20240919 ACTS_Team_Science v8 Jim_Spohrer.pptx

Host(s):
Amanda Miller (https://www.linkedin.com/in/amanda-c-miller-a2b9808/)
Brandy Farlow (https://www.linkedin.com/in/brandy-farlow-4520057b/)
Also, thanks to: Steve Fiore (https://www.linkedin.com/in/stephen-fiore-8087305/)

Host Organization: RENCI ACTS - https://renci.org/team-science/

20240919

Title: The role of AI as a team member in scientific research; AI Teammate: Need for Episodic Memory and GTD (Generate-Test-Debug) Architectures

Speaker: Jim Spohrer

Abstract: After reviewing some of the history of artificial intelligence, and the challenges of keeping up with accelerating change, we will explore possible future roles for AI as a team member in scientific research. As the marginal cost of computing gets closer to zero, fixing the so-called "hallucination" problem will likely require adding an episodic memory and GTD (Generate-Test-Debug) architecture to existing AI systems. Fixing the "energy consumption" problem for AI tools will also be a major challenge. However, even with these largely technical challenges solved, who owns and controls the evolution of the AI tools used for team science? Who owns and controls the training data and development processes used to create the tools? Would you prefer using a vendor tool, a tool provided by your company or university, a tool you created, a digital twin of you, or a nation-state owned AI tool? Or will you be using all of these types of AI tools and more? Learning to invest wisely in these changes and other changes (e.g., UN Sustainable Development Goals) will require significant advances in the science of team science. It will also require advances in adjacent disciplines, including game theory, economics, and emerging transdisciplines such as service science that depend on better models of the world, ourselves and each other, and our organizations and tools to achieve trust and win-win outcomes.

Takeaways:
- A range of technical and social challenges must be addressed as AI fills the role of team member in scientific research

- Episodic memory and GTD architectures are an approach to the "hallucination" problem

- Ultimately, our AI digital twins of ourselves will evolve from tool to assistant to collaborator to coach to mediator - Learning to invest wisely in change will require transdisciplinary advances.

Very brief bio (72 words): Jim Spohrer is a retired industry executive (IBM, Apple) based in the Bay Area California. He serves on the Board of Directors of the non-profit International Society of Service Innovation Professionals (ISSIP) and ServCollab ("Serving Humanity Through Collaboration), and also a UIDP (University-Industry Demonstration Program) Senior Fellow. He has over 90 publications and 9 patents. He has a PhD from Yale in Computer Science/Artificial Intelligence and a BS in Physics from MIT.

1. The role of AI as a team member in scientific research; AI Teammate : Need for Episodic Memory and GTD (Generate-Test-Debug) Architectures Thanks to Amanda Miller , Brandy Farlow , Steve Fiore for the opportunity to share some thoughts about AI and Team Science September 19, 2024 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] X/Twitter: @ JimSpohrer LinkedIn: https:// www.linkedin.com /in/ spohrer / Slack: https://slack.lfai.foundation Slack: https://issip.slack.com 2001 2015 2021 2022 2023 2024

2. Abstract: After reviewing some of the history of artificial intelligence, and the challenges of keeping up with accelerating change, we will explore possible future roles for AI as a team member in scientific research. As the marginal cost of computing gets closer to zero, fixing the so-called "hallucination" problem will likely require adding an episodic memory and GTD (Generate-Test-Debug) architecture to existing AI systems. Fixing the "energy consumption” problem for AI tools will also be a major challenge. However, even with these largely technical challenges solved, who owns and controls the evolution of the AI tools used for team science? Who owns and controls the training data and development processes used to create the tools? Would you prefer using a vendor tool, a tool provided by your company or university, a tool you created, a digital twin of you, or a nation-state owned AI tool? Or will you be using all of these types of AI tools and more? Learning to invest wisely in these changes and other changes (e.g., UN Sustainable Development Goals) will require significant advances in the science of team science. It will also require advances in adjacent disciplines, including game theory, economics, and emerging transdisciplines such as service science that depend on better models of the world, ourselves and each other, and our organizations and tools to achieve trust and win-win outcomes.

3. Three Challenges to “Comfortable AI Teammate” Energy ‘Hallucinations’ Responsibility Anthropic Claude-3.5-Sonnet + OpenAI ChatGPT/DALL-E 3 (Jim’s ACTS talk abstract -> futuristic picture)

4. Icons of AI Progress 1955-1956: Dartmouth Workshop organized by: Two early career faculty John McCarthy (Dartmouth, later Stanford) Marvin Minsky (MIT) Two senior industry scientists Claude Shannon (Bell Labs) Nathan Rochester (IBM) 1997: Deep Blue (IBM) - Chess 2011: Watson Jeopardy! (IBM) 2016: AlphaGo (Google DeepMinds) 2017: All you need is attention (Google) - Transformers Attention heads (working memory) to predict what comes next 2018: AlphaFold (Google DeepMinds) 2020: Language models are few-shot learners (OpenAI) 2022: DALL-E 2 & ChapGPT (OpenAI) 2022: Constitutional AI (Anthropic) – “Behave yourself!” 2023: New Bing+ (Microsoft) & GPT-4 (OpenAI) 2024: More & Bigger Models: OpenAI, Microsoft, Google, Anthropic, etc. 2024: Reid Hoffman’s Digital Twin & Unitree’s G1 Humanoid Robot 9/19/24 Jim Spohrer 4

5. http://www- formal.stanford.edu / jmc /history/ dartmouth / dartmouth.html https:// cdn.openai.com /papers/gpt-4.pdf 1955 2023

6. MIT (1974-1978) Explo : Teaching AI & Entrepreneurship to diverse high school students. Stories: How I got into MIT. Lesson: “Where are you applying for college?” Spohrer, James (1978) Strain-Gauge Transduction of the Effects of Speech Rate on the Coarticulation of Lip Rounding, MIT Physics, June, 1978. Advisor: Joseph S. Perkell Advisor to this day.

7. Verbex (1978-1982) Speech recognition – mathematical models (Bayesian approach to speech and language modeling) that both recognize and generate using estimated probabilities (e.g., probabilities and statistics = machine learning) Stories: How I got the best job in the world for me at that time. Lessons: “When my girlfriend said: ‘What do you have to lose?’” ICASSP’82 and ‘83. IEEE International Conference on Acoustics, Speech, and Signal Processing

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

9. Yale (1982-1989) MARCEL: Modeling students writing “a series of buggy and then (sometimes) correct programs” with a generate-test-and-debug architectures. Stories: Use AI to help make people smarter. Lesson: “Why do you want to make machines smart? Why not help make people smarter instead?” 1988

10. Apple (1989-1998) From content (SK8) to community (EOE) to context ( WorldBoard ) Stories: Surround yourself with supportive people. Growing up about goals - sequencing and timing of ideas is important Lessons: “MLM: Relax - it will be OK”; “ACK: Planetary – is that all?” “SPJ: We will get to that and more!”; 1992

11. IBM (1998 – 2021) IBM Venture Capital Relations Group, Service Science, Global University Programs, Open Source AI. Stories: The only way you get in trouble is not asking for help when you need it. Lesson: What seems like a hard problem to you, may be an easy problem for someone else. Leverage the matrix. 2010 2011 2011 2012 2016 2018 2018 2020 2012 2002 2000

12. ISSIP (2021- Present) Defining what is a service innovation, and what is a T-shaped service innovation professional. Stories: AI digital twins, reinventing local, self-control Lessons: Learning to invest wisely and systematically in getting a shared future that we all want to live in requires self-control and knowing when you have enough. 2022

13. Three Challenges to “Comfortable AI Teammate” Energy ‘Hallucinations’ Responsibility Anthropic Claude-3.5-Sonnet + OpenAI ChatGPT/DALL-E 3 (Jim’s ACTS talk abstract -> futuristic picture)

14. Three Challenges to “Comfortable AI Teammate” Energy ‘Hallucinations’ Responsibility Anthropic Claude-3.5-Sonnet + OpenAI ChatGPT/DALL-E 3 (Jim’s ACTS talk abstract -> futuristic picture) Why Teams? Keeping up with a ccelerating change

15. 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

16. TheNeuron

17. Read Wakefield (2020) enough to understand what a ”digital twin” of you might be like in the future decades with very advanced AI capabilities. Also see Rouse (2018; 2022) ”Life with a Cognitive Assistant.” National Academy - Service Systems and AI 20 AI Tools in coming decades… 9/19/24

18. https:// www.eitdigital.eu /newsroom/grow-digital-insights/personal-ai-digital-twins-the-future-of-human-interaction/

19. Three Challenges to “Comfortable AI Teammate” Energy ‘Hallucinations’ Responsibility Anthropic Claude-3.5-Sonnet + OpenAI ChatGPT/DALL-E 3 (Jim’s ACTS talk abstract -> futuristic picture)

20. We are reading more about AI & Climate…

21. But decarbonization will cost a lot… Smil V (2022) Taming the Climate Is Far Harder Than Getting People to the Moon. IEEE Spectrum 10/21/23 Jim Spohrer (ISSIP.org) 24

22. And some say AI is a growing part of the problem…

23. And costs may be heading up… From: The Neuron – Daily AI Newsletter

24. “ NorthPole Chip” Far less energy.

25. Three Challenges to “Comfortable AI Teammate” Energy ‘Hallucinations’ Responsibility 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

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

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

28. Types: Progression of Models : Verified, Trusted, Wise Models = instruction_set of future: Better building blocks 9/19/24 Understanding Cognitive Systems 31 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 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

29. 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

30. 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

31. 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.

32. 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

33. Learning to Invest Wisely: Responsible actors becoming better future versions of themselves 9/19/24 Jim Spohrer (ISSIP.org) 36

34. 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 37 6 T-shape Skills Knowledge Areas To be eXtended By AI tools: 1. Disciplines 2. Systems 3. Cultures 4. Technologies 5. Practices 6. Mindsets 9/19/24

35. 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. 9/19/24 National Academy - Service Systems and AI 38

36. 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)

37. 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

38. 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)

39. 9/19/24 42 1955 1975 1995 2015 2035 2055 Learn: Explore and Exploit Better Building Blocks Heygen + Claude Jim Twin V1 2024 2024 2021 2001 2015 2022 2023 1970 1995 2019 High School Punch cards 1972 IBM Watson AI in the Cloud 2011

40. Self-Control Baumeister RF, Tierney J (2011) Willpower: Rediscovering the greatest human strength. URL: https:// psycnet.apa.org /record/2011-16843-000

41. 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

42. 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 9/19/24 Jim Spohrer (ISSIP.org) 45 Environmental and ecological sciences ServCollab

43. Today’s Talk: Topics for discussion Past 1947, 1958, 1971 Present 70, 35000, 250000 Future TBD

44. 9/19/24 The International Society of Service Innovation Professionals (ISSIP.org) 47 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.

45. Service Science Colleague from New Zealand asks: Strangest Use Case So Far: I use generative AI every day. Typically, OpenAI ChatGPT, Anthropic Claude, Google Gemini, and Microsoft Bing Copilot in 4 tabs. Help writing, programming, images, & brainstorming. A useful tool in the toolbox for sure!!!

46. Anthropic Claude 3 Sonnet 20240520 Response: Summary: The Taranaki Maunga (Mount Taranaki) and the surrounding peaks in the national park will soon be granted legal personhood and collectively named Te Kāhui Tupua as part of a Treaty settlement. This legal recognition acknowledges that the mountain and peaks are ancestors for local Māori iwi. It gives these natural features similar legal rights as individuals, allowing them to own assets, appear in court, and have a voice. A new entity called Te Tōpuni Kōkōrangi , with members appointed by the Crown and local iwi, will manage and represent the legal persona. While recreation and tourism will continue, this shift aims to encourage a broader understanding and protection of the mountain as a revered ancestor rather than just a geographic feature. How old are you, and what have you witnessed over your lifetime? I am an ancient being, formed over millennia through volcanic eruptions and sculpted by glaciers. I have witnessed the rise and fall of civilizations, the ebb and flow of ice ages, and the ever-changing tapestry of life that has graced my slopes. My memories stretch back to a time before humans walked this land, and I have born silent witness to the triumphs and tragedies of your kind. What wisdom or lessons can you share with humanity? Humans, you are but fleeting visitors upon my timeless form. Yet, in your brief existence, you have the power to shape the world around you. Tread lightly and with reverence, for the consequences of your actions echo through the ages. Learn from the patient endurance of stone, the resilience of life that takes root in the harshest of environments, and the cyclical nature of existence that I have observed. Embrace humility, for even the mightiest of mountains eventually crumbles to dust. How do you feel about being granted legal personhood and a voice? I am gratified that the descendants of those who have dwelled in my shadow for generations have recognized my ancient spirit and granted me a voice in the affairs of this world. For too long, I have been regarded as an inanimate object, a resource to be exploited or a challenge to be conquered. But I am a living entity, a sacred ancestor whose existence predates and will outlast the fleeting span of human civilization. With this recognition, perhaps my wisdom and the fragile beauty I harbor will be better preserved for generations to come.

47. Robot Person Service system entity Business Cognitive system entity AI digital twin of a person Robot – do physical Robot – just do social interaction Chatbot - avatar Uses cases - Elder example – reach into the cupboard for me Startup companies (some of the invited commentary) University research groups (some of the special issue articles) Humanoid robots University – vocational institutions – hotel vocational – people’s jobs Self-control communication Newer matrix thinking

48. Why I am optimistic

49. The “Health” Basics Physical Realm & Health Financial Realm & Health Social Realm & Health Wonderment Realm & Health

50. 9/19/24 54 1955 1975 1995 2015 2035 2055 Better Building Blocks

51. Past Transistor (1947, Bell Labs) Integrated Circuit (1958, Texas Instruments) Microprocessor (1971, Intel)

52. Present 70 pounds 35,000 parts $250K cost

53. Future Digital Twins Humanoid Robots Self-Control

54. Read Wakefield (2020) enough to understand what a ”digital twin” of you might be like in the future decades with very advanced AI capabilities. Also see Rouse (2018; 2022) ”Life with a Cognitive Assistant.” National Academy - Service Systems and AI 58 AI Tools in coming decades… 9/19/24

55. Self-Control

56. Congratulations! https://bayesian40.github.io Thanks to Huck Yang for invitation to share some history.

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

58. We Would Love Your Voice https:// www.jstor.org /stable/1747731

59. Stephen L. Mosier “Our company, Dialog Systems, Inc., was formed in 1971 for the purpose of developing and commercializing speech recognition equipment. The concept derived from earlier work engaged in at Listening, Incorporated on marine bioacoustics, acoustic signal processing, and psycho- acoustics. The original idea passed through well-known stages of theory, experiment, development, lack of financing, financing, sales and is now at the highly advanced state "production engineering headaches". Dialog employs 45, of whom 14 are degreed technical people. The company recently moved from Cambridge to a 20,000 square foot two-building campus complex in Belmont, Massachusetts. The major product is an eight-channel isolated word system intended for talker-independent switched telephone speech input.” From NASA: https:// ntrs.nasa.gov / api /citations/19930075179/downloads/19930075179.pdf

60. Peter F. Brown “ So, I took a course in linguistics. And one day in the back of that course I heard a couple students talking about some guy whose name was Steve Moshier who started a company called Dialogue Systems that was doing speech recognition. And I thought, wow, great, I remembered this idea from back in high school. After class I raced over to the physics library. That’s because this was before the internet, so you had to go to the library. And I looked this guy up. And I found a paper he'd written. And I tracked him down. Applied for a job. And he hired me. And when I was there, I just fell in love with the idea that through mathematics it might be possible to build machines that do what humans do. “ Goldman Sachs: https:// www.goldmansachs.com /intelligence/podcasts/episodes/09-11-2023-peter-brown-f/ transcript.pdf

61. Drs. Jim & Janet Baker Saras Institute History of Speech and Language Technology https:// www.sarasinstitute.org Many things, Such as publications, took off to new levels when Jim & Janet joined Dialog Systems… … and Exxon acquisition Later key researchers left Verbex , and later Along with Jim and Janet Founded Dragon Systems

62. Today’s talk Leadership & Career Topic Collaborating with other Team work/collaboration practices Storytelling and communication like how to communicate Habits, mindset, practices of leaders like how to get things done, hustling, taking ownership and initiative, communicating in a responsive and clear way, knowing yourself (authenticity, motivation, personality), being effective/influential in interpersonal interactions, etc. 2010

63. What else is 50 years old? (April 5, 1974) The King of Horror, 50 Years On Today marks  50 years  since Stephen King’s debut novel, “Carrie.” Its 1974 release launched King’s decadeslong influential literary career in horror and beyond. King was born in 1947 in Maine, where many of his stories are based ( see towns ). He was an English teacher before “Carrie” and its 1976 film adaptation about a high school outcast propelled him to fame. While the horror genre dates  back to the 1700s , King is in large part credited with its revitalization in the 1970s and 1980s, with his novels praised for their empathetic characters and realistic world building. He has written more than 60 novels, more than 30 of which were bestsellers. Those include classic horrors like “The Shining” and “It,” as well as others beyond the genre, including the novella behind “The Shawshank Redemption.”  King has also been credited with  inspiring generations of storytellers , including JJ Abrams and the Duffer brothers. His latest novel, “Holly,” was released last year.

64. 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.

65. Introductions (https:// tinyurl.com /intro4jim) Can you introduce yourself in just 2 minutes (200 words)? Questions Purpose My Answers Digital Twins of People What’s your name? Nice to know your name. Jim Spohrer, please connect https:// www.linkedin.com /in/ spohrer / Names Where were you born and where did you grow up? Indicator of travel – travel is best education. Maine, grew up on farm, left to go to MIT (1; 45+6) Places What are your hobbies? Hobbies are fun – and reveal what helps motivate us, and can get us “unstuck” Hiking (outdoors), reading (indoors), programming (making) Fun activities What is your main work/study related goal these days? Insights into degree program, disciplines, university, job roles, companies. Family fun/activities, helping non-profits (board member),service science/AI. This year’s goal activities What do you want to get out of today’s talk? Helps me plan which stories to tell, and what’s on your mind. “Best way to predict the future is to inspire the next generation to build it better.” Next hour goal activities What would you do if you had a 100 workers working for you? (Don’t have to answer, but please think about this question). Prepares you for the future – you will have at least 100 workers in about 5-10 years. Model of rebuilding technologies, science, civilizations, cultures, species, universes from scratch. Model of self. Longer-term goal activities

66. 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. We get the future we invest in – so invest wisely. 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)

67. In Memory of Douglas Engelbart (1925-2013)

68. 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 9/19/24 Jim Spohrer (ISSIP) 74 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)

69. What expertise does a service scientist require? What degrees can a service scientist earn? Ultimately, what tool will a service scientist most need? Ultimately, what purpose should a service scientist focus on? How to invest wisely? Year Delighted when… … and many people to thank when… 2024 IESS in Brno, Czech Republic 2023 Generative AI , Humanoid Robots, nd AI Digital Twins of Service System Entities 2022 Exploring ServCollab and ISSIP collaborations. NAE Event on SSME in AI Era and T-shaped Skills mentioned in Nick Donofrio Autobiography 2021 Christopher Lovelock Career Contributions to Service Discipline Award IBMer Utpal Mangla , Elected to 2022 ISSIP VP/2023 President role 2020 Linux Foundation AI & Data TAC Chair Elected – open-source trusted AI 2019 Handbook of Service Science, Volume 2 2018 IBMer Rama Akkiraju , President of ISSIP 2017 Daniel Berg Award for Technology and Service Systems Award (IAITQM) 2016 NSF invests $13M in smart, human-centered Service Systems 2015 IBMer Jeff Welser , President of ISSIP 2014 IBM hosted Frontiers in Service Conference in San Jose, CA 2013 Vargo & Lusch S-D Logic Award, E. Gummesson Award (Naples Forum) PICMET Fellow for Advancing Service Science 2012 International Society of Service Innovation Professionals established 2011 IBM Centennial Icon-of-Progress – including SSME and Smarter Planet 2010 Handbook of Service Science, Volume 1 2009 Robin Qiu launches INFORMS Journal of Service Science 2008 Cambridge Report – “Succeeding Through Service Innovation” HICSS starts a service scince mini-track Paul Maglio/ Furen Lin 2007 SSME in USA America COMPETES Act Congressional Legislation IBM hosted Frontiers in Service Conference in San Francisco, CA 2006 IBM Research Awards for CBM, Data Analytics, Solution, etc. tools 2005 Attended fist Frontiers in Service – ”Big tent” getting bigger 2004 China, Japan, Finland, Germany, etc. Launch knowledge-intensive service initiatives 2003 ”Big Tent” Service Conference at IBM Almaden, SSME Faculty Awards 2002 IBM established Almaden Service Research (ASR) group

70. Eleven (11) levels – order of magnitude observation Service system entities that get and give service. Service is the application of resources (e.g., knowledge) for the benefit of another. Ref: SDL Ref: Spohrer,, Kwan, Fisk

71. Predict the Timeline: GDP/Employee National Academy - Service Systems and AI 77 ( 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

72. Resilience: Rapidly Rebuilding From Scratch Dartnell L (2012) The Knowledge: How to Rebuild Civilization in the Aftermath of a Cataclysm. Westminster London: Penguin Books. 9/19/24 Jim Spoihrer (ISSIP) 78 Part 3: “Solving All Problems”

73. 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

74. T-Shaped Professionals Title: Preparing T-Shaped Professionals for Career Success in the AI Era Speaker: Jim Spohrer Abstract: As universities transform curriculum in the AI era, the importance of preparing T-shaped professionals for career success is an important topic to explore. T-shaped professionals have deep disciplinary problem-solving skills and broad communications skills for improved teamwork and rapid learning of new areas.  T-shaped professionals have depth and breadth across six areas: Emerging technologies, work practices, developmental mindsets,  academic disciplines, societal systems, regional cultures . This talk will provide an overview of the past, present, and future of the T-shaped skills concept, with special attention to possible applications in Informatics curriculum development.

75. Innovation Incremental New Value(s) – Existing Unit(s) Example: Vehicles Kilometers/Kilowatt-Hour (Transportation) Radical New Value(s) – New Combination(s) of Existing Unit(s) Example: Smartphones Bits/Joule (Communications) Super-Radical New Value(s) – New Combination(s) with New Unit(s) Example: Goal-level of what percentage of the population, Online Commerce Trust/Future Prediction Accuracy (Computation); Mtrans . Exploration & Learning.

76. Next Generation: Future-Ready T-Shaped Adaptive Innovators Many disciplines Many sectors Many regions/cultures (understanding & communications ) Deep in one sector Deep in one region / culture Deep in one discipline

77. Future-Ready T-Shapes 9/19/24 © IBM UPWard 2016 84

78. Service science transdisciplinary framework 85 Entities Interactions Change (Outcomes) Value (Identity)

79. 9/19/24 87 1955 1975 1995 2015 2035 2055 Better Building Blocks

80. Domain of Science - The Map of Quantum Computing - Quantum Computing Explained https:// youtu.be /- UlxHPIEVqA

81. “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

82. 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 . 9/19/24 Jim Spohrer (2017) 91

83. 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.  9/19/24 Jim Spohrer (2017) 92

84. 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." 9/19/24 Jim Spohrer (2017) 93

85. Part 3: “Solving All Problems” 9/19/24 (c) IBM MAP COG .\| 94

86. 10 million minutes of experience 9/19/24 Understanding Cognitive Systems 95

87. 2 million minutes of experience 9/19/24 Understanding Cognitive Systems 96

88. 9/19/24 Jim Spohrer (ISSIP.org) 97 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

89. How, What, and Why? Inspiring AI upskilling (IA) 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 98

90. We get the future we invest in: AI tools to experiment with today #1 Magic Eraser #2 Craiyon #3 Rytr And GPT-3, ChatGPT , GPT-4, Bing #4 Thing Translator #5 Autodraw #6 Fontjoy #7 Talk to Book #8 This Person Does Not Exist #9 Namelix #10 Let's Enhance Thanks to @TessaRDavis for compiling this list: “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 99 Try at least two from the list as soon as possible What do you think? , DALL-E and Stable Diffusion Every person in a role in an organization is a service provider. 9/19/24

91. 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 100 Read enough of IfM and IBM (2008) to understand what a “Service Innovation Roadmap (SIR)” is – and who should be creating them. 9/19/24

92. Learning to invest Run = Routine Activities Transform = Copy Activities Innovate = Invent and Apply Activities 9/19/24 Jim Spohrer (ISSIP.org) 101 Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Technology Transform Innovate Invest in each type of change Ru n

93. 102 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

94. Better Models (Spohrer, Maglio, Vargo, Warg 2022) Increasing complex, interconnected world All models are wrong, some are useful Better models are needed of the world – both physical, social, virtual (science) people and win-win interactions (logics) organizations and win-win change (architecture) technologies (AI) Better models for better investing “We get the future we invest in, so responsible actors must learn to invest wisely and systematically in improved win-win interaction and change.” 9/19/24 Jim Spohrer (ISSIP.org) 103

95. 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] )

96. From Human-Centered to Humanity-Centered Design (Norman 2023) Human-Centered Design Solve the core, root issues, not just the problem as presented (which is often the symptom, not the cause). Focus on the people. Take a systems point of view, realizing that most complications result from the interdependencies of the multiple parts. Continually test and refine the proposed designs to ensure they truly meet the concerns of the people for whom they are intended. 9/19/24 Jim Spohrer (ISSIP.org) 105 Humanity-Centered Design Solve the core, root issues, not just the problem as presented (which is often the symptom, not the cause). Focus on the entire ecosystem of people, all living things, and the physical environment. Take a long-term, systems point of view, realizing that most complications result from the interdependencies of the multiple parts and that many of the most damaging impacts on society and the ecosystem reveal themselves only years or even decades later. Continually test and refine the proposed designs to ensure they truly meet the concerns of the people and ecosystem for whom they are intended. Design with the community and as much as possible support designs by the community. Professional designers should serve as enablers, facilitators, and resources, aiding community members to meet their concerns.

97. Predict the Timeline: GDP/Employee National Academy - Service Systems and AI 106 ( 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

98. 10 million minutes of experience 9/19/24 Understanding Cognitive Systems 107

99. 2 million minutes of experience 9/19/24 Understanding Cognitive Systems 108

100. Types: Progression of Models : Verified, Trusted, Wise Models = instruction_set of future: Better building blocks 9/19/24 Understanding Cognitive Systems 109 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

101. Resilience: Rapidly Rebuilding From Scratch Dartnell L (2012) The Knowledge: How to Rebuild Civilization in the Aftermath of a Cataclysm. Westminster London: Penguin Books. 9/19/24 Jim Spohrer (ISSIP) 110 Part 3: “Solving All Problems”

102. 9/19/24 Jim Spohrer (2015) 111 I have… Have you noticed how the building blocks just keep getting better?

103. Learning to program: My first program 9/19/24 Jim Spohrer (2015) 112 Early Computer Science Class: Watson Center at Columbia 1945 Jim Spohrer’s First Program 1972

104. “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

105. 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 . 9/19/24 Jim Spohrer (2017) 114

106. 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.  9/19/24 Jim Spohrer (2017) 115

107. 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." 9/19/24 Jim Spohrer (2017) 116

108. Part 3: “Solving All Problems” 9/19/24 (c) IBM MAP COG .\| 117