Enterprise Platforms - SJSU for Ammar_Rayes 202510 v18.pptx

20251031

Enterprise Platforms – Service Science & AI Perspectives�October 31, 2025, 3:00pm PT at SJSU�For Ammar Rayes(ISSIP, SJSU)

Ammar Rayes: https://www.linkedin.com/in/ammarrayes/

1. Enterprise Platforms – Service Science & AI Perspectives October 31, 2025, 3:00pm PT at SJSU For Ammar Rayes(ISSIP, SJSU) Presentations online at: https:// slideshare.net / spohrer Jim Spohrer Retired Industry Executive (Apple, IBM) Board of Directors (ISSIP, ServCollab) UIDP Senior Fellow Questions: [email protected] BlueSky: ‪@ spohrer.bsky.social ‬ LinkedIn: https:// www.linkedin.com /in/ spohrer / English: https:// youtu.be /T4S0uZp1SHw French: https:// youtu.be /02hCGRJnCoc https://answersfrom.me/jimtwin

2. Questions for Students: Your generation needs good answers to these questions. Q1: What would you do if you have 100 highly skilled workers working for you (e.g., software development, marketing, etc.)? Q2: What job(s) would you assign to (if you had one) your AI Digital twin? Q3: What is the best way(s) that you know of to keep up with accelerating change?

3. OpenAI’s Roadmap

4. Enterprise Platforms Discussion Enterprise Aspect Big – IBM Medium – Startup Small – ISSIP.org Employees (HRM) Customers (CRM) Supply Chain (SCM) Offerings (Product & Service) Communications Productivity Locations (ERP) Finance & M&A Shareholders Governments & Legal Competitors

5. Gemini: Enterprise Platform Vendor Landscape: Incumbents vs Disruptors This table maps core enterprise functions to the platforms that manage them, contrasting the largest incumbent vendors with smaller, often cloud-native, startups aiming to disrupt the market. Note: The platform landscape is complex, with many vendors spanning multiple categories (e.g., Microsoft and Oracle provide solutions across almost every aspect). The placement above reflects their primary areas of competitive strength. Enterprise Aspect Platform Category Large Incumbent Vendors (Established Leaders) Disruptor / Niche Vendors (Cloud-Native, AI Focus) Employees (HRM) Human Resources Management (HCM) Workday, Oracle HCM Cloud, SAP SuccessFactors, ADP Gusto  (Payroll/HR for SMBs),  Deel  (Global payroll/compliance),  Hibob  (Employee experience focus) Customers (CRM) Customer Relationship Management (CRM) Salesforce (Sales Cloud, Service Cloud), Microsoft Dynamics 365 HubSpot  (Inbound Marketing/CRM),  Outreach (Sales Engagement),  Pipedrive  (Sales focused CRM) Supply Chain (SCM) Supply Chain & Logistics SAP SCM, Oracle SCM Cloud, Blue Yonder (formerly JDA), Infor project44  (Real-time logistics visibility),  Kinaxis (Supply Chain Planning),  Gong  (Logistics Automation) Offerings (Product & Service) Product Lifecycle Management (PLM), Development, Design Atlassian (Jira, Confluence), Dassault Systèmes, ServiceNow Figma  (Collaborative Design),  GitLab  (DevOps Platform),  Notion  (Knowledge & Product Workspace) Communications Unified Communications & Contact Center (UCaaS) Microsoft Teams, Cisco Webex, Zoom (Meetings) Slack  (Acquired by Salesforce, disruptive messaging),  Dialpad  (AI-powered UCaaS),  RingCentral Productivity Collaboration & Office Suites Microsoft 365 (Word, Excel, SharePoint), Google Workspace (Docs, Drive) Notion  (All-in-one workspace),  Asana  (Work Management),  Glean  (Enterprise Search/Knowledge Retrieval) Locations (ERP) Enterprise Resource Planning (ERP) & Core Financials SAP S/4HANA, Oracle ERP Cloud, Microsoft Dynamics 365 F&O Oracle NetSuite  (Cloud-native ERP, often disruptive to SAP/Oracle implementations),  Acumatica ,  Odoo  (Open-source/Modular ERP) Finance & M&A Financial Planning, Close, & Compliance Oracle, SAP, IBM, BlackLine (Financial Close) Workiva  (Compliance & Reporting),  Anaplan (Financial Planning & Analysis - FP&A),  Tink (Open Banking Infrastructure) Shareholders Investor Relations (IR) & Governance Nasdaq IR Insight, S&P Global (Market Intelligence), Cision Q4 Platform  (IR Operations),  EQS Group (Compliance/IR),  Irwin  (IR Intelligence) Governments & Legal Governance, Risk, & Compliance (GRC) / Legal Tech Thomson Reuters, SAP GRC, Dell Technologies (Legal/GRC) Fenergo  (Client Lifecycle Management/KYC),  Cyera  (Data Security Posture Management),  Workiva  (GRC components) Competitors Market & Data Intelligence Legacy Data Warehouses (Teradata, IBM), Cloud (AWS, Azure) Snowflake  (Cloud Data Warehouse),  Databricks (Lakehouse Platform),  Scale AI  (AI Data Labeling/Generation)

6. Claude: Enterprise Platform Vendors by Category Consolidation trends : Many major vendors (Microsoft, Oracle, SAP, Salesforce) now offer suites spanning multiple categories Vertical specialization : Many disruptors focus on specific industries or company sizes Cloud-native advantage : Most disruptors are built cloud-first, while legacy vendors are still transitioning AI integration : Latest competitive battleground across all categories as of 2024-2025 Enterprise Aspect Major Platform Vendors Disruptors & Emerging Players Employees (HRM) Workday, SAP SuccessFactors, Oracle HCM Cloud, ADP Rippling, Deel, Gusto, BambooHR, Lattice, 15Five, Culture Amp Customers (CRM) Salesforce, Microsoft Dynamics 365, HubSpot, Oracle CX Pipedrive, Freshworks, Zoho CRM, Close, Attio, Affinity Supply Chain (SCM) SAP SCM, Oracle SCM Cloud, Blue Yonder (formerly JDA), Manhattan Associates Flexport, project44, FourKites, Infor Nexus, o9 Solutions, Kinaxis Offerings (PLM) Siemens PLM (Teamcenter), PTC (Windchill), Dassault Systèmes (ENOVIA), SAP PLM Autodesk Fusion Lifecycle, Arena (PTC), Propel Software, OpenBOM Communications Microsoft Teams, Slack (Salesforce), Zoom, Cisco Webex Discord (enterprise), Mattermost, Rocket.Chat, Element, Loom, Grain Productivity Microsoft 365, Google Workspace, Atlassian Suite, Monday.com Notion, Coda, ClickUp, Airtable, Linear, Height, Asana Locations (ERP) SAP S/4HANA, Oracle ERP Cloud, Microsoft Dynamics 365, Infor CloudSuite, NetSuite (Oracle) Acumatica, Odoo, ERPNext, Sage Intacct, FinancialForce, Ramco Systems Finance & M&A SAP Analytics Cloud, Oracle Fusion Cloud Financials, Workiva, BlackLine, Anaplan Vena Solutions, Prophix, Datarails, Pigment, Mosaic, Runway, Carta (cap table) Shareholders Computershare, Broadridge, EQ (Equiniti), AST (American Stock Transfer) Carta (private markets), Shareworks (Morgan Stanley), Capshare, Pulley Governments & Legal Thomson Reuters (Practical Law), LexisNexis, Workday Strategic Sourcing, Coupa Ironclad, Docusign CLM, LinkSquares, Juro, ContractPodAi, SpotDraft, Dili Competitors Salesforce (Compete), Klue, Crayon, Kompyte (Semrush) AlphaSense , Contify , Owler , SimilarWeb , Puzzle (acquired), Visualping

7. ChatGPT: Enterprise Platform Vendors Enterprise Aspect Largest Platform Vendors (examples) Smaller Vendors / Startups (disruptors) Employees (HRM) Workday, ADP Rippling, Gusto Customers (CRM) Salesforce, Microsoft Dynamics 365 HubSpot, Zendesk Supply Chain (SCM) Oracle Cloud SCM, Manhattan Associates Flexport, Convoy Offerings (PLM, Service Mgmt, E-commerce & Delivery) PTC (PLM), ServiceNow, Shopify Aras, Salsify Communications Microsoft Teams, Zoom, Slack Twilio, RingCentral Productivity (Docs, Sheets, Collaboration) Microsoft 365, Google Workspace Notion, Airtable Locations / Core ERP Oracle ERP, Infor, Microsoft Dynamics 365 (ERP) Acumatica, Rootstock Finance & M&A Oracle Finance, Workday Financials / Adaptive Datasite, DealRoom Shareholders (IR / Investor Platforms) Broadridge, Nasdaq DFIN, Backstop Governments & Legal Relativity, LexisNexis Ironclad, LegalZoom Competitors (Market & Competitive Intelligence) Gartner, Forrester Klue , Crayon

8. Enterprise Platforms Stakeholder Big – IBM Medium – Startups Small – ISSIP.org Employees (HRM) WorkDay Volunteer Customers (CRM) Salesforce Donors – Zeffy , Benevity, Roundup Supply Chain (SCM) Offerings (Product & Service) GitHub, Rational Cloud: AWS, Google, Azure, IBM Communications AT&T, Zoom, Slack Productivity Microsoft Locations (ERP) SAP, IBM Maximo Finance & M&A Shareholders Governments & Legal Competitors

9. Two disciplines: Two approaches to the future Artificial Intelligence is almost seventy-years-old discipline in computer science that studies automation and builds more capable technological systems. AI tries to understand the intelligent things that people can do and then does those things with technology. ( https://deepmind.com/about “... we aim to build advanced AI - sometimes known as Artificial General Intelligence (AGI) - to expand our knowledge and find new answers. By solving this, we believe we could help people solve thousands of problems.” ) Service science is an emerging transdiscipline not yet twenty-years- old that studies transformation and builds smarter and wiser socoi -technical systems – families, businesses, nations, platforms and other special types of responsible entities and their win-win interactions that transform value co-creation and capability co-elevation mechanisms that build more resilient future versions of themselves – what we call service systems entities. Service science tries to understand the evolving ecology of service system entities, their capabilities, constraints, rights, and responsibilities, and then then seeks to improve the quality of life of people (present/smarter and future/wiser) in those service systems. Service systems are dynamic configurations of people, technology, organizations, and information, connected internally and externally by value propositions, to other service system entities. (Maglio et al 2009)

10. Optimistic Realistic Knowing Doing How to keep up with accelerating change? Follow a diverse collection of people… make up dimensions meaningful to you! Sadly for me… my brain is biased into thinking I can understand older, white, males the best… maybe AI can help overcome! TheNeuron Who do I wish I had Accurate, Up-to-date AI Digital Twins of?

11. Jensen: You imagine a tiny chip… The H100 weighs 70 pounds… 35000 parts… $250K cost… It replaces a data center… Full of computers and cables… Jim: Driving the marginal cost of computing to zero… Drives the demand for new service offerings based on computing through the roof

12. 1960 1980 2000 2020 2040 2060 2080 $1,000,000,000,000 (Trillion) $1,000,000 (Million) $1,000,000,000 (Billion) $1,000 (Thousand) $1 Gigascale (10 9 ) Terascale (10 12 ) Petascale (10 15 ) Exascale (10 18 ) Zettascale (10 21 ) Yottascale (10 24 ) Ronnascale (10 27 ) GDP/Employee Trend Estimating Knowledge Worker Productivity Based on USA Historical Data Year Value 1960 $10K 1980 $33K 2000 $78K 2020. $151K 2023 $169K Kiloscale (10 3 ) Megascale (10 6 ) Cost of computation goes down by 1000x every 20 years (left to right diagonals), driving knowledge worker productivity up.

13. Predict the Timeline: GDP/Employee National Academy - Service Systems and AI 13 ( Source ) Lower compute costs translate into increasing productivity and GDP/employees for nations Increasing productivity and GDP/employees should translate into wealthier citizens AI Progress on Open Leaderboards Benchmark Roadmap to solve AI/IA Alistair Nolan (OECD AI for Science Productivity): “It has been stated that the number of engineers proclaiming the end of Moore's Law doubles every two years.” Rouse WB, Spohrer JC. (2018) Automating versus augmenting intelligence. Journal of Enterprise Transformation. 2018 Apr 3;8(1-2):1-21. Read Rouse & Spohrer (2018) enough to understand this slide including what ”exascale” means 11/22/22 Part 1: Solving AI

14. What is an AI digital twin? Well, imagine if there was a “mimic” version of you that was online 24x7 and could speak any language, with knowledge of your publications, and could explain things in a way an audience of listeners might understand? ReidAI’s purpose - to challenge Reid Hoffman in new ways and experiment with new tech capabilities https:// youtu.be /rgD2gmwCS10 ReidTwin ReidReal

15. Who else is getting a twin (AI Avatar)? SJSU President Cynthia Teniente Matson https://youtu.be/gqrIMItHyz8 “expanding our reach, and enhancing communications.”

16. JimTwin Adventure… ChatBot ( Tmpt.app ) Scott Zimmer https://answersfrom.me/jimtwin Avatar-1 ( HeyGen.ai ) SJSU Team (Claude + HeyGen ) https://youtu.be/T4S0uZp1SHw https://youtu.be/02hCGRJnCoc Avatar-2 (GitHub) Arnay Bhatia https://youtu.be/mwnZjTNegXE https://youtu.be/QR17aXYgefk

17. Do you want a digital twin of yourself? No/Yes/Not Sure Narayan S & Spohrer J (2025) Metrics, Incentives, Rewards, and Culture for Impact. In Hall R & Boccanfuso A,Editors , University-Industry Collaboration, Innovation at the Interface. Springer . URL: https:// link.springer.com /book/10.1007/978-3-031-94913-5 Spohrer, J.C. (2010). IBM's University Programs. IEEE Computer 43(8):102-104. URL: https://service- science.info /wp-content/uploads/2017/04/IBM-GUP-5Rs-copy-2.pdf Spohrer, J.C. (2013). What's Up at IBM? University Programs! The 6 R's helping to build a Smarter Planet: Research, Readiness, Recruiting, Revenue, Responsibility, Regions. May 14, 2013. Slideshare. URL: https://www.slideshare.net/slideshow/ibm-up-external-20130514-v11/21175603 Spohrer, J. (2017). IBM's service journey: A summary sketch. Industrial Marketing Management, 60, 167-172. URL: https:// www.sciencedirect.com /science/article/abs/ pii /S0019850116301778?via%3Dihub Spohrer, J. (2024a). AI Upskilling and Digital Twins: A Service Science Perspective on the Industry 4.0 to Industry 5.0 Shift. In Industry 4.0 to Industry 5.0: Explorations in the Transition from a Techno-economic to a Socio-technical Future (pp. 79-92). Singapore: Springer Nature. URL: https:// link.springer.com /chapter/10.1007/978-981-99-9730-5_4 Spohrer, J. (2024b) Personal AI digital twins: the future of human interaction? EIT Digital URL: https://www.eitdigital.eu/newsroom/grow-digital-insights/personal-ai-digital-twins-the-future-of-human-interaction/

18. 3Es: Challenges to “Humanity-Friendly AI Teammate” Energy Errors Ethics Hicks MT, Humphries J, Slater J (2024) ChatGPT is bullshit. Ethics & Information Technology 26(38). URL: https:// doi.org /10.1007/s10676-024-09775-5 IBM Research - TrueNorth (Dharmendra Modha and team) Pssssssst! The real problem is communication between people. Can more computation help?

19. Why do GenAI LLMs work as well as they do? Honestly, no one knows for sure. We see prediction & pattern completion, but not true reasoning, just mimicry Impressive performance, but prediction alone is not enough Imperfect, because human-like reasoning (with world models) is not there Nevertheless, pattern completion is very good The answer will require a better understanding of optimization in high dimensional spaces The good and the bad What is AI good at? Speed, Summarization (What is needed to regenerate whole, stripped of most specifics), Outline content (What the abstract structures are), Creative Pattern Completion (Fiction – made up details that might seem plausible). What is AI bad at? 3Es (energy, errors, ethics <- because of how we build it today). What is surprising? Surprise! Everything can be near and far at the same time in a high dimensional space (very similar, very different) – amplifier of consilience and polarization. Surprise! Every starting point is near a ”black hole” of nearly ideal optimization as higher and higher dimensions and more and more data are used. (quadrillions of partial coherent structures) Impressive, but imperfect Impressive: The mathematics of high-dimensional optimization work pretty well for predicting local coherence at multiple scales of patterns ( plausible pattern completion tasks) Imperfect: Reasoning requires world models, perhaps multiple mappings from high dimensional to low dimensional representation spaces preserving certain relations as world models, or creating Python program world models to help. Generate-Test-and-Debug (G-T-D) will likely be required with human-like episodic memory with expectation violations and remindings (Schank’s ”Dynamic Memory” and Case-Based Reasoning)

20. HCI for HHI Teammates, that I know is much better in my mind…. Recent Stanford paper – generic AI teammates “It’s the AI PI’s job to figure out the other agents and expertise needed to tackle the project,” Zou said. For the SARS-CoV-2 project, for instance, the PI agent created an immunology agent, a computation biology agent and a machine learning agent. And, in every project, no matter the topic, there’s one agent that assumes the role of critic. Its job is to poke holes, caution against common pitfalls and provide constructive criticism to other agents.”

21. Hot Topic: More Readings Every Day Gary Hunnicut suggested (2025) “Digital Twins for Cancer—Not If, But When, How, and Why?” https://datascience.cancer.gov/news-events/blog/digital-twins-cancer-not-if-when-how-and-why Cybernetic Teammates (2025) “The Cybernetic Teammate: A Field Experiment on Generative AI Reshaping Teamwork and Expertise” https:// papers.ssrn.com /sol3/ papers.cfm?abstract_id =5188231 Vendor Policy Brief “A Policy Framework for Building the Future of Science with AI” https://static.googleusercontent.com/media/publicpolicy.google/en//resources/ai_policy_framework_science_en.pdf ”Towards an AI Co-Scientist” - https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf Humanity (just out today – April 2, 2025) Being Human in 2035: How Are We Changing in the Age of AI URL: https://imaginingthedigitalfuture.org/wp-content/uploads/2025/03/Being-Human-in-2035-ITDF-report.pdf Transdisciplinarity (2023) "Transdisciplinary Team Science: Transcending Disciplines to Understand Artificial Social Intelligence in Human-Agent Teaming” https://journals.sagepub.com/doi/full/10.1177/21695067231192245 Augmentation – Amplification (1962) “Augmenting Human Intellect:  A Conceptual Framework” (cites Licklider 1960 and Bush 1945) https://www.dougengelbart.org/pubs/augment-3906.html

22. Tool, Assistant, Collaborator, Coach, Mediator (“Trust”) 10/31/25 Understanding Cognitive Systems 22 Task & World Model/ Planning & Decisions Self Model/ Capacity & Limits User Model/ Episodic Memory Institutions Model/ Trust & Social Acts Tool + - - - Assistant ++ + - - Collaborator +++ ++ + - Coach ++++ +++ ++ + Mediator +++++ ++++ +++ ++ Cognitive Tool Cognitive Assistant Cognitive Collaborator Cognitive Coach Cognitive Mediator Part 2: Solving IA = Intelligence Augmentation (in a humanity-friendly way) Solving IA also requires All of this and done well As a “bicycle for the mind” To make us stronger, Not weaker When tech is all removed Read Demirkan & Spohrer (2025) enough to understand this slide including what ” trusted mediator ” means Demirkan H, Spohrer J (2025) Talent Management: “Here Come the Digital Workers!”. In ORMS Today, INFORMS, June 17, 2025. URL: https:// pubsonline.informs.org /do/10.1287/orms.2025.02.15/full/

23. The Communication Problem: In a Nutshell Doing More Agreeing Less Can GenAI LLMs help people to stop wasting creative friction? Competing ideas can lead to “insanely great” win-win collaborations. If we can figure out communications between people. Latent spaces for people. Barile S, Piciocchi P, Saviano M, Bassano C, Pietronudo C, Spohrer JC (2019)) Towards a new logic of value co-creation in the digital age: doing more and agreeing less. Naples Forum on Service. URL: ttps :// tinyurl.com /2019-DoingMoreAgreeingLess Failure To Find Win-Win

24. Long flights sometimes allow long conversations 1440 News (July 11, 2025): The high-fashion ‘It’ bag origin story Birkin (Actress) and Dumas (Fashion Designer) meet “The bag’s story began in the 1980s when the  actress met  Hermès CEO Jean-Louis Dumas on a flight. Frustrated with her handbag, Birkin described her ideal bag to Dumas, and they famously sketched the design on an airsickness bag.”  URL: https:// en.wikipedia.org /wiki/ It_bag Win-Win Opportunities Do Win-Win opportunities always exist between any two actors? What are the set of possible Win-Win’s between actors? How best to explore the Win-Win possibilities between two actors? How does finding Win-Win opportunities relate to Truth?

25. Truth, Trust, and Wisdom Truth: The ongoing pursuit Mathematical, Computational, Empirical, Historical, Rhetorical Knowing a ”better argument” when we see it and why (humility needed) Trust: Hard to build, easy to destroy Mental models and predictable behaviors AI digital twins of all responsible actors Wisdom: Learning to invest wisely In becoming better future versions of ourselves In a world that future generations will want to live in together

26. Resilience: Rapidly Rebuilding From Scratch Dartnell L (2012) The Knowledge: How to Rebuild Civilization in the Aftermath of a Cataclysm. Westminster London: Penguin Books. 10/31/25 Jim Spohrer (ISSIP) 26 Part 3: “Solving All Problems”

27. Two disciplines: Two approaches to the future Artificial Intelligence is almost seventy-years-old discipline in computer science that studies automation and builds more capable technological systems. AI tries to understand the intelligent things that people can do and then does those things with technology. ( https://deepmind.com/about “... we aim to build advanced AI - sometimes known as Artificial General Intelligence (AGI) - to expand our knowledge and find new answers. By solving this, we believe we could help people solve thousands of problems.” ) Service science is an emerging transdiscipline not yet twenty-years- old that studies transformation and builds smarter and wiser socoi -technical systems – families, businesses, nations, platforms and other special types of responsible entities and their win-win interactions that transform value co-creation and capability co-elevation mechanisms that build more resilient future versions of themselves – what we call service systems entities. Service science tries to understand the evolving ecology of service system entities, their capabilities, constraints, rights, and responsibilities, and then then seeks to improve the quality of life of people (present/smarter and future/wiser) in those service systems. Service systems are dynamic configurations of people, technology, organizations, and information, connected internally and externally by value propositions, to other service system entities. (Maglio et al 2009)

28. Service Science: Conceptual Framework 10/31/25 (c) IBM MAP COG .\| 28 Service Science

29. (c) IBM MAP COG .\| 29 Service Science: Transdisciplinary Framework to Study Service Systems Systems that focus on flows of things Systems that govern Systems that support people’s activities transportation & supply chain water & waste food & products energy & electricity building & construction healthcare & family retail & hospitality banking & finance ICT & cloud education &work city secure state scale nation laws social sciences behavioral sciences management sciences political sciences learning sciences cognitive sciences system sciences information sciences organization sciences decision sciences run professions transform professions innovate professions e.g., econ & law e.g., marketing e.g., operations e.g., public policy e.g., game theory and strategy e.g., psychology e.g., industrial eng. e.g., computer sci e.g., knowledge mgmt e.g., statistics e.g., knowledge worker e.g., consultant e.g., entrepreneur stakeholders Customer Provider Authority Competitors resources People Technology Information Organizations change History (Data Analytics) Future (Roadmap) value Run Transform (Copy) Innovate (Invent) Stackholders (As-Is) Resources (As-Is) Change (Might-Become) Value (To-Be)

30. 30 Time ECOLOGY 14B Big Bang (Natural World) 10K Cities (Human-Made World) Sun writing (symbols and scribes) Earth written laws bacteria (uni-cell life) sponges (multi-cell life) money (coins) universities clams (neurons) trilobites (brains) printing press (books) steam engine 200M bees (social division-of-labor) 60 transistor Where is the “Real Science”? Ecology++ Transdisciplinary sciences that study the natural and human-made worlds… Unraveling the mystery of evolving hierarchical-complexity in new populations… To discover the world’s structures and mechanisms for computing non-zero-sum Value- CoCreation (VCC), Diverse Architectures of Holistic Service Systems (HSS) Sun Earth Bacteria Sponges Clams Universe Cities Writing Laws Money Universities

31. We get the future we invest in… “Service providers will not be replaced by AI, but trusted service providers who use AI (well and responsibly) will replace those who don’t.” National Academy - Service Systems and AI 31 Every person in a role in an organization is a service provider. 10/31/25

32. “The best way to predict the future is to inspire the next generation of students to build it better.” Digital Natives Transportation Water Manufacturing Energy Construction ICT Retail Finance Healthcare Education Government

33. 10/31/25 33 1955 1975 1995 2015 2035 2055 Learn: Explore and Exploit Better Building Blocks Heygen + Claude JimTwin V1 ( Tmpt.app ) 2024 High School Punch cards 1972 IBM Watson AI in the Cloud 2011 2024 2001 2015 2022 2023 1970 1995 2019 2025 2021

34. Jim Spohrer is a Silicon Valley-based Advisor to industry, academia, governments, startups and non-profits on topics of AI upskilling, innovation strategy, and win-win service in the AI era. Most recently with a consulting team working for a top 10 market cap global company, he contributed to a strategic plan for a globally connected AI Academy for achieving rapid , nation-scale upskilling with AI. With the US National Academy of Engineering, he co-led a 2022 workshop on “Service Systems Engineering in the Era of Human-Centered AI” to improve well-being. Jim is a retired IBM Executive since July 2021, and previously directed IBM’s open-source Artificial Intelligence developer ecosystem effort, was CTO IBM Venture Capital Group, co-founded IBM Almaden Service Research, and led IBM Global University Programs. In the 1990’s at Apple Computer, as a Distinguished Engineer Scientist and Technologist, he was executive lead on next generation learning platforms.  In the 1970’s, after his MIT BS in Physics, he developed speech recognition systems at Verbex (Exxon) before receiving his Yale PhD in Computer Science/AI. In 1989, prior to joining Apple, he was a visiting scholar at the University of Rome, La Sapienza advising doctoral students working on AI and Education dissertations. With over ninety publications and nine patents, he received the Christopher Lovelock Career Contributions to the Service Discipline award , Gummesson Service Research award, Vargo and Lusch Service-Dominant Logic award, Daniel Berg Service Systems award, and a PICMET Fellow for advancing service science. Jim was elected and previously served as Linux Foundation AI & Data Technical Advisory Board Chairperson and ONNX Steering Committee Member (2020-2021). Today, he is a UIDP Senior Fellow for contributions to industry-university collaborations, and a member of the Board of Directors of the International Society of Service Innovation (ISSIP) and ServCollab . Jim Spohrer , Advisor Retired Industry Executive (Apple, IBM) UIDP Senior Fellow Board of Directors, ServCollab Board of Directors, ISSIP.org Changemaker Priorities Service Innovation Upskilling with AI Future Universities Geothermal Energy Poverty Reduction Regional Development Competitive Parity Technologies AI & Robotics Digital Twins Open Source AR/VR/XR Geothermal Learning Platforms

35. Service System Design: A Service Science Perspective Designs that improve human capabilities while improving the safety and sustainability of Service Systems Service innovations leverage emerging technologies, new business models, and institutional arrangement and other means Service is the application of resources (e.g., knowledge) for the benefit of another Technology Example Companies Safety Regulatory Bodies (Founded) Stakeholder Harms Stakeholder Benefits Firearms Smith & Wesson ATF (1886) Boilers Babcock & Wilcox NBBPVI (1911) Boiler explosions Railroads, steam-powered factories, building heating, etc. Radio & TV RCA, NBC FCC (1934) Drugs Bayer FDA (1938) Airplanes Boeing, PanAm FAA (1958) Automobiles Ford NHTSA (1966) Nuclear Energy Westinghouse NRC (1975) Social Media Facebook/Meta ?TBD – “Social Dilemma” AI OpenAI , Microsoft, Google ?TBD – “A.I. Dilemma” 10/31/25 Jim Spohrer (ISSIP.org) 35

36. As I was preparing this talk…. Some words kept going thru my mind from Arbesman (2025)… Chapter 8: Tools for Thought: Software for Thinking. “Too often technology is at odds with humanity... For example... QWERTY... ... we have, by and large, adapted ourselves to technology in ways that are not good for us. Our increased drive for optimization of work can run directly counter to our ability to think deeply, or to even feel that human.”

37. And this book as well… Property All social problems seem rooted in three types of property Noncoercion Freedom Gratitude Need for cultural evolution to avoid coercion in any form.

38. Today’s Talk Will our AI Digital Twins become our HCI of the future? Exploring Twin HCI as a “Service Innovation” Capabilities (Possibilities) Benefits (Pros) Harms (Cons) Future Directions Keeping up with accelerating change Service science connections Responsible actors learning to invest wisely in interaction and change processes

39. Homework Apple’s Knowledge Navigator https://www.youtube.com/watch?v=umJsITGzXd0 Luckily colleague Jill was available to chat and help with the class…. … But what if Jill had not been available, but she was willing to share her AI Digital Twin?

40. High Stakes Use Case - Law Not Done Well, but could be

41. Better Done Dead victim, “in his own words”

42. Bad Actors – Cloning Eye on AI

43. Paul Saffo: We Live in Exponential Times Chasing Fire: Matching Strategy To Today's Greatest Challenges Paul Saffo URL: https:// baychi.org /calendar/20250211/ “May you live in exponential times. This is the 21st century version of the oft-told proverb about the blessing (and curse) of living in interesting times.” “Simply put, we are locked in a race between positive and negative exponentials.”

44. Bonjour, je suis JacquesJumeauNumérique . HeyGen Platform JimTwin_French https://youtu.be/02hCGRJnCoc Prompt: « Veuillez résumer ce court article en français, puis formuler trois questions qui pourraient m’être posées et y répondre . » Spohrer, J. (2024b) Personal AI digital twins: the future of human interaction? EIT Digital URL: https://www.eitdigital.eu/newsroom/grow-digital-insights/personal-ai-digital-twins-the-future-of-human-interaction/

45. Questions et réponses avec JimTwin Question 1: Uncurated Que pensez-vous du manque de vérification des faits sur certaines plateformes de médias sociaux basées aux États-Unis ? What are your thoughts regarding the lack of fact checking happening on certain US-based social media platforms?

46. JimTwin Réponse (Français) Le manque de vérification des faits sur certaines plateformes de médias sociaux basées aux États-Unis est une préoccupation croissante . Ce problème peut conduire à la propagation rapide de la désinformation , ce qui peut avoir des conséquences néfastes sur la société, notamment en influençant l'opinion publique de manière erronée et en exacerbant les divisions sociales . Les plateformes de médias sociaux ont souvent été critiquées pour ne pas avoir mis en place des mécanismes efficaces pour vérifier l'exactitude des informations partagées par leurs utilisateurs . Il est suggéré que des mesures telles que l'interdiction de la désinformation sur les réseaux sociaux et les moteurs de recherche, ainsi que la responsabilisation des utilisateurs par la vérification de l'identité , pourraient être des solutions potentielles . De plus, le développement d'une intelligence artificielle plus avancée pour vérifier la véracité des informations pourrait également jouer un rôle crucial. Cependant , la mise en œuvre de ces solutions pose des défis , notamment en ce qui concerne la protection de la liberté d'expression et la gestion de la vie privée des utilisateurs . En fin de compte , il est essentiel que les plateformes de médias sociaux , les gouvernements et les utilisateurs travaillent ensemble pour trouver un équilibre entre la liberté d'expression et la responsabilité de l'information partagée en ligne .

47. JimTwin Answer (English) The lack of fact-checking on some US-based social media platforms is a growing concern. This problem can lead to the rapid spread of misinformation, which can have negative social consequences, including misleading public opinion and exacerbating social divisions. Social media platforms have often been criticized for failing to implement effective mechanisms to verify the accuracy of information shared by their users. It has been suggested that measures such as banning misinformation on social media and search engines, as well as empowering users through identity verification, could be potential solutions. Furthermore, the development of more advanced artificial intelligence to verify the accuracy of information could also play a crucial role. However, implementing these solutions poses challenges, particularly with regard to protecting freedom of expression and managing user privacy. Ultimately, it is essential that social media platforms, governments, and users work together to find a balance between freedom of expression and responsibility for the information shared online.

48. Jim Real (English) The AI generated response (based on my Tmpt.me knowledge hub which is built from my publications and recordings of my mentoring students) is quite a good answer. It mirrors my own thinking well at a high level. I would add this: Education is key. Finland has elementary school classes to teach young people in their society to check sources and evidence, and to be skeptical and verify. Today’s AI is terrible at fact checking, but it will get better. First in mathematics and programming, then in the sciences, and finally in rhetoric, debate, and history. I urge young people interested in AI, to make a focus on “AI-powered pursuit of truth” their mission.

49. Humanity-Centered Harmonization of Disciplines - Transdisciplinarity Why the (holistic) service systems trend is important to future sustainability Business and societal systems and supply chains are increasingly complex and interconnected. Real-world problems do not respect discipline boundaries. Scalable solutions require many schools of practice working together, and current solutions may have unintended consequences, short-term or longer-term, especially if perspectives are not invited/considered. Technological progress improved the scalability of agriculture and manufacturing, and next all types of service will be made more scalable (and currently, energy intensive) by future AI capabilities and progress. A small sampling of schools and disciplines below – more exist  - apologies for not adding yours to this summary. School of practice for Physical Sciences & Engineering Technology School of practice for Behavioral & Social Sciences, Humanities & Arts People School of practice for Managerial Sciences & Entrepreneurship Information & Organizations Comp. Sci./AI HCI/Robotics Electrical & Mech. Eng. Systems Engineering Economics Public Policy & Law Design Information Systems Operations Research Marketing & Strategy Read enough of Kline (1995) to understand conceptual foundation of multidisciplinary thinking and the techno-extension factor and the accelerating soci o-technical system design loop concepts. 10/31/25 National Academy - Service Systems and AI 49

50. Why upskilling with AI trend is important to systems thinking Talent development is moving from I to T to X ( eXtended with AI) National Academy - Service Systems and AI 50 6 T-shape Skills Knowledge Areas To be eXtended By AI tools: 1. Disciplines 2. Systems 3. Cultures 4. Technologies 5. Practices 6. Mindsets 10/31/25

51. Final Thoughts: Communications Communication between responsible actors: Appropriateness Speed Accuracy Responsible actors Collaborate well – “insanely great collaborations possible” (win-win-win) However, there is still the competition for collaborators So… Learning to invest wisely in becoming better future versions of self (individual and collective)is a key future challenge Rawls (1971) A Theory of Justice – has thought experiments to consider

52. Speed Test: Words Per Minute Speaking/Listening versus Writing/Reading People speak on average between 100-150 words per minute Many people are comfortable listening at 200-300 words per minute Writing an essay on a familiar topic, people write about 10-20 words a minute Many people are comfortable reading at about 400-600 words per minute (Shu 2023) (Barnard 2022) See also: https:// calculatingempires.net /

53. Some paths to becoming 640x smarter: Speed up communications for collaborations – ultimately with our AI digital twins. Improving learning of world models and performance of win-win interactions 2x from Learning sciences (methods) Better models of concepts – including models of self and others Better models of learners – including social-emotional intelligence 2x from Learning technology (tools) Guided learning paths Elimination (?) of “ thrashing ” AI & Education (model trace, constructivist, individual tutors, etc.) 2x from Quantity effect (overlaps) More you know, faster (?) you go Advanced organizers 2x from Lifelong learning (time) Longer lives and longer careers Keeps “ learning-mode ” activated 2x from Early learning (time) Start earlier: Challenged-based approach Rebulding all human knowledge from scratch 20x from Cognitive service systems (digital twins) AI Digital Twins for performance support All our interactions tuned to super-mind levels

54. What is Truth? Probably first in math (where a form of verifiable truth exists) Then in programming (where a form of verifiable truth exists) Then in physics, chemistry, and biology (where a form of pursuit of truth exists) And then things get much harder... rhetoric and debate (where arguments are explored) Most of rhetoric and debate rely on history (where a form of pursuit of truth exists)

55. 10/31/25 The International Society of Service Innovation Professionals (ISSIP.org) 55 Advice… 1. AI upskill 2. Build your “digital twin” 3. Set bigger goals(*) (*) This directly implies learning better strategies for coping with failures, and resiliently rebounding.

56. Job description: A person who operators an AI trained to be an expert in some role. The human operator like a vehicle operator helps ensure a good service for customers. An AI is “running” for mayor in Wyoming A resident of Cheyenne, Wyoming trained GPT-4 on “thousands of documents gleaned from Cheyenne council meetings” and announced that the resulting bot, named VIC (the “Virtually Integrated Citizen”) will be running for mayor. The bot’s creator said  he’d be the “meat puppet”  who would operate the AI and act on its behalf, but the bot would be the brains of the operation, deciding on votes and how to run the city. However, Wyoming’s Secretary of State contends that non-humans like VIC can’t run for office. New Job – Person who is an Operator for AI in a New or Existing Service System Role

57. AI Operator Job description: A person who operators an AI trained to be an expert in some role. The human operator like a vehicle operator helps ensure a good service for customers. Future of Skills & Work

58. Self-Control

59. Important Distinctions

60. Thank-you for participating today! You are all awesome!! Try chat at: https:// tmpt.app /@ jimtwin

61. “The best way to predict the future is to inspire the next generation of students to build it better” Digital Natives Transportation Water Manufacturing Energy Construction ICT Retail Finance Healthcare Education Government

62. Some Topics for Today Leadership in the AI era “Leaders Make the Future” Keeping up with accelerating change AI Digital Twins of people Humanoid robots, master mechanic robot Marginal cost of computation goes to zero Truth, trust, learning to invest wisely Innovation - Free Online Events July 30 th – Dr. Haluk Demirkan (Amazon, ISSIP Board Member) Responsible GenAI Framework International Society of Service Innovation Professionals https:// www.issip.org

63. Leaders Make the Future (Johansen et al): How do you want to be augmented? Augmented futureback curiosity Augmented clarity Augmented dilemma flipping Augmented bio-engaging Augmented immersive learning Augmented depolarizing Augmented commons creating Augmented smart mob swarming Augmented strength with humility Human calming From Bob:

64. TheNeuron

65. Today’s talk ( JimReal 2025) Intro: AI (by 1955 definition) has arrived Just took 68 years, but… What’s really going on? Your data is becoming your AI… IA transformation AI Digital Twin = IA (Intelligence Augmentation) Adjustment period underway… Part 1: Solving AI: Leaderboards/Profession Exams Roadmap and implications Open technologies, innovation Part 2: Solving IA: Better Building Blocks Solving problems faster, creates new problems Identity, social contracts, trust, resilience Part 3: ”Solving All Problems” What could go wrong? Be prepared. 37-year long adjustment period is now underway… 10/31/25 Jim Spohrer 67

66. 1956 2023 2060 2080 1956 First AI Workshop 2023 ChatGPT 100M users in just 2 months (1.5B visits in Sept) 2060 (Predicted) Exascale for $1000 (~ one human brain) 2080 (Predicted) Ronnascale for $1B (~ billion human brains) Progress in IA (Intelligence Augmentation) for nations can be estimated as GPD/worker. Progress in AI (Artificial Intelligence) is directly connected to the cost of computing. Review: Remember These Dates

67. 1947 1958 1971 2024 1947 Transistor Bell Labs 1958 Integrated Circuit Texas Instrument 1971 Microprocessor Intel 2024 H100 NVidia Challenges: How to prepare for the next wayes of innovations, including digital twins and humanoid robots, as well as to learn to invest more wisely (self-control). As the marginal cost of computing goes to zero, service innovation will go thru the roof, and energy consumption will go thru the roof as well… Remember These Dates, FACTS, Challenges weight: 70 pounds complexity: 35,000 parts cost: 250,000 dollars

68. Predict the Timeline: GDP/Employee National Academy - Service Systems and AI 70 ( Source ) Lower compute costs translate into increasing productivity and GDP/employees for nations Increasing productivity and GDP/employees should translate into wealthier citizens AI Progress on Open Leaderboards Benchmark Roadmap to solve AI/IA Alistair Nolan (OECD AI for Science Productivity): “It has been stated that the number of engineers proclaiming the end of Moore's Law doubles every two years.” Rouse WB, Spohrer JC. (2018) Automating versus augmenting intelligence. Journal of Enterprise Transformation. 2018 Apr 3;8(1-2):1-21. Read Rouse & Spohrer (2018) enough to understand this slide including what ”exascale” means 11/22/22 Part 1: Solving AI

69. Types: Progression of Models : Verified, Trusted, Wise Models = instruction_set of future: Better building blocks 10/31/25 Understanding Cognitive Systems 71 Task & World Model/ Planning & Decisions Self Model/ Capacity & Limits User Model/ Episodic Memory Institutions Model/ Trust & Social Acts Tool + - - - Assistant ++ + - - Collaborator +++ ++ + - Coach ++++ +++ ++ + Mediator +++++ ++++ +++ ++ Cognitive Tool Cognitive Assistant Cognitive Collaborator Cognitive Coach Cognitive Mediator Part 2: Solving IA Solving IA also requires All of this and done well As a “bicycle for the mind” To make us stronger, Not weaker When tech is all removed

70. Resilience: Rapidly Rebuilding From Scratch Dartnell L (2012) The Knowledge: How to Rebuild Civilization in the Aftermath of a Cataclysm. Westminster London: Penguin Books. 10/31/25 Jim Spohrer (ISSIP) 72 Part 3: “Solving All Problems”

71. Why I am optimistic

72. “The best way to predict the future is to inspire the next generation of students to build it better.” Digital Natives Transportation Water Manufacturing Energy Construction ICT Retail Finance Healthcare Education Government

73. Questions (Jim on AI in 2017) What is the timeline for solving AI and IA? TBD: When can a CEO buy AI capability <X> for price <Y>? Who are the leaders driving AI progress? What will the biggest benefits from AI be? What are the biggest risks associated with AI, and are they real? What other technologies may have a bigger impact than AI? What are the implications for stakeholders ? How should we prepare to get the benefits and avoid the risks? 10/31/25 Jim Spohrer (2017) 75

74. Timeline: Short History 10/31/25 Jim Spohrer (2017) 76 Dota 2 “Deep Learning” for “AI Pattern Recognition” depends on massive amounts of “labeled data” and computing power available since ~2012; Labeled data is simply input and output pairs, such as a sound and word, or image and word, or English sentence and French sentence, or road scene and car control settings – labeled data means having both input and output data in massive quantities. For example, 100K images of skin, half with skin cancer and half without to learn to recognize presence of skin cancer.

75. Rapid Progress History and Future 10/31/25 Jim Spohrer (ISSIP.org) 77

76. Who is winning 10/31/25 Jim Spohrer (2017) 78 https:// www.technologyreview.com /s/608112/who-is-winning-the- ai -race/

77. GPT-4: Needs more planning capability 10/31/25 Jim Spohrer (ISSIP.org) 79

78. AI Benefits Access to expertise “Insanely great” labor productivity for trusted service providers Digital workers for healthcare, education, finance, etc. Better choices ”Insanely great” collaborations with others on what matters most AI for IA = Augmented Intelligence and higher value co-creation interactions 10/31/25 Jim Spohrer (2017) 80

79. AI Risks Job Loss Shorter term bigger risk = de-skilling Super-intelligence Shorter term bigger risk = bad actors 10/31/25 Jim Spohrer (2017) 81

80. Other Technologies: Bigger impact? Yes. Augmented Reality (AR)/ Virtual Reality (VR) Game worlds grow-up Trust Economy/ Security Systems Trust and security immutable Advanced Materials/ Energy Systems Manufacturing as cheap, local recycling service (utility fog, artificial leaf, etc.) 10/31/25 Jim Spohrer (2017) 82

81. 10 million minutes of experience 10/31/25 Understanding Cognitive Systems 83

82. 2 million minutes of experience 10/31/25 Understanding Cognitive Systems 84

83. Hardware < Software < Data < Experience < Transformation 10/31/25 Understanding Cognitive Systems 85 Value migrates to transformation – becoming our future selves; people, businesses, nations = service system entities Pine & Gilmore (1999) Transformation Roy et al (2006) Data Osati (2014) Experience Life Log

84. Intelligence Augmentation (IA) = Socio-Technical Extension Factor on Capabilities Engelbart (1962) Spohrer & Engelbart (2002) 10/31/25 Jim Spohrer (ISSIP) 86 Dedicated to Douglas E. Engelbart , Inventor The Mouse (Pointing Device) The Mother of All Demos Bootstrapping Practice/Augmentation Theory Note: Bush (1945) and Licklider (1960) created funding programs that benefitted Engelbart in building working systems.

85. IA as Socio-Technical Extension Factor on Capabilities & Values IA (human values) is not AI (technology capability) Difference 1: IA leads to more capable people even when scaffold removed Difference 2: IA leads to more responsible people to use wisely the capabilities 10/31/25 Jim Spohrer (ISSIP) 87 Superminds Malone (2018) Things that Make Us Smart Norman (1994) Worldboard Augmented Perception Spohrer (1999) Bicycles for the Mind Kay & Jobs (1984) Techno-Extension Factor Measurement & Accelerating Socio-Technical Design Loop Kline (1996)

86. 10/31/25 Jim Spohrer (ISSIP.org) 88 25 50 100 125 150 Automobile 75 Years 50 100 Telephone Electricity Radio Television VCR PC Cellular Internet % Adoption Capability Augmentation and Adoption Rate Increases

87. Part 3: “Solving All Problems” 10/31/25 (c) IBM MAP COG .\| 89

88. 10/31/25 Jim Spohrer (2015) 90 I have… Have you noticed how the building blocks just keep getting better?

89. Learning to program: My first program 10/31/25 Jim Spohrer (2015) 91 Early Computer Science Class: Watson Center at Columbia 1945 Jim Spohrer’s First Program 1972

90. 10/31/25 92 1955 1975 1995 2015 2035 2055 Better Building Blocks

91. Artificial Leaf Daniel Nocera, a professor of energy science at Harvard who pioneered the use of artificial photosynthesis, says that he and his colleague Pamela Silver have devised a system that completes the process of making liquid fuel from sunlight, carbon dioxide, and water. And they’ve done it at an efficiency of 10 percent, using pure carbon dioxide—in other words, one-tenth of the energy in sunlight is captured and turned into fuel. That is much higher than natural photosynthesis, which converts about 1 percent of solar energy into the carbohydrates used by plants, and it could be a milestone in the shift away from fossil fuels. The new system is described in a new paper in Science . 10/31/25 Jim Spohrer (2017) 93

92. Food from Air Although the technology is in its infancy, researchers hope the "protein reactor" could become a household item.  Juha-Pekka Pitkänen , a scientist at VTT, said: "In practice, all the raw materials are available from the air. In the future, the technology can be transported to, for instance, deserts and other areas facing famine. "One possible alternative is a home reactor, a type of domestic appliance that the consumer can use to produce the needed protein."  According to the researchers, the process of creating food from electricity can be nearly 10 times as energy efficient as photosynthesis, the process used by plants.  10/31/25 Jim Spohrer (2017) 94

93. Exoskeletons for Elderly A walker is a “very cost-effective” solution for people with limited mobility, but “it completely disempowers, removes dignity, removes freedom, and causes a whole host of other psychological problems,” SRI Ventures president Manish Kothari says. “ Superflex’s goal is to remove all of those areas that cause psychological-type encumbrances and, ultimately, redignify the individual." 10/31/25 Jim Spohrer (2017) 95

94. What I study Service Science and Open Source AI – Trust is key to both Service Science Artificial Intelligence Trust: Value Co-Creation/Collaboration Responsible Entities Learning to Invest Transdisciplinary Community Trust: Secure, Fair, Explainable Machine Collaborators Open Source Communities

95. Route 128, aound Boston, MA USA ICASSP 1983

96. IJCAI 1989 – GTD (Generate-Test-Debug)

97. At the end of the day.. Episodic Memory – an accurate version of history on which individual identity is based, and prediction of future interaction behavior (trust) Privacy versus auditability tradeoff Openness-based risk reduction GTD – relative energy cost of generate, test, and debug phases in exploring beneficial and risky possibilities in different realms (intelligence) From mathematically true, to empirically true, to shared history true Truth-based risk reduction

98. Learning to Invest Wisely: Responsible actors becoming better future versions of themselves 10/31/25 Jim Spohrer (ISSIP.org) 100

99. Timeline: Leaderboards Framework AI Progress on Open Leaderboards - Benchmark Roadmap Perceive World Develop Cognition Build Relationships Fill Roles Pattern recognition Video understanding Memory Reasoning Social interactions Fluent conversation Assistant & Collaborator Coach & Mediator Speech Actions Declarative Deduction Scripts Speech Acts Tasks Institutions Chime Thumos SQuAD SAT ROC Story ConvAI Images Context Episodic Induction Plans Intentions Summarization Values ImageNet VQA DSTC RALI General-AI Translation Narration Dynamic Abductive Goals Cultures Debate Negotiation WMT DeepVideo Alexa Prize ICCMA AT Learning from Labeled Training Data and Searching (Optimization) Learning by Watching and Reading (Education) Learning by Doing and being Responsible (Exploration) 2018 2021 2024 2027 2030 2033 2036 2039 10/31/25 Jim Spohrer (2017) 101 Which experts would be really surprised if it takes less time … and which experts really surprised if it takes longer? Approx. Year Human Level -> +3 See: https:// paperswithcode.com / sota

100. Timeline: Leaderboards Framework AI Progress on Open Leaderboards - Benchmark Roadmap Perceive World Develop Cognition Build Relationships Fill Roles Pattern recognition Video understanding Memory Reasoning Social interactions Fluent conversation Assistant & Collaborator Coach & Mediator Speech Actions Declarative Deduction Scripts Speech Acts Tasks Institutions Chime Thumos SQuAD SAT ROC Story ConvAI Images Context Episodic Induction Plans Intentions Summarization Values ImageNet VQA DSTC RALI General-AI Translation Narration Dynamic Abductive Goals Cultures Debate Negotiation WMT DeepVideo Alexa Prize ICCMA AT Learning from Labeled Training Data and Searching (Optimization) Learning by Watching and Reading (Education) Learning by Doing and being Responsible (Exploration) 2018 2021 2024 2027 2030 2033 2036 2039 10/31/25 Jim Spohrer (2017) 102 Which experts would be really surprised if it takes less time … and which experts really surprised if it takes longer? Approx. Year Human Level -> +3 See: https:// paperswithcode.com / sota

101. From leaderboards to profession exams 10/31/25 (c) IBM MAP COG .\| 103

102. Leader Boards: Professional Benchmarking 10/31/25 Jim Spohrer (ISSIP.org) 104

103. How, What, and Why? Inspiring upskilling with AI How to learn AI-powered search can help people - motivated people – to learn about whatever they put their minds to learning What to learn AI technological capabilities and limitations – foundational models AI applications that can actually improve processes for how things get done (case studies - productivity, quality, compliance, sustainability, decarbonization) AI-as-a-service investment cases to motivate stakeholders to change to better win-win interactions in business and societal service systems (investment pitch) The “startup of you” investment case – learning to invest systematically and wisely (startup pitch) Why learn? Challenge and opportunity - nations must upskill with AI and decarbonize Motivation is key – find the very best free online videos/courses and subscribe Universities will play an increasingly important role as industry research partners and venture testbeds even as learners can do more and more on their own with online curriculum National Academies – Service Systems and AI 105

104. Final thoughts on AI as a Science Teammate Estimating knowledge worker productivity Marginal cost of computing going to zero Learning to invest wisely Upskilling with AI & Systems Thinking Humanity-Centered Harmonization of Disciplines – Transdisciplinarity Next revolution in communication and human intelligence Two disciplines: Two approaches to the future Keep learning (self-control) Baumeister RF, Tierney J(2011) Willpower: Rediscovering the greatest human strength. Penguin Press. URL: https:// psycnet.apa.org /record/2011-16843-000

105. uidp.org | [email protected] Research: Creating new knowledge that can both be published and protected as IP. Readiness: Skills development & sharing knowledge to develop business-ready talent. Recruiting: From permanent hires to internships, these programs include HR. Revenue: Partnership executive programs to sustain long-term win-win relationships. Responsibility : Employees donating time to mentor students and give guest lectures. Regions: Programs related to public-private partnerships for regional economic development. Refresh: Explore new programs, sunset some old programs. 7 R’s

106. uidp.org | [email protected] For a sample list in a presentation, you can consider the following points: Introduction to the topic Key points to be covered Supporting examples or evidence Visual aids or graphics Conclusion and key takeaways Remember to organize your content in a clear and engaging manner to effectively communicate your message to the audience. Big Header

107. Overlap Acknowledgement: E. Noei, S. Brisson, Y. Liu Via Kelly Lyons, NAE Talk Oct 2022 2010 2019 109 Service science has come a long way in two decades… 2004-2011

108. Three views on service and AI Discipline View on Service View on AI Broader View Economics Service sector Productivity Sector productivity & quality – better economic systems Automation Technology improved agriculture and manufacturing, service sector is next up Computer Science Web services Capabilities AI provides human capabilities on tasks as technological capability – better tools Automation Robots will further automate agriculture and manufacturing, and eventually service sector as well Service science, based on Service-Dominant Logic Value cocreation Service is the application of resources (e.g., knowledge) for the benefit of another Augmentation Responsible actors (service system entities) upskilling with AI to give and get better service Humanity-Centered Responsible actors learning to invest in improved win-win interaction and change

109. Call to Action: Create SIRs Responsible actors need to learn to invest wisely in getting the future service innovations we want with AI – guided by “Service Innovation Roadmaps (SIRs).” National Academy - Service Systems and AI 111 Read enough of IfM and IBM (2008) to understand what a “Service Innovation Roadmap (SIR)” is – and who should be creating them. 10/31/25

110. Service in the AI era Science science Service dominant (S-D) logic Service Dominant Architecture (SDA) Service in the AI era revisited Core message? Better automation and augmentation improve service processes Better science improves understanding (learning) processes Better logics improve interaction processes Better architectures improve change processes X+AI requires learning to invest systematically and wisely to improve service Where are the better models? Technology Disciplines Minds Enterprise Disciplines + AI Minds + AI Enterprise + AI What type of model? Digital twins Digital twins Digital twins Digital twins Digital twins Service in the AI Era: Science, Logic, and Architecture Perspectives (Spohrer, Maglio, Vargo, Warg – request your digital copy – [email protected] )

111. Who I am: Take 2 The Three Ages of Man (Giorgione) Thanks to Alan Hartman for kind inspiration ( slides ) ( recording ) Service is an actor applying resources (e.g., knowledge) to benefit another Service sy stem entities are responsible actors that give and get service (e.g., people, businesses, universities, nations, etc.) Service science studies service systems as an evolving ecology of responsible actors that interact and change. Service innovations improve win-win interaction and change in business and society Service systems are dynamic configurations of four types of resources

112. What I study Service Science and Open Source AI – Trust is key to both Service Science Artificial Intelligence Trust: Value Co-Creation/Collaboration Responsible Entities Learning to Invest Transdisciplinary Community Trust: Secure, Fair, Explainable Machine Collaborators Open Source Communities

113. 10/31/25 The International Society of Service Innovation Professionals (ISSIP.org) 115

114. IA Progression – Tool, Assistant, Collaborator, Coach, Mediator 10/31/25 Jim Spohrer (ISSIP) 116 Rouse & Spohrer (2018) Siddike , Spohrer, Demirkan, Kodha (2018) Araya (2018) Spohrer& Siddike (2018)

115. Intelligence Augmentation (IA) = Socio-Technical Extension Factor on Capabilities Engelbart (1962) Spohrer & Engelbart (2002) 10/31/25 Jim Spohrer (ISSIP) 117 Dedicated to Douglas E. Engelbart , Inventor The Mouse (Pointing Device) The Mother of All Demos Bootstrapping Practice/Augmentation Theory Note: Bush (1945) and Licklider (1960) created funding programs that benefitted Engelbart in building working systems.

116. IA as Socio-Technical Extension Factor on Capabilities & Values IA (human values) is not AI (technology capability) Difference 1: IA leads to more capable people even when scaffold removed Difference 2: IA leads to more responsible people to use wisely the capabilities 10/31/25 Jim Spohrer (ISSIP) 118 Superminds Malone (2018) Things that Make Us Smart Norman (1994) Worldboard Augmented Perception Spohrer (1999) Bicycles for the Mind Kay & Jobs (1984) Techno-Extension Factor Measurement & Accelerating Socio-Technical Design Loop Kline (1996)

117. 10/31/25 Jim Spohrer (ISSIP.org) 119 25 50 100 125 150 Automobile 75 Years 50 100 Telephone Electricity Radio Television VCR PC Cellular Internet % Adoption Capability Augmentation and Adoption Rate Increases Techno-Extension Factor Measurement & Accelerating Socio-Technical Design Loop Kline (1996)

118. Learning to invest Run = Routine Activities Transform = Copy Activities Innovate = Invent and Apply Activities 10/31/25 Jim Spohrer (ISSIP.org) 120 Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Transform Innovate Invest in each type of change Ru n

119. 121 How responsible entities (service systems) learn and change over time History and future of Run-Transform-Innovate investment choices Diverse Types Persons (Individuals) Families Regional Entities Universities Hospitals Cities States/Provinces Nations Other Enterprises Businesses Non-profits Learning & Change Run = use existing knowledge or standard practices (use) Transform = adopt a new best practice (copy) Innovate = create a new best practice (invent) Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Transform Innovate Invest in each type of change Ru n Spohrer J, Golinelli GM, Piciocchi P, Bassano C (2010) An integrated SS-VSA analysis of changing job roles. Service Science . 2010 Jun;2(1-2):1-20. March JG (1991)  Exploration and exploitation in organizational learning. Organization science. 1991 Feb;2(1):71-87. URL: exploit explore

120. 10/31/25 Jim Spohrer (ISSIP.org) 122 APPLE https://podcasts.apple.com/us/podcast/service-science-and-the-impending-ai-revolution/id1612743401?i=1000583800244 SPOTIFY: https://open.spotify.com/episode/0n3h9rgX6UYDCwxgTzokoK?si=yVF0mtHsRZSmdfy-aMi8DA GOOGLE  https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5idXp6c3Byb3V0LmNvbS8xOTQ5NTE3LnJzcw?sa=X&ved=2ahUKEwiPzL-Zxvv6AhXzjo4IHVbTAuUQ9sEGegQIARAC

121. Service Systems Engineering in the Human-Centered AI Era 123 Knowledge Value Data Science Engineering Policy Investing in Skills for Diverse Systems to Sustainably Serve People and Planet in the AI Era Management S ervice S cience M anagement E ngineering Many disciplines Many sectors Many regions/cultures (understanding & communications ) Deep in one sector Deep in one region / culture Deep in one discipline T -Shaped Skills Depth and Breadth People-centered Data-intensive +Design-Arts- Public-Policy

122. 124 University Trend: “Sister Campuses” (People Flows) University sub-systems Disciplines in Schools (circles) Innovation Centers (squares) E.g., CMU Website (2009) “Research Centers: where it all happens – to solve real-world problems” Disciplines in Schools Award degrees Single-discipline focus Research discipline problems Innovation Centers (ICs) Industry/government sponsors Multi-disciplinary teams Research real-world systems D D D D D D Engineering School Social Sciences, Humanities Professional Studies Business School water & waste transportation health energy/grid e-government Science & Mathematics I-School Design food & supply chain

123. 125 City Trend: “Sister Cities” (People Flows) World as System of Systems World (light blue - largest) Nations (green - large) Regions (dark blue - medium) Cities (yellow - small) Universities (red - smallest) Cities as System of Systems Transportation & Supply Chain Water & Waste Recycling Food & Products ((Nano) Energy & Electricity Information /ICT & Cloud (Info) Buildings & Construction Retail & Hospitality/Media & Entertainment Banking & Finance Healthcare & Family (Bio) Education & Professions (Cogno) Government (City, State, Nation) Nations: Innovation Opportunities GDP/Capita (level and growth rate) Energy/Capita (fossil and renewable) Developed Market Nations (> $20K GDP/Capita) Emerging Market Nations (< $20K GDP/Capita) IBM UP WW: Tandem Awards: Increasing university linkages (knowledge exchange interactions)