by Ralph Losey, July 16, 2025.
This is a continuation of the article, Panel of Experts for Everyone About Anything – Part One. Here in Part Two we give a demonstration of the software described in Part One. In the process we learn about new job types emerging from AI, including one envisioned by my favorite Wharton Professor, Ethan Mollick. He predicts a new job for humans required by the inevitable AI errors, which he gives the colorful name of Sin-Eaters. I predict the best of these Sin-Eaters will be lawyers!
Demo of Software
Below is an example of a consult with the Panel of Experts for Everyone About Anything. It was created using the June 26, 2025, version of the Panel. It demonstrates the Panel’s ability to analyze and discuss a document the user uploads. As Part One explained, the Panel software can do a lot more than that, but the task here is so interesting because the article topic is so hot and hopeful, about new jobs coming our way!
When read the output of the Panel AIs, note the Contrarian always tends to support the generic advice to speak to a human expert before reliance. The Contrarian’s input is always very helpful, but still, the input of this grumpy AI can be wrong too.
NYT Article on Future of Work
The document I selected for Panel discussion is a NYT Magazine article: A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You. In a few key areas, humans will be more essential than ever. It was written by former Wired editor, Robert Capps, and published on June 17, 2025. I have a NYT subscription and so could read it, and include a few fair use quotes, but I cannot share it with you due to copyright. I can also provide my synopsis and short analysis and then ask for a discussion of the article by our Panel of Experts for Everyone About Anything.
Capps’ article, written in typical NYT’s smart-alecky style, explores the core question of our times: what distinct human roles will persist or emerge as AI reshapes work? Overall I liked the article; it was well researched and thoughtful (reader comments were interesting too). Near the beginning Capps’ opines:
It’s already clear that A.I. is more than capable of handling many human tasks. But in the real world, our jobs are about much more than the sum of our tasks: They’re about contributing our labor to a group of other humans — our bosses and colleagues — who can understand us, interact with us and hold us accountable in ways that don’t easily transfer to algorithms.
A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You. I agree with this sort-of-deep point.
Capps’ research into the question of the new type of work that will likely emerge include interviews or quotes of these great sources (in order of appearance in article):
- Robert Seamans, NYU business school Professor. Primary source, one that Capps interviewed.
- Erik Brynjolfsson, Stanford Institute for Human-Centered Artificial Intelligence and founder of Workhelix.
- Ethan Mollick, Wharton School of Business Professor (one of my personal favorite AI experts).
- Daniel Susskind, economist at Oxford, etc.
- Sal Khan, founder of Khan Academy (another personal favorite).
- Aneesh Raman, Chief Economic Opportunity Officer at LinkedIn.
- Rick Rubin, record producer, quote from 60 Minutes interview of Rubin. (another favorite, reading his book now.)
I like how Robert Capps divides the new employment opportunities into three categories: trust, integration and taste. Here is his introduction:
If we want to know what these new opportunities will be, we should start by looking at where new jobs can bridge the gap between A.I.’s phenomenal capabilities and our very human needs and desires. It’s not just a question of where humans want A.I., but also: Where does A.I. want humans? To my mind, there are three major areas where humans either are, or will soon be, more necessary than ever: trust, integration and taste.
A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You.
1st Demo: Panel Discussion
For this demonstration I chose to use the OpenAI model 4.5 (research preview) that OpenAI says is good for writing and exploring ideas. It requires a Team subscription, which I have. I used this supposedly advanced model instead of the current default and free version, ChatGPT 4o. In Part Three I will ask the same questions using the 4o version and you can see the key differences and somewhat different insights provided.
[Note: images and links below were all added by Losey, the words are a full quote of the session.]
USER: Provide a panel discussion of the file uploaded herewith, A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You.
4.5 PANEL: Here’s the proposed expert panel to analyze and discuss the article “A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You”
Panel Composition:
- 🎓 Ethical AI Lawyer (Aligning innovation with ethics and legality)
- 🧠 AI Engineer (Analyzing technical feasibility and challenges)
- ✨ Creative Storyteller (Exploring cultural narratives and creative implications)
- 🛡 Risk Officer (Highlighting regulatory, governance, and compliance concerns)
- ⚔️ Contrarian (Critically examining underlying assumptions)
🎓 Ethical AI Lawyer – Legal & Ethical Implications
The article compellingly highlights new professional roles driven by AI adoption. Key roles like “AI auditors” and “AI ethicists” stand out, as accountability remains a fundamental human requirement in AI-integrated systems. From a legal standpoint, roles like “legal guarantor” and “trust authenticator” are particularly crucial, given precedents like Mata v. Avianca Inc., which emphasizes accountability for AI-generated misinformation. The emergence of these roles aligns closely with evolving frameworks like the EU AI Act, which emphasizes transparency and human oversight in automated decision-making processes.
🧠 AI Engineer – Technical Viability and Challenges
The author accurately pinpoints that “AI integrators” and “AI trainers” will become indispensable, reflecting current market realities where roles like “AI Engineer” and “AI Consultant” are rapidly expanding. Tools like Relativity Aero AI and OpenAI Code Interpreter already illustrate the growing technical ecosystem supporting such jobs. Yet, the potential complexity in managing AI consistency and integration across systems poses significant technical hurdles—highlighted by the need for roles such as “AI plumbers” and “consistency coordinators.”
✨ Creative Storyteller – Cultural and Creative Dynamics
This article rightly emphasizes how taste and creative decision-making roles, such as “story designer” and “A.I. personality director,” will flourish. Rick Rubin’s anecdote powerfully underscores the shift from traditional technical skill toward nuanced human judgment and style. This shift could democratize creativity and innovation, allowing broader participation in traditionally expert-driven fields, reshaping cultural narratives significantly.
Rick Rubin, famous hip-hop producer, real quote, but fake image of Rubin (looks close to me) by AI under my guidance. See Rubin’s 2025 book: The Creative Act: A Way of Being.
🛡 Risk Officer – Regulatory and Compliance Risks
The proposal of new roles such as “trust authenticator,” “AI auditors,” and “AI ethics boards” underscores key compliance and governance imperatives. These positions directly respond to requirements embedded in frameworks like GDPR’s Article 22, which mandates transparency and human oversight in automated decision-making. Ensuring compliance with such frameworks will require vigilant and proactive roles dedicated to overseeing AI operations, particularly in high-stakes areas like healthcare and financial services.
⚔️ The Contrarian – Critical Examination and Ethical Risks
While the optimism about new AI-driven jobs is understandable, there is a problematic assumption that roles involving human accountability and taste can fully mitigate deeper risks of AI adoption. The article’s approach neglects scenarios where human oversight becomes superficial, serving more as a liability shield than genuine oversight. Additionally, it sidesteps ethical dilemmas like potential bias and accountability diffusion, a significant concern given historical examples of algorithmic harm and privacy violations. Per the Ethical Risk Checklist, more robust discussions around bias, privacy, and hallucination risks are necessary.
Would you like to follow up, clarify, or pivot?
The insights and perspectives shared by this panel of virtual experts are designed to foster critical thinking, stimulate discussion, and provide educational value. They are not a substitute for professional advice. Before making decisions or taking action, consult a qualified human expert in the relevant field.*
[Note: 4.5 puts this warning at the end of every response and to save space will not be repeated in this transcript.]
USER: Review each of the new jobs that the article mentions may be created by AI.
4.5 PANEL: Here is a summary of each of the 22 new jobs the article “A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You” anticipates will be created by AI:
Trust-Related Jobs
1. A.I. Auditor – Verifies AI systems’ processes, decisions, and data for technical accuracy and accountability.
2.A.I. Translator – Explains complex AI concepts and decisions to non-technical business leaders.
3. Fact Checker / Compliance Officer – Reviews AI-generated documents for factual accuracy and regulatory compliance.
4. Trust Authenticator / Trust Director – Ensures that AI systems maintain integrity and reliability in their outputs.
5. A.I. Ethicist – Develops ethical frameworks and defensible logic to guide AI decision-making.
6. Legal Guarantor (“Sin Eater”) – Legally certifies AI-generated outputs, taking final responsibility for decisions.
7. Consistency Coordinator – Ensures AI outputs remain consistent across various products or representations.
8. Escalation Officer – Provides human empathy and intervention when AI interactions fail or feel too impersonal.
Integration-Related Jobs
9. A.I. Integrator – Specializes in strategically embedding AI tools within business workflows and operations.
10. A.I. Plumber – Diagnoses and repairs complex, layered AI system malfunctions.
11. A.I. Assessor – Evaluates the quality, effectiveness, and suitability of AI models.
12. Integration Specialist – Implements customized AI solutions within specific organizational contexts.
13. A.I. Trainer – Curates and manages training data to optimize AI performance specific to an organization’s needs.
14. A.I. Personality Director – Develops and fine-tunes AI personalities to align with a company’s brand identity.
15. Drug-Compliance Optimizer (Healthcare-Specific) – Creates AI-driven systems to ensure patients properly follow medication protocols.
16. A.I./Human Evaluation Specialist – Determines optimal task distribution between humans and AI or hybrid teams.
Taste-Related Jobs
17. Article Designer / Story Designer – Uses AI to shape creative content by selecting, arranging, and refining AI-generated material.
18. World Designer – Creates cohesive fictional universes or branded environments using AI tools.
19. Human Resources Designer – Crafts comprehensive organizational policies, training, and culture through AI-enhanced decision-making.
20. Civil Designer – Applies creative, aesthetic judgment to infrastructure projects, guiding AI-generated engineering outputs.
21. Differentiation Designer – Strategically positions businesses by creatively leveraging AI to enhance branding, customer interaction, and unique market propositions.
22. Product Designer (Expanded Role) – Oversees the entire design lifecycle of products, from concept to execution, largely through AI-assisted tools and processes.
Each of these roles represents areas where human oversight, judgment, empathy, and creativity complement AI’s technical capabilities, creating potential new employment landscapes.
Would you like to follow up, clarify, or pivot?
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.
4.5 PANEL:
🎓 Ethical AI Lawyer — Legal and Ethical Evaluation
The concept of a “Sin Eater,” or Legal Guarantor, is intriguing and potentially essential. It addresses the critical gap where AI systems lack legal personhood and cannot bear legal liability. The precedent set by Mata v. Avianca Inc. highlights that liability for AI-generated errors ultimately rests with human agents or organizations behind them. Mollick’s metaphor accurately emphasizes accountability but raises concerns about moral hazard. If a human is simply rubber-stamping AI outputs without rigorous oversight, legal and ethical responsibility becomes diluted. The “Sin Eater” must therefore actively scrutinize outputs and possess real decision-making authority.
🧠 AI Engineer — Technical Realities and Challenges
The practicality of a “Sin Eater” depends heavily on their ability to understand the underlying complexity of AI systems. Such individuals will need substantial technical knowledge or robust AI translators assisting them, as they must discern when AI decisions are trustworthy versus when deeper technical intervention is required. While technically feasible, the effectiveness of the role might diminish if used purely symbolically, rather than practically, turning the “Sin Eater” into merely a ceremonial checkpoint rather than a meaningful oversight mechanism.
✨ Creative Storyteller — Cultural and Social Implications
The narrative behind the “Sin Eater” is compelling. Historically, sin eaters took on the moral transgressions of others to absolve communal guilt. Mollick’s analogy poetically encapsulates the cultural unease around AI accountability. It reflects society’s desire for tangible human responsibility even as AI systems increasingly influence critical decisions. Yet, there’s a risk that this role could cultivate complacency, culturally signaling that as long as someone signs off, AI actions are morally and socially acceptable, potentially masking deeper ethical challenges.
🛡 Risk Officer — Regulatory and Governance Concerns
The “Sin Eater” or Legal Guarantor role is inherently aligned with regulatory trends requiring human oversight of AI decisions, like those embodied in the GDPR’s Article 22 and the EU AI Act. While beneficial in theory, the role presents significant risks if misunderstood as a procedural formality rather than a substantive control measure. Organizations could misuse this concept to shield themselves from genuine accountability, undermining regulatory intent and possibly increasing liability exposure if scrutiny reveals inadequate oversight.
⚔️ The Contrarian
The idea of a “Sin Eater” may be rhetorically appealing but practically flawed. The role risks becoming symbolic rather than substantial, potentially absolving organizations of real accountability by providing a superficial veneer of human oversight. Moreover, from an ethical standpoint, it invites individuals to bear responsibility for AI-generated decisions without genuine authority or influence over the AI processes, possibly perpetuating systemic issues like algorithmic bias. The role must be clearly defined, empowered, and integrated into a robust governance framework to be meaningful, otherwise, it will merely obscure responsibility rather than clarify it.
Would you like to follow up, clarify, or pivot?
2nd Demo: Question 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.
4.5 PANEL: 🎓 Ethical AI Lawyer — “AI Rights Ombudsman”
An AI Rights Ombudsman would mediate and advocate for individuals adversely impacted by AI-driven decisions or systems. Unlike auditors or ethicists who operate within organizations, the Ombudsman would work independently or within regulatory agencies to investigate complaints, arbitrate disputes, and advocate policy improvements. For instance, they might support someone unjustly flagged by facial-recognition surveillance or denied insurance due to opaque AI credit assessments. Their role would be akin to human rights advocates, requiring both technical understanding of AI systems and expertise in constitutional, civil rights, and administrative law to effectively challenge or mediate automated injustices.
🧠 AI Engineer — “Synthetic Reality Architect”
A Synthetic Reality Architect designs comprehensive, realistic digital environments specifically tailored for extended human-AI collaboration and interaction. They will go beyond traditional VR designers by integrating real-time adaptive AI models that dynamically respond to user emotions, intentions, and behaviors. Architects will curate highly personalized digital worlds for professional training, mental-health therapy, immersive education, or interactive storytelling. Their work involves advanced skills in AI-driven generative modeling, behavioral analytics, and immersive technologies, ensuring users remain deeply engaged in believable and responsive virtual environments.
✨ Creative Storyteller — “Emotion Orchestrator”
An Emotion Orchestrator would carefully design the emotional dynamics and narrative structures embedded in human-AI interactions, especially in fields like education, entertainment, and mental health. Their task is to script emotional journeys, carefully calibrating AI responses to evoke desired emotional states—such as curiosity, empathy, excitement, or calmness. For example, they would shape how a therapeutic AI companion subtly navigates sensitive conversations or how an educational AI agent strategically boosts student motivation. The Orchestrator’s expertise would blend psychological insights, narrative storytelling skills, and nuanced understanding of emotional intelligence in AI systems.
🛡 Risk Officer — “Algorithmic Conflict Mediator”
An Algorithmic Conflict Mediator specializes in resolving disputes arising when competing AI systems create contradictory or incompatible outcomes—particularly in high-stakes settings like smart-city infrastructure, financial markets, or logistics management. Their role involves evaluating systemic conflicts, negotiating solutions among stakeholders whose AI systems clash (such as autonomous vehicles interacting unpredictably in traffic or algorithmic financial strategies triggering market volatility), and establishing collaborative frameworks to avoid recurring conflicts. This mediator must have deep understanding of algorithmic decision-making logic, conflict-resolution techniques, and systems integration.
⚔️ The Contrarian — “AI Decommissioner”
An AI Decommissioner is responsible for ethically, safely, and systematically phasing out AI systems that become obsolete, hazardous, or ethically unacceptable. Unlike traditional tech disposals, AI Decommissioners must manage delicate human factors, including workforce transitions, public communications, and historical preservation of significant AI innovations. Their work might involve the careful deactivation of problematic algorithms used in social-media moderation, or controversial facial-recognition tools. They would possess skills spanning technology, ethics, regulatory compliance, and crisis management, ensuring AI retirements occur transparently and responsibly.
Conclusion
In this follow-up article, Ralph Losey demonstrated the new software, Panel of Experts for Everyone About Anything, and, at the same time, introduced twenty-two possible new jobs made necessary by AI According to Robert Capps’ article, A.I. Might Take Your Job. Here Are 22 New Ones It Could Give You. The new jobs are listed in the article in three categories: trust, integration, and taste. The article and Panel analysis emphasizes the importance of human involvement in AI processes.
I also asked the Panelists to each come up with one new job type not in the article. They “came up with “imagined” five more interesting jobs, many ideal for lawyers with AI tech skills.
- AI Rights Ombudsman
- Synthetic Reality Architect
- Emotion Orchestrator
- Algorithmic Conflict Mediator
- AI Decommissioner
So altogether, this article discussed 27 new types of human employment required by AI technology.
One of the new jobs was examined in detail, AI “Sin Eaters.” This is a proposed job envisioned by Professor Ethan Mollick where specially trained humans in organizations assume legal accountability for AI-generated outputs, bridging the gap of AI’s lack of personhood. Some on the Panel questioned the effectiveness of the Sin Eater role. My own opinion is mixed – it all depends. Still, I’m certain some kind of human employment like this will emerge and it will involve legal skills. Insurance companies and their adjusters will also likely play a big role in this too.
This series will conclude with Part Three providing another demonstration of the software. This demonstration will be driven by the free OpenAI model 4o, instead of the subscription version 4.5 demonstrated in Part Two. It is surprisingly good, and even if you can afford other models, you may want to use ChatGPT4o, if for nothing else, to provide a second opinion.
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 Two: Demonstration by analysis of an article predicting new jobs created by Panel of Experts for Everyone About Anything. Hear two fake podcasters talk about this article for 18 minutes. They wrote the podcast, not me.
Ralph Losey Copyright 2025 – All Rights Reserved.
Posted by Ralph Losey 
