two? Which panel is the winner? Which gave the best demonstration?

Read on and discover using classic steampunk style images, because, after all, once Einstein discovered Relativity, and Science quickly jumped into Quantum, shouldn’t we have continued to advance at that accelerated rate and discovered AI long ago? Think where we’d be today if we did, eh Mr. Babbage?

Charles Babbage (1791-1871), ‘father of computers’ shown in steampunk style by Losey. What took us so long?

First Demo of 4o Model Version

In some respects, I like the 4o version of the session better than the Model 4.5 version shown in Part Two. Here are the key excerpts from the response of the Panel of Experts for Everyone About Anything when we repeated the same initial User Prompt, namely to analyze the NYT’s article by Robert Capps, A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You.

4o PANEL: Let’s curate a panel to explore the implications of the NYT article “A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You”. Before we begin the panel discussion, I’ll propose eight candidate experts based on the article’s focus on AI disruption, new job creation, and socio-technical dynamics. You’ll choose four, and I’ll automatically add the mandatory Contrarian.

🎯 Article Focus:

  • Trust-based roles (e.g., AI auditors, ethicists)
  • Integration roles (e.g., AI plumbers, integrators)
  • Taste and creative decision-making (e.g., world designers)
  • Socioeconomic shifts due to AI (entrepreneurial entry-level roles)

👥 Suggested Panelists:

  1. Ethical AI Lawyer – interprets legal responsibility and liability frameworks for trust-based roles.
  2. AI Engineer – evaluates technical feasibility and skill demands of new AI-centric jobs.
  3. Creative Storyteller – articulates the evolution of taste-driven roles like world designers and content curators.
  4. Risk Officer – identifies governance and regulatory gaps in emerging hybrid AI-human workplaces.
  5. Data Visionary – maps future employment and systemic transformation under AI’s rise.
  6. Litigation Strategist – examines legal risks of roles like “legal guarantor” or “AI auditor” under current jurisprudence.
  7. Public Health Advocate – reflects on AI’s impact on human dignity, trust, and socio-emotional labor.
  8. Quantum Analyst – cross-reads how AI role disruption mirrors past technology shifts (like CAD/CAM or simulation in science).

Please select four experts from this list. I’ll then add the Contrarian and begin the panel.

USER: I choose 1, 2, 3 and 5.

4o PANEL: . . .

Panel on new jobs created by AI in steampunk style by Losey.

🎓 Ethical AI Lawyer — Legal and Ethical Responsibility Architect

The article’s treatment of trust-based roles like “AI auditors,” “legal guarantors,” and “trust authenticators” directly engages legal norms surrounding delegation of accountability. These roles resemble constructs already debated in U.S. case law like Mata v. Avianca Inc., where counsel submitted AI-generated briefs with hallucinated citations, prompting sanctions and affirming that humans remain the accountable party despite automation.

The concept of the “sin eater” — someone who absorbs A.I.’s mistakes — raises sharp questions about the limits of vicarious liability and professional standards. No matter how advanced the AI, current jurisprudence requires traceability to a human agent. This aligns with the Fed. R. Evid. 901(b)(9) authentication requirements for complex systems, demanding explainability and provenance.

Further, the emergence of “AI translators” and “ethics boards” intersects with legal debates over due process in algorithmic decision-making, especially under frameworks like Article 22 of the GDPR and proposals for AI-specific tort law in the EU AI Liability Directive. These developments could create novel duties of disclosure and internal governance.

Bottom line: AI may generate drafts, workflows, or evaluations, but legally enforceable trust must still be human-certified.

Engineer dissecting AI in steampunk style by Ralph Losey.

🧠 AI Engineer — Dissecting Feasibility and Tech-Skill Transitions

The article outlines plausible near-future roles such as AI plumbers, virtual twin managers, and integration specialists — all of which track well with emerging enterprise needs. From a systems engineering standpoint, each represents a layering of human interface over increasingly agentic AI.

A role like “AI plumber” is especially apt: as we move to multi-agent, multi-modal systems, debugging becomes less about code and more about tracing decision nodes through dynamic graphs. Tools like LangSmith or OpenTelemetry for AI will support this, but human oversight must close the loop.

Equally pragmatic is the “AI trainer” role, particularly in retrieval-augmented generation (RAG) settings where corporate data must be contextualized with extreme care. Hallucination risk escalates when source curation is poor — an engineer versed in prompt architectures and data labeling becomes indispensable.

However, I’d caution that some roles (e.g., “AI personality director”) may prove transient or cosmetic. Unless this impacts UX or regulatory tone (e.g., health chatbots), it will likely be a rebranded comms function.

Still, the job market is aligning. “AI consultant” and “integration lead” roles are skyrocketing per LinkedIn data. These aren’t speculative—they’re already hiring.

Human taste guiding AI image by Losey guiding AI.

✨ Creative Storyteller — Reframing Jobs Around Taste, Not Tasks

This article is really about the return of judgment as labor. The shift from doing to curating, from generating to refining, is the beating heart of the “taste economy” the author envisions.

Take the imagined roles of “story designer,” “differentiation designer,” or “world builder.” These all recast creativity as orchestration — selecting from near-infinite AI outputs to assemble emotionally resonant or brand-coherent narratives. In storytelling terms, we’re moving from penmanship to direction.

The Rick Rubin anecdote nails it: craft may fade, but curation ascends. Rubin’s “confidence in his taste” mirrors what’s being asked of tomorrow’s knowledge workers. We may not sculpt every sentence, but we’ll decide which sentences shape the message.

This resonates with media trends already: TikTok creators “direct” AI-generated visuals, musicians remix AI stems, and even journalists act more like narrative editors than sole authors. The job isn’t dying—it’s mutating.

And taste isn’t just aesthetic. It’s ethical, strategic, and human. As the article wisely closes: “We are the designers of our AI future. Let’s hope we have great taste.”

Robot Puppet Theatre in Steampunk style by Losey’s AI puppets.

🛰 Data Visionary — Mapping the Labor Realignment

The piece offers more than speculative roles—it maps a nascent transformation in the labor-capital interface. It posits three durable human moats: trust, integration, and taste. This triptych aligns with observed market inflections.

Trust anchors around accountability and transparency: humans ensure AI outputs meet institutional thresholds. Integration speaks to workflow orchestration—systems-thinking roles that bridge software and organizational context. Taste, the most abstract, becomes a differentiator in saturated generative landscapes.

This trifocal framework is not utopian. It mirrors what Erik Brynjolfsson calls the “complementarity imperative”: value will accrue where humans can amplify machine leverage, not where they replicate it. The World Economic Forum’s projection of 11 million new jobs by 2030 versus 9 million displaced jobs captures the macro realignment. [EDITOR: Future of Jobs Report 2025 (WEF, 01/7/25) at pg. 25 (“trends in AI and information processing technology are expected to create 11 million jobs, while simultaneously displacing 9 million others, more than any other technology trend.“)]

We must recognize, however, the uneven geography of adoption. As the article’s robotics example shows, access to “AI integrators” could determine regional economic divergence. Without policy scaffolding (training pipelines, local incentives), AI may exacerbate inequality.

Still, this is no mere displacement story. It is a diversification story, seeded with entrepreneurial possibility.

Fictitious vision of where new jobs may appear and old be replaced. Image by Ralph Losey using AI.

⚔️ The Contrarian

The panel indulges in optimism but skirts real constraints. “AI trainer”? Perhaps. But many orgs will under-invest in proper RAG or hallucination testing. “AI plumber”? Realistically, that’s a role for the already-employed IT person, not a new hire.

The legal take? Idealistic. In practice, AI auditors will lack statutory teeth unless regulation mandates it—and current efforts like the EU AI Act remain unenforced in key domains.

And “taste” as job defense? That’s privileged territory. It assumes stability in jobs where creative discretion is rewarded. But what of the displaced clerk, paralegal, or content writer who once did real intellectual work?

Lastly, from an ethical risk lens:

  • Bias: Are these new roles equally accessible? Or do they reinforce existing inequities?
  • Privacy: Will AI integrators mishandle sensitive data pipelines?
  • Regulatory: Could roles like “AI translator” mask liability via plausible deniability?

We risk over-indexing on shiny titles while ignoring structural frictions.

Contrarians tend to see the glass as half empty. Image by Losey.

Would you like to follow up, clarify, or pivot?


USER: Review each of the new jobs that the article mentions may be created by AI.

4o PANEL:

Here’s a comprehensive job-by-job breakdown of the new roles suggested in “A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You”. The article groups these under three themes: Trust, Integration, and Taste. I’ve organized the roles accordingly and added brief descriptions for each.

🛡 TRUST-Based Roles

Roles focused on ensuring transparency, accountability, and human oversight:

  1. AI Auditor
    Verifies what AI systems are doing, why, and whether outcomes meet legal or operational standards.
  2. AI Translator
    Bridges technical and business domains by explaining AI behavior and outcomes to non-expert stakeholders.
  3. Fact Checker (AI-Aided)
    Verifies AI-generated content for errors, hallucinations, and compliance issues.
  4. Compliance Officer (AI-Aware)
    Reviews AI-generated outputs in sensitive domains like law, finance, and health to ensure regulatory alignment.
  5. Trust Authenticator / Trust Director
    Ensures users can rely on AI-generated outputs, enforcing policies for fairness, accuracy, and traceability.
  6. AI Ethicist / Ethics Board Member
    Constructs defensible logic for decisions made by AI, ensuring ethical oversight and transparency.
  7. Legal Guarantor
    A licensed or certified person who legally vouches for AI-assisted work, assuming liability (akin to a “sin eater”).
  8. Consistency Coordinator
    Validates uniformity of AI output across systems (e.g., ensuring consistent product visuals or messaging).
  9. Escalation Officer
    Handles cases where AI fails emotionally or functionally—especially in customer service and education.
Buyer and seller must establish trust in robots to make sale. Combined styles in image by Losey.

🛠 INTEGRATION-Oriented Roles

Roles aimed at connecting AI capabilities to organizational workflows and technical systems:

  1. AI Integrator
    Designs and implements AI adoption strategies within specific business functions or verticals.
  2. AI Plumber
    Diagnoses and fixes errors in layered AI systems, often dealing with agentic or multi-step workflows.
  3. AI Assessor
    Continuously evaluates different AI models for specific uses (e.g., determining hallucination rates or performance drifts).
  4. AI Trainer (Domain-Specific)
    Feeds proprietary data into AI systems and fine-tunes model outputs for organizational accuracy.
  5. AI Personality Director
    Curates the “voice” and tone of an organization’s AI agents to match brand identity or customer expectations.
  6. Drug-Compliance Optimizer
    Uses AI to monitor and improve medication adherence—potentially in hospitals, insurance, or elderly care.
  7. AI-Human Evaluation Specialist
    Identifies tasks best suited for humans, AI, or hybrid approaches, especially in safety-critical industries.

🎨 TASTE-Driven Roles

Creative and strategic roles where human judgment and vision are irreplaceable:

  1. Product Designer (AI-Enabled)
    Expands beyond visuals to include brand strategy, user interaction, and narrative consistency, directing AI tools creatively.
  2. Article Designer
    Orchestrates content generated by AI—selecting structure, tone, and messaging across platforms.
  3. Story Designer
    In film, TV, or gaming, crafts the underlying plot or world that AI then fleshes out.
  4. World Designer
    Creates fictional or themed environments for marketing, gaming, or entertainment—used by AI to generate media.
  5. Human Resources Designer
    Shapes company culture, training, and employee experiences using AI-curated content and interfaces.
  6. Differentiation Designer
    Strategizes how a company distinguishes itself when competitors use the same powerful AI tools—aligning product, brand, and communication.
Steampunk taste team selected! Click to see celebration. Images, video by Losey.

Would you like me to visualize these 22 roles in a chart or cluster them by skillsets or industries?


USER: I would like the whole panel to discuss the “Sin Eater” job proposed by Wharton Business School Professor and noted AI expert, Ethan Mollick.

Ethan Mollick in Steampunk style by Losey.

USER: I would like the whole panel to discuss the “Sin Eater” job proposed by Wharton Business School Professor and noted AI expert, Ethan Mollick.

4o PANEL:

🎓 Ethical AI Lawyer — Legal and Normative Accountability

The “Sin Eater” role, as Mollick frames it, carries significant legal implications. It reflects the enduring legal doctrine that accountability cannot be delegated to a machine. In tort law, liability flows to the agent of record—currently, only humans or legal entities can occupy that role.

This aligns with precedents such as Mata v. Avianca Inc., where AI misuse led to sanctions because no human properly vetted its output. The sin eater, therefore, functions not just as a compliance actor but as a liability firewall, absorbing both reputational and legal risk.

But this framing raises concerns. Can one be a guarantor without actual authorship? If AI makes the decision and the sin eater merely signs off, we risk creating paper accountability. Regulatory models like the EU AI Act are moving toward traceability mandates, but as yet, U.S. law lacks statutory recognition of such roles.

In short, the sin eater concept is both legally plausible and ethically fraught—it acknowledges human limits while asking them to bear machine risk.

Sin Eaters will employ many lawyers. Image by Ralph Losey AI.

🧠 AI Engineer — Technical Risk ≠ Human Blame

From a systems view, the “Sin Eater” is a human checksum: the last human in the loop before AI action becomes irreversible. It’s a reactive model of risk management—and one that’s arguably too brittle.

We need better forward defenses, not just cleanup personnel. Sin eaters are useful when explainability fails or outputs are inherently opaque. But the real problem is epistemic opacity: even experts can’t always trace LLM decisions.

Instead, we should engineer auditable AI stacks, use differential logging, and isolate decision modules for forensic review. Relying on a human “approver” as a fix-all invites rubber-stamping, not real scrutiny.

And technically, sin eaters will need tooling—model trace maps, hallucination flags, metadata dashboards. Without this infrastructure, we’re just asking someone to trust what they can’t parse.

✨ Creative Storyteller — A Mythic Role, Made Literal

“Sin Eater” is such an evocative term because it draws from ritual and folklore. Historically, sin eaters consumed bread over a corpse, symbolically absorbing the sins of the dead. In this context, the sins are hallucinated citations, algorithmic bias, or wrongful denials.

That metaphor frames the sin eater as both guardian and scapegoat. They bear blame to protect the system’s perceived legitimacy. That’s powerful—but also dangerous. Mythic roles lack clear scope. Is the sin eater a validator? A fall guy? A moral compass?

We risk theatrical accountability: jobs that feel weighty but do little to prevent harm. The storytelling matters, because it shapes how we see responsibility. Are they heroes, martyrs, or cover-ups?

The role’s narrative weight is real, but it must be grounded in operational clarity.

Combined steampunk and medieval manuscript styles of historical Sin Eaters by Losey.

🛰 Data Visionary — Institutionalizing the “Last Human Standing”

Mollick’s metaphor reveals a deeper systemic truth: as AI scales, we need roles that enforce last-mile responsibility. The sin eater becomes the institutional locus of that burden.

In distributed systems, there’s a similar construct: the circuit breaker. When cascading failures occur, this mechanism stops the chain. The sin eater is a social circuit breaker. But who designs the thresholds? Who funds the liability insurance?

Scaling this requires:

  • Certification bodies to credential sin eaters
  • Policy frameworks (e.g., “AI final-signoff registries”)
  • Liability shields akin to whistleblower or auditor protections

Done well, this role could professionalize AI accountability, akin to CPAs or actuaries. But without those structures, it’s a fig leaf—blaming humans for systemic opacity.

Last Man Standing role shown in steampunk style by Losey. Only brave humans need apply for this job.

⚔️ The Contrarian

This entire discussion sanitizes an ugly reality: the sin eater is a liability sink, not a solution. It externalizes blame from the system designer to a human end-point. It masks architectural unaccountability.

And let’s check the ethical risk boxes:

  • Bias: Who becomes the sin eater? Likely junior, marginalized, or contractual workers—sacrificed for optics.
  • Regulatory: There’s no statute affirming this role. It’s an HR workaround, not a legal safeguard.
  • Hallucination: Will they detect model lies in high-stakes contexts (e.g., medical or legal reasoning)? Doubtful, unless they are domain experts.

In sum, the sin eater is not a visionary role—it’s institutional cowardice disguised as ethics.

Would you like to follow up, clarify, or pivot?

Nobody likes the contrarian lawyer. Steampunk image by Losey.

New Request to the Panel

USER: Each panelist should imagine and describe in detail an entirely new line of work for humans that will likely be created by AI. It should not come within the scope of the job types mentioned in the article.

4o PANEL: Let’s break new ground. Each panelist below proposes a novel, AI-enabled human job that was not covered in the NYT article. These roles are speculative yet grounded in emerging technological and social trajectories.

🎓 Ethical AI Lawyer — Probabilistic Liability Architect

As AI systems increasingly operate on statistical inference (rather than deterministic logic), courts and regulators will need new doctrines for “probabilistic harm.” Enter the Probabilistic Liability Architect.

This legal role designs frameworks to allocate risk and assign partial liability when AI systems cause harm but no single actor is clearly negligent. For example:

  • A predictive policing system misidentifies a suspect with 70% confidence.
  • An autonomous delivery drone injures a bystander during path optimization.

The architect would:

  • Quantify and model AI system confidence thresholds.
  • Define shared responsibility regimes across vendors, deployers, and auditors.
  • Draft model legislation and policy for AI tort reform.

This job combines legal theory, policy design, and statistical reasoning—making it a bridge between law and machine logic.

Steampunk image by Losey.

🧠 AI Engineer — Synthetic Interaction Architect

As LLMs evolve into multi-agent swarms, orchestrating their interactions will become a full-time role. The Synthetic Interaction Architect manages the interplay of dozens or hundreds of autonomous AI agents assigned to a complex task (e.g., planning an international supply chain or modeling a political campaign).

Key functions:

  • Configuring inter-agent protocols (who talks to whom, when, and how).
  • Monitoring emergent behaviors and pruning dysfunctional collaboration patterns.
  • Designing reward structures that simulate human incentive alignment (e.g., competition, consensus, escalation).

Think of this as managing a hive mind—an ensemble of AI intelligences operating like a virtual team. The architect ensures synergy, not chaos.

AI Interaction Architect conducting a swarm of interactive AIs. Shown on steampunk style by Losey.

✨ Creative Storyteller — Emotion Wrangler

As AI becomes increasingly conversational and emotionally fluent, it will sometimes simulate emotions better than it understands them. This creates the need for an Emotion Wrangler—a specialist who trains, tests, and fine-tunes the emotional accuracy and appropriateness of AI systems.

They would:

  • Script nuanced emotional arcs for AI in education, therapy, or customer service.
  • Conduct “empathy audits” to ensure AIs express concern, humility, or apology convincingly—but not manipulatively.
  • Design cultural calibration modules (e.g., how grief or politeness differs across geographies).

This job safeguards the emotional realism of AI while guarding against artificial affect that deceives or coerces.

Humans can feel emotions, AI can’t. Emotion Wrangler in steampunk style by Losey.

🛰 Data Visionary — Synthetic Ecology Steward

Generative AI is already creating simulated environments for science, entertainment, and climate modeling. The Synthetic Ecology Steward curates and manages these ecosystems as long-running simulations with economic, environmental, and ethical stakes.

Examples:

  • A virtual planet used for testing urban planning at planetary scale.
  • A simulated biosphere for biotech AI to evolve new proteins.
  • An economic microcosm for experimenting with new market policies or governance rules.

This steward oversees:

  • The ethical boundaries of simulation (e.g., are emergent sentient entities possible?).
  • Cross-disciplinary calibration (from physics to sociology).
  • Integration with real-world policy levers or educational systems.

The role marries design, governance, and philosophy at the frontier of synthetic reality.

Syn Ecology Stewart image by Visual Muse & Ralph Losey.

⚔️ The Contrarian — Moral Exit Facilitator

In the coming wave of AI-induced identity dislocation, some people will choose to opt out—not from society, but from systems that make them feel obsolete, surveilled, or coerced. The Moral Exit Facilitator helps these individuals ethically detach.

It’s not just a career counselor. It’s a combination of:

  • Data minimization advocate (helping users erase or obscure their digital footprint).
  • Self-sovereignty designer (tools for autonomy outside AI ecosystems).
  • Philosophical guide (navigating moral disengagement from pervasive automation).

The role critiques the system while enabling graceful withdrawal—offering humans a structured way to say: No, thank you.

Helping people get tech-free, escape AI addictions. Steampunk style by Losey.

Would you like these roles visualized in a chart or used to seed a scenario?


USER: “Seed a scenario?” Not sure what that means, so sure, go ahead and do that, seed a scenario.

4o PANEL: Great — “seeding a scenario” means I’ll take those new job ideas and embed them in a realistic future situation, crafting a brief scenario that explores how these roles might interact, conflict, or evolve. Think of it as a mini-future vignette for testing policy, tech, or narrative ideas.

🌍 Scenario Seed: “The Eden Loop Disruption”

📅 Year: 2031

🧭 Setting: A high-fidelity AI simulation called Eden Loop, used globally for climate-risk modeling, educational immersion, and synthetic biodiversity experimentation.

Steampunk image by Losey using Visual Muse.

Something goes wrong in the Eden Loop and each of the new human roles worked together to deal with the problems. Dealing with the hypothetical would be interesting in a role-play type workshop, but not for this essay.

Conclusion

History tells us that all technology breakthroughs cause disruptions to existing society, and all put some people out of work, at first, but overall, they always create more new jobs than they destroy. There is no reason to think it will be any different this time with AI. And there are many reasons to think the new jobs created will be far more interesting, creative and enjoyable than the jobs lost. It may even change the negative meaning that comes with the word work for most people. Work will have far fewer boring drudgery tasks because that will all be done by the robots. Work and play may become synonymous.

Image of AI doing the hard dirty work while humans do the fun jobs. By Ralph Losey with his AI doing the boring drawing parts.

In the article that ChatGPT 4o version of the Panel of Experts found, Future of Jobs Report 2025 (WEF, 01/7/25), the World Economic Forum predicted a significant shift in how both humans and machine work will change. In 2025 employers reported 47% of work tasks are performed by humans alone, 22% by machines and algorithms alone, and 30% by a hybrid combination. By 2030, employers expect these task-delivery proportions to be nearly evenly split across all categories: one-third human only, one-third machine only and one third hybrid.

The World Economic Forum report explains that this is only a task-delivery proportionality measurement, it does not take into account the amount of work getting done in each of the three task categories. The Future of Jobs Report 2025 at page 27 goes on to state:

The relevance of the third category approach, human-machine collaboration (or “augmentation”) should be highlighted: technology could be designed and developed in a way that complements and enhances, rather than displaces, human work; and, as discussed further in the next chapter (Box 3.1), talent development, reskilling and upskilling strategies may be designed and delivered in a way to enable and optimize human-machine collaboration.34 It is the investment decisions and policy choices made today that will shape these outcomes in the coming years.35

Hybrid Man and Machine New Jobs Report is looking good. Image by Losey in Steampunk style

The global employers polled favored a hybrid approach, as did the World Economic Forum expert analysis. Generative AI requires human supervision now and certainly for the next five years. To again quote the WEF Report, at the mentioned Box 3.1 at page 44:

Skills rooted in human interaction – including empathy and active listening, and sensory processing abilities – and manual dexterity, endurance and precision, currently show no substitution potential due to their physical and deeply human components. These findings underscore the practical limitations of current GenAI models, which lack the physicality to perform tasks that require hands-on interaction – although advances in robotics and the integration of GenAI into robotic systems could impact this in the future.

After that, as the AI skills improve, there will in our opinion and that of the WTF, still be a need for human collaboration. The need and human skills required will change but will always remain. That is primarily because we are corporal, living beings, with emotion, intuitions and other unique human powers. Machines are not. See my essay, The Human Edge: How AI Can Assist But Never Replace (1/30/25). Even if Ai were to someday become conscious, and have some silicon based corporality, perhaps even a kind of chemical based feelings, it would need to work with us to gain our unique human feel, our vibes and our evolutionary connection with life on Earth. Real life in time and space, not just a simulation.

Factory floor with cool AI features in steampunk style. Click here to see video by Losey.

PODCAST

As usual, we give the last words to the Gemini AI podcasters who chat between themselves about the article. It is part of our hybrid multimodal approach. They can be pretty funny at times and have some good insights, so you should find it worth your time to listen. Echoes of AI: Panel of Experts for Everyone About Anything – Part Three: Demo of 4o as Panel Driver. Hear two fake podcaster talk about this article for 18 minutes. They wrote the podcast, not me. For the first time we also offer a Spanish version here.

Click here to listen to the English version of the podcast.

Ralph Losey Copyright 2025 – All Rights Reserved.


Henry Kissinger and His Last Book – GENESIS: Artificial Intelligence, Hope, and the Human Spirit

June 19, 2025

Ralph Losey. June 19, 2025.

Henry A. Kissinger co-wrote his last book at the age of 100 with tech giants Eric Schmidt and Craig Mundie. Genesis makes clear that what we do next with AI could be our greatest triumph or our gravest mistake. Here I review the book and, to the extent necessary, the legend behind it, Henry Kissinger.

Henry Kissinger’s Genesis was published posthumously in late 2024. He had great technical help and was prodded to write the book by his two co-authors: Eric Schmidt, the former CEO of Google, and Craig Mundie, the former Chief of Research at Microsoft. They both knew Kissinger well before starting to write the book with him, which at age 99, they all knew would be his last. This is Kissinger’s second book on AI with Eric Schmidt. His first was published in 2022 entitled, The Age of AI: And Our Human Future, with another co-author, Daniel Huttenlocher, a Professor and Dean at MIT.

Like many, I had mixed feeling about Henry Kissinger from his work for Nixon and the Vietnam War, but still I was persuaded by Eric Schmidt’s many videos to give Genesis a try. Schmidt has been tirelessly promoting the book and the strategic insights Kissinger has on AI. He even created a slick promotional video for Genesis that uses an AI enhanced voice speaking Kissinger’s own words (suggest you click on it now to prep for my all-too-human book review). Also see, Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger (Nixon Foundation, 3/5/25) (more personal details on Kissinger than any of the dozens of other Schmidt interviews).

AI generated image in style of elder Kissinger. All images in the article are by Ralph Losey using AI (except the two public domain photos noted).

In the Nixon Foundation video Schmidt states that Kissinger was the leader in the writing and editing of Genesis and that Henry was very meticulous and dedicated to it. Id. at video 27:46. Henry finished the last chapter the week before he died on November 29, 2023. Id. at video 35:50. At the same time he was writing Genesis, Kissinger was co-authoring an article with his diplomatic colleague, Graham Allison. The Path to AI Arms Control: America and China Must Work Together to Avert Catastrophe, (Foreign Affairs, 10/13/23). Yes, at the end of his life Henry Kissinger was focused on the power, promises and severe dangers of AI, including the danger of war with China posed by possible superintelligence.

Having now read the book I can well understand why Schmidt is urging everyone to read Genesis. We are living in dangerous times where strategy and diplomacy are more important than ever. Henry Kissinger’s last book is a red flag, outline of solutions and a beacon of hope. I am happy to recommend it.

Schmidt and Kissinger meeting with government officials in Beijing. Real meeting, fake AI image of it by Losey.

Kissinger’s Inside Briefings About AI

Schmidt went on to share in the Nixon Foundation video that he and introduced Kissinger to both Demis Hassabis and Dario Amodei. Henry became friends with them and had many in-person and zoom conversations. Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger, video at 29:30.

With their help, and that especially that of Schmidt and Mundie, Kissinger came to understand that AI involved the Midas Touch archetype, not only for its profitability, but as a warning to be careful what you ask for. Our dream of superintelligent AI, one well beyond our comprehension, could easily become a nightmare. Genesis, in Kissinger’s words, “examines what AI means to humanity and explores solutions to the challenges it poses.

AI Image of Hassabis, Amodei, Schmidt, Kissinger.

In fact, Eric tells the story of when Kissinger asked to test out Dario’s latest AI models. Amodei told Henry to come up with a prompt, a question, which he did: “Design a new religion that will spread rapidly in today’s age.Id. at video 30:00. Kissinger was blown away by the AI’s detailed response and plan of action. Schmidt says it was that demonstration that caused Kissinger to understand fully, for the first time, the power of the AI revolution underway. Henry had some hands-on AI experience and that drove him, as it does me, to think and write about it obsessively.

AI image of Henry writing about AI and religion. Who would expect he’d do that at age 100 just before he passed away?

I thought it would be fun to run the same prompt on OpenA’sI new model, o3 Pro, released on 6/12/25. OpenAI states that o3 Pro is its best model for reasoning. It is certainly far ahead of the Anthropic AI that Kissinger used a few years ago. It took o3 Pro thirteen minutes and two seconds of reasoning time before it responded. That is a very long time for AI, which thinks millions of times faster than we do. In the end, it did figure out how to create a new, very appealing religion.

In fact, like Kissinger before me, I was blown away by its frighteningly well considered plan. The religion proposed is called “Synterra Path – a mash‑up of syn (“together”) and terra (“earth”).” You can see the full eleven point plan for yourself in the attached transcript, which does not include the extensive sources that o3 Pro also provided. Please do not attempt to implement the plan for Synterra Path, which is already underway, or the AI lawyer agents will file suit.

The new AI religion where Kissinger is the prophet who asked AI first. Try Henry’s prompt yourself!

Genesis Is a Short Book by Kissinger Standards

At 218 pages Genesis is a short read, but to be honest, not an easy read. It takes concentration. The AI parts are fairly easy and beautifully explained but the complex Kissinger strategy and philosophy parts are more difficult. Those Kissinger insights are also what make Genesis a must read for anyone trying to understand the AI Age.

The book is very short by the standards of Henry Kissinger. He is famous for many things, but one you might not have heard of is the controversy surrounding his undergraduate, senior paper at Harvard in 1950, The Meaning of History: Reflections on Spengler, Toynbee and Kant. This paper caused Harvard to start a 35,000 word limit rule for senior papers that stands to this day. You see the paper young Henry, shown below, submitted to his professors was over 400 pages long!

Kissinger in 1950 Harvard Yearbook, public domain.

Young Kissinger did not talk much. Instead, he wrote and wrote. A few years after his senior paper fiasco. Harvard gushed to read his Ph.D. thesis: Peace, Legitimacy, and the Equilibrium (A Study of the Statesmanship of Castlereagh and Metternich. It won many awards and led to Harvard making him a professor. His word generation skills were equal to or exceeded the best generative AI of today.

At the end of his life Kissinger was still writing. He somehow crammed his one hundred years of insights into the 218 pages of Genesis. So admittedly, it is a challenging read, and yes, it would take about 400 pages for my AIs and I to totally unpack it, but don’t worry, that’s not happening. Ask your AI to do it. Hopefully it understands statesmanship, Henry Kissinger and Immanuel Kant.

AI image of Kant and Kissinger.

Henry Kissinger in WW II

To understand the book more information about Kissinger’s formative years is required, the years before he became famous as a Harvard professor, Richard Nixon’s National Security Advisor, Secretary of State, and controversial Nobel Peace Prize winner. You need to understand first of all that Kissinger was born and raised in Germany in a Jewish family where he suffered persecution as a boy. As a teenager in 1938, his parents and younger brother were among the lucky few to escape Nazi Germany and immigrate to America.

Henry was drafted into the Army 1943 and, while in training camp in Camp Croft, became a U.S. citizen. He was then shipped to France as a private, and since he was obviously smart and spoke German, was assigned to an intelligence unit. Young Henry Kissinger saw combat right away as a kind of spy at the front lines. He even volunteered for hazardous intelligence duties during the Battle of the Bulge.

On April 10, 1945, at age of 21, Henry participated in the liberation of the Hannover-Ahlem concentration camp, part of the Neuengamme concentration camp. At the time, Kissinger wrote in his journal, “I had never seen people degraded to the level that people were in Ahlem. They barely looked human. They were skeletons.Isaacson 1992, pp. 39–48. For more details and photos see Henry Kissinger’s World War II (Warfare History Network, June 2018). Both Eric Schmidt and I think this was a turning point in his life.

AI generated image of liberation of concentration camp with young Kissinger on the far right.

Kissinger was relatively silent about his wartime service. In fact, he rarely spoke at all as a boy and young man. ‘Too shy‘ is what they called it back then. Can you imagine what it must have been like for a young Jewish man on the spectrum to walk into a Nazi concentration camp in his home country? He saw people, his people, barely alive; prisoners who had been treated at dirty things, with no human dignity or respect for their life at all. He turned to the German philosopher Immanuel Kant for comfort of sorts and, according to his friend, Eric Schmidt, decided at that time to dedicate his life to a “higher purpose” of preventing the horrors of war. Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger, video at 19:30.

According to Kissinger’s biographer, Walter Isaacson, Henry never lost his strong German accent because he suffered from extreme shyness as a child and that made him hesitant to ever speak. Isaacson, Kissinger: A Biography (Simon & Schuster 1992). It remained a very strong accent his whole life. Eric Schmidt tells the story that despite Google’s best efforts, neither the German nor English language AI could understand his speech well enough to transcribe it. Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger video at 12:12.

As the War against Germany ended, and after the shock of seeing near death prisoners released from a Jewish Concentration Camp, Kissinger was assigned to the Counter Intelligence Corps (CIC), where he became a CIC Special Agent. Henry quickly received a field promotion to sergeant and was put in charge of a team in Hanover Germany tracking down the hated Gestapo officers and saboteurs. Once discovered they were tried, imprisoned or hanged. After seeing a concentration camp, that must have been satisfying work for Kissinger. He was awarded a Bronze Star for his service.

AI image of what Kissinger might have looked like as a U.S. Army intelligence agent hunting Gestapo intelligence agents. Click here to me my AI video visualization of his work. Upcoming Netflix series?

In June 1945 he was promoted again and made commandant of the Bergstraße district of Hesse Germany, with responsibility for denazification of the district. In 1946, Kissinger was reassigned to teach at the European Command Intelligence School at Camp King in Germany. He continued to teach there as a civilian employee following his separation from the army. Kissinger later recalled that his experience in the army “made me feel like an American.” Isaacson. Kissinger. p. 695.

Kissinger’s Kant, AI, Inherent Dignity and Dogs

Obviously, the deep thoughts of this legend impressed and influenced his co-authors, Schmidt and Mundie. They are elite tech scientists and businessmen who readily admit to having had no time in their past for social studies. Henry Kissinger’s politely viewed them as one-dimensional scholars, not fully educated. Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger video at 18:40 (“technology people don’t understand history, people, social dynamics, politics“). They were not polymaths with great interdisciplinary knowledge like Kissinger, they were just trained in a science/math bubble. For that reason, Kissinger told Schmidt that he “should not be in charge of anything. Id.

That’s a kind of funny thing to say to the former CEO of Google and one of the most successful business leaders of our day. Surprisingly, Schmidt agreed with Kissinger, saying “it would be nice if there were more than just the tech people making these decisions.” Id. I wholeheartedly agree, and so does Eric Schmidt, one of the richest people in the world ($32 Billion), but as Schmidt pointed out to Kissinger, that is not likely in profit driven companies.

Kissinger learned from talking to the lead technology people that they did not understand psychology, international law, geopolitics, diplomacy, warfare, history, or philosophy, much less Kissinger’s favorite, the notoriously difficult Immanuel Kant (1724-1804) and Kantian ethics. Lucky me, I was forced to study Kant while studying philosophy in Vienna. Immanuel is generally considered to be the greatest German philosopher. Immanuel Kant believed that all humans have the right to common dignity and respect. It was part of his famous categorical imperative that humans must never treat others merely as a means to an end, but always as ends in themselves. This is the opposite of what many people in fact think and do, especially the Nazis that Henry fought.

Kissinger puzzled over whether AI might someday deserve this dignified treatment. Right now, we treat it as a tool, a pet we control. That’s appropriate now, but what happens when it’s smarter than we are? Could the tables then be turned? Kissinger worried about that too, that AI might someday advance so far as to rob humanity of its dignity. Maybe we would someday be the less intelligent beings on a leash, the spoiled pets of super advanced AI.

Pampered rich human taken for a walk by his AI owner.

This is fate some people might welcome, especially a dog lover like me, but not Henry. I kind of doubt he ever had time for a dog. As Schmidt puts it, and I paraphrase, it is important that when we are no longer the smartest beings on Earth, that we control our masters better than dogs control us. Again, I suspect Schmidt has not spent much time with dogs either, at least not ones like mine that seem pretty good at controlling their owner. Beam me up for a walk on the moon please AI master, I’m bored

Pet human likes all the great things his AI owner does for him, like perfect health and beaming up for a walk on the Moon.

This Kantian ethical view of human dignity influenced the thinking of Kissinger on a variety of AI topics discussed in Genesis. See for instance Genesis at page 205:

As a starting point we would encourage a definition of dignity. . . . Without a definition of dignity, we would not know if and when AI, given enough faculties, could become a being of dignity, could stand fully in place of a human, or could be entirely unified with a human. An AI, even if sustainably proved to be not human, might instead constitute a member of a separate, similarly dignified category that would nonetheless deserve its own, equal standard of treatment.

[We] encourage inclusive coexistence with AI while avoiding reckless attempts as premature coevolution.

For these reasons the authors conclude at page 207: “that humans retain and exercise the power of conscious choice in the age of AI.” The authors say we must be free and not let AI control us, no matter how attractive the much loved, pampered pet role may seem.

This AI is so nice to her pet human. He doesn’t seem to mind.

Genesis on Managing Emergence of Superintelligent AI

The authors go beyond intellectual discussion and take positions on several issues, and when they do so, take pains to use words such as “we believe.” This confirms this is a key issue they discussed at length. One such topic is “AI emergence” in Chapter 5 on Security.

We believe there will not be just one supreme AI but rather multiple installations of superior intelligence in the world. . . . Our strongest creations, acting as countervailing forces, could be better equipped than humans to exert and maintain an equilibrium in global affairs, inspired (but not constrained) by human precedent. Non-human intelligence could thus manage its own emergence, at least in the realms of national security and geopolitics. . . .

No doubt, it is a risk for AI to assume early and sustained responsibility for the species and societies behind its own conception, but the traditional pathways, which require perfection in human performance, may be even riskier. Best, in our current view, would be to have AI working before, and not after, humanity has to confront the proliferation of new threats to survival. The appropriate question under this assumption is this. How can humans accelerate only desirable pathways for AI while delaying the undesirable?

We believe that in diplomacy, defense, and perhaps elsewhere, some of the risks of AI can be managed successfully only by AI itself. . . .

This is one especially poignant instance of the dilemma of dependence—and subsequent perceived inferiority—explored in an earlier chapter. But, in the case of our security, unlike that of our displacement in scientific or other academic endeavors, we may more readily accept the impartiality of a mechanical third party as necessarily superior to the self-interestedness of a human—just as humans easily recognize the need for a mediator in a contentious divorce. It is our belief, and hope, that in this case some of our worst traits will enable us to exhibit some of our best: that the human instinct towards self-interest, including at the expense of others, may prepare us for accepting AI’s transcendence of the same.

Genesis pgs. 120, 124, 135-136.

Henry Kissinger had personal experience of the superiority of AI in some fields. For instance, Schmidt says that Kissinger, whom he calls the greatest diplomat in the world, naturally liked to play the board and video game of Diplomacy, and he found that the AI systems could play as well as he could. Eric Schmidt on AI, Foreign Policy, and working with Dr. Henry Kissinger video at 25:00.

Henry Kissinger loses again to the little AIs and doesn’t like it.

Genesis on the Problems and Pleasures of Prosperity

On Chapter Six on Prosperity, “the authors of this book believe that AI could conceivably be harnessed to generate a new base-line of human wealth and well-being.Id. at 148. I for one am glad to see they all agreed on that.

They also agree on a few basic worries and likely outcomes pertaining to prosperity: “We do worry that a great fraction of humans could become primarily passive consumers of AI-generated content.” Id.

Just relax, sit back and enjoy it. What kind of life is that?

Kissinger and friends then go on to observe in Genesis:

Our concern about human passivity is not about the human loss of paid work. We already have a prototype of how people live when they can have what they want without working. We call them the rich and the retired. . . .

The adjustment to abundance is likely a problem of transition rather than a permanent challenge. Some will initially perceive the introduction of machine labors as depriving them of their primary source of fulfillment and joy. No doubt this will be a jarring experience. But to us it seems likely—not as a response to our exhortation, but rather as an outgrowth of human instinct—that, given time, humans would choose to persevere, perhaps in new avenues or as partners of AI, avoiding atrophy and instead excelling as thinkers and doers. Ultimately, if we establish the needed systems for distribution, connection, participation, and education, humans–empowered and inspired by AI–may continue working not for pay, but for pleasure and pride.

Id. 158-159

Better image of AI as partner and coach.

Key Question of Genesis:
Will we become more like them, or will they become more like us?

On Chapter Eight on Strategy, a key question that was introduced in earlier chapters is resolved, at least somewhat, by the authors agreement on the best answer.

To our minds, one question must define our human strategy in this new age of reckoning. That question is this: Will we become more like them, or will they become more like us?

Id. 184-185

The authors then discuss possible redesigns of the human form, including implants and DNA alterations, so we could be more like them. Fortunately, they agree that “extreme self-redesign may not be necessary and is anyway “generally undesirable.” They point out that:

‘Upgrading’ ourselves biologically might backfire to become a greater limitation on ourselves. . . . If we are unwilling or unable to become more like them, we must, while we are able, find ways to make them more like us. Towards this end, we need to apprise ourselves more fully not only of the essential and evolving nature of AI but also of humanity’s own nature, and we must attempt to encode these understandings in our machines. If we are to entwine ourselves with these non-human beings, and yet retain our independent humanity, these efforts are essential.

Id. at 190. I concur with their opinion. Know thyself.

Create AI in alignment with your higher self.

The Book’s Conclusion

The concluding paragraphs to Genesis at page 218 are clear, accent free, and very well written. They represent the last few days of the writing and life of Henry Kissinger. These words ring the bell for a new beginning for all mankind:

Neither blind faith nor unjustified fear can form the basis of an effective strategy; one needs self-doubt to have knowledge, but self-confidence to act. Indeed, in the age of AI, this is all the more urgent. We must try to understand the challenges that AI will present even as we lack the prior exposure or the essential experience to guarantee the accuracy of our comprehension. And even as we navigate this daunting task, we must also, to avoid a passive future, surmount the many difficulties already facing our species.

While some may view this moment as humanity’s final act, we perceive instead a new beginning. The cycle of creation—technological, biological, sociological, political—is entering a new phase. That phase may operate under new paradigms of, among other things, logic, faith, and time. With sober optimism, we may meet its genesis.

Click here for intro to a Losey movie on a new AI paradigm of logic, faith, and time. Here’s another, The cycle of creation.

My Conclusion: Impressive Man, Impressive Book

I was impressed by the young Henry Kissinger who overcame severe handicaps, including being Jewish as a boy in Nazi German, escaping as an immigrant in a strange land, joining the U.S. Army, and then, a few years later, fighting on the front lines as an intelligence scout, helping liberate a concentration camp, and then hunting down and prosecuting Gestapo criminals.

I was impressed by Kissinger’s intellectual curiosity and breadth of knowledge, which caused his technology co-authors to label him, in awe, a polymath.

I was in awe of Henry’s relentless writing outlet that continued to the last few days of his very long, one-hundred-year life. Physically spent but mentally as sharp as a tack. Incredible.

I was impressed by Kissinger’s unique insights and warnings about the impact of AI on humanity, both psychological and geopolitical.

Finally, I was impressed by Henry Kissinger’s hope, which I share, about the great potential for good of an ethically aligned, superintelligent AI, and the chance, if we work hard, that it will help humanity to achieve a far better future.

AI using propaganda poster art style.

As usual I provide an AI podcast where two young techie AIs share their slant on things. Echoes of AI: Henry Kissinger and His Last Book – GENESIS: Artificial Intelligence, Hope, and the Human Spirit.” Two Google Gemini AIs generated a 16-minute podcast talking about this article. They wrote the podcast, not me. 

Ralph Losey Copyright 2025. All Rights Reserved.


Power Meets Platform: Legal Lessons from the Trump–Musk Dispute

June 9, 2025

By Ralph Losey. June 9, 2025.

Disclaimer & Purpose: This article is offered for educational discussion only. No endorsement or disparagement of any individual is intended. The goal is to illuminate emerging points of law where public authority meets private techno‑sovereignty.

Visual Allegory: Imagine Trump‑Kong squaring off against Musk‑Godzilla atop a smoldering volcano. The image is meant in respectful fun—an allegory for colossal forces testing modern legal frameworks.

All images and videos in this article are by Ralph Losey using AI tools. Like most techies, Kong and Godzilla are two of Losey’s favorite superheroes.

Why This Dispute Matters

The public sparring between President Donald J. Trump and entrepreneur Elon Musk is more than celebrity drama. It exposes structural tension between public authority and the private platforms that now shape global infrastructure and discourse. Their quarrel touches seven legal fault lines every lawyer, policymaker, and technologist should watch. These will be described here as we observe a new kind of chess game unfolding between two grand masters.

A Strategic Power Play

What began as a political bromance in 2017 evolved into open conflict after a series of public barbs. Musk criticized trade and climate policies; Trump hinted at cutting lucrative launch contracts. The clash fuels partisan passions—but behind the spectacle lies a constitutional stress‑test played out on social media amplified by AI.

Beyond Ego: A New Battle Over Sovereignty

When a single private actor commands satellites, rockets, electric grids, AI, and a megaphone reaching hundreds of millions, the traditional checks on concentrated power blur. Our legal system—built for railroads and rotary phones—must redraw the lines between public interest and private empire.

Musk as Archetype: The Sovereign Technologist

Musk’s vertical integration—rockets, satellites, cars, AI labs—embodies a modern platform sovereign. As The Guardian observed, “Handing the keys of planetary infrastructure to a handful of billionaires is a dangerous gamble.” Nick Robins-Early, The Trump-Musk feud shows danger of handing the keys of power to one person (6/7/25). Yet Musk’s innovations also slash launch costs and accelerate EV adoption, illustrating the dual edge of private leadership.

Seven Legal Lessons

1 — Privatized Infrastructure & National Dependence

Starlink’s frontline use in Ukraine showed the upside of commercial networks—but Musk’s hint he could “turn it off” awakened Congress to a single‑point vulnerability. Redundancy mandates under the Defense Production Act and competitive‑procurement clauses are gathering bipartisan support.

2 — Blurred Lines: Public Roles & Private Gain

Federal ethics laws, like 18 U.S.C. § 208, prevent officials from acting on matters affecting their financial interests. Musk’s simultaneous role as SpaceX CEO and unpaid federal adviser on space policy stretched that framework. Stronger recusal and disclosure standards are under debate.

3 — Retaliatory Contract Cancellation & the First Amendment

Government may not cancel contracts to silence speech (see Board of Comm’rs, Wabaunsee Cty. v. Umbehr, 518 U.S. 668 (1996)). Allegations that Trump weighed launch budgets against Musk’s criticism raise viewpoint‑retaliation red flags. Peter BakerTrump’s Feud With Musk Highlights His View of Government Power: It’s Personal (NYT Opinion, 6/8/25).

4 — Private Forums, Public Impact

In  Moody v. NetChoice, LLC and NetChoice, LLC v. Paxton, 603 U.S. 707 (2024), the Supreme Court affirmed private platforms’ have editorial discretion protected by the First Amendment,and states cannot compel them to host speech they would prefer to exclude. Also see: Trump v. Twitter, Inc., 602 F. Supp. 3d 1213 (N.D. Cal. 5/6/22) (Twitter is a private entity, not governmental, and so President Trump’s First Amendment rights were not violated when he was banned). 

5 — Section 230 Reform: Scalpel, Not Sledgehammer

Critics say platforms should lose Section 230 safe harbor when algorithms amplify harmful content; defenders call § 230 a backbone of online free expression. Draft bills now focus on narrow carve‑outs for paid promotion or deepfakes rather than full repeal.

6 — Federalism & AI Governance

President Trump’s call for a 10‑year moratorium on state AI laws collided with Musk’s plea for agile regulation. A layered approach—baseline federal standards plus state innovation zones—may offer balance. See: Anthropic C.E.O., Dario Amodei’s recent opinion essay on need for some federal regulation, Don’t Let A.I. Companies off the Hook (6/5/25).

7 — Digital Sovereignty as National Security

Allied governments fear U.S. firms hold strategic “kill switches.” Expect growth in data‑localization mandates and consortium models that dilute single‑point control. Understanding European tech sovereignty: Why Europe is taking back control (HiveNet, 3/12/25).

From Spectacle to Structure

Legal systems built for an analog era are stress‑testing against hybrid actors who command code, capital, and charisma. This feud is a teaching case for future statutes that channel private ingenuity without ceding public accountability.

Action Items for the Legal Profession

  • Master AI literacy (prompt engineering, algorithmic auditing).
  • Write redundancy clauses into government‑tech contracts.
  • Advocate balanced § 230 reform instead of blanket repeal.
  • Strengthen public‑private ethics rules.
  • Monitor digital‑sovereignty laws to ensure cross‑border compliance.

Closing Thoughts

This dispute isn’t merely a tale of clashing egos or partisan spectacle—it is a vivid demonstration of legal lag. Democratic institutions engineered for an analog age are now colliding with empires built on code, capital, and charisma.

For the legal profession, the implications are urgent. This moment requires proactive engagement: architecting ethical guardrails for AI, demanding transparency in algorithmic decision‑making, and crafting standards as dynamic and decentralized as the technologies they seek to govern. Prompt engineering must become a core element of legal literacy; AI outputs deserve the same scrutiny we once reserved for contracts and statutes. Sovereignty, once confined to the nation‑state, now resides equally in APIs and datasets.

We need not fear AI—we must govern it. Used wisely, generative systems can illuminate policy fault lines and help safeguard traditional American freedoms. By wielding the gavel of AI, we can forge the next generation of hybrid lawyers—super‑charged with computational insight and grounded in constitutional values.

Click here to see image of making of next gen lawyers. YouTube by Losey.

Ralph Losey Copyright 2025. — All Rights Reserved.