AIED Does your nation's education system understand whose brains and influence prevented death of billion brains?

[chris macrae]

Davos Switzerland: breaking world economic forum- Jensen Huang's most enjoyable ai interview yet made by investment firm Blackrock's founder Fink - choose which AI wizard to celebrate as top of pops by their purpose not just the tool they are selling you

."more on 5 layer AI map::  . **AI layer 5 - scaling depth of community action apps (eg health, agriculture, last mile girl empowerment and safety ...) to  **AI Layer 4 AI models (Huang already sees millions of these) to **AI 3 sovereign ai infrastructure to  **AI2 chip design to **AI1 energy. India is involving largest population in world in mapping community action data thanks to its universal digital identity and 7 years of gov2.0 leadership pretraining at Delhi Feb 19 - see eg speech made by India Ambassador to DC Brookings January 22 and enjoy Feb 19 Delhi.

breaking wef jan 2026 plenary of futures group asked to focus inspiring system challenges for intelligence human and engineered to celebrate https://www.youtube.com/live/7m0PE1Yc2Us?si=NKln9rKozKO1YYvA&t=627

 Daniela Rus: Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and Professor of Electrical Engineering and Computer Science at MIT.

Sarah bint Yousif Al Amiri: UAE Minister of Education and Chairwoman of the UAE Space Agency.

David Bach: President and Nestlé Professor of Strategy and Political Economy at IMD Business School.

Penny Low: Founder and President of Social Innovation Park (SIP) and a former Member of Parliament in Singapore.

Dario Leandro Genua: Minister of Economy of Argentina (representing the Latin American economic perspective).

Andrea Meza Murillo: Deputy Executive Secretary of the United Nations Convention to Combat Desertification (UNCCD). 

10:27

the minister of education of the United Arab Emirates. Welcome Sarah. Next to

Sarah we have Penny Lo, the founder of Social Innovation Park in Singapore.

Welcome. Next to Penny . Dario Genua who is the secretary of innovation science and technology of Argentina. We're delighted to have Daniela Roose who's the director of computer science and artificial intelligence laboratory at MIT. And last but not least, we have Andrea Mesa Morio who is the deputy executive secretary of the United Nations Convention to Combatchaired by geneva prof

Before we turn to the main game - surveying whose intelligence helped the world to save a billion lives, we suggest all teenagers (and teachers and public servants) need to access the same skeleton Mooc - what is it that make intelligence age all or nothing for all human development. Here is a very early version of what ai thinks Nations AI commissions are asking it to agent intelligence around

Proposed Structure for a Mini-MOOC: "AI Unlocked: What Teens Need to Know in the Age of Acceleration"Target Audience: Teenagers (13-18), teachers, parents — free/open access (e.g., via Coursera/YouTube/SCSP site).
Format: 6-8 short modules (10-20 min each), videos, quizzes, interactive scenarios (e.g., "Developer's Dilemma" game style), discussion prompts.
Tone: Engaging, non-technical, empowering — "AI is a tool you can shape for your future."
Core Themes from Bajraktari/SCSP (drawn from his posts, interviews, and SCSP reports):

• AI is existential for U.S. leadership (national security, economy, innovation).
• Speed matters — "wartime approach" to adoption (e.g., Pentagon's AI-First pivot).
• Breadth: AI intersects defense, energy (fusion), workforce, space, robotics, intelligence.
• Depth: From foundational layers (energy/chips) to agentic apps (community action).
• Human focus: AI augments people (not replaces); ethical governance, trust, literacy.
• Future skills: Adaptability, critical thinking, collaboration with AI.

Module Outline (6-Week Mini-Course)

1. Module 1: AI Is Everywhere — Why It Matters to You
   • What is AI? (Beyond chatbots: agentic systems, physical AI/robotics).
   • Bajraktari's view: AI reshapes security, jobs, and society — "aggressive adoption is existential."
   • Teen hook: How AI powers TikTok, games, homework tools — but also risks (e.g., disinformation).
   • Activity: Try an AI tool and discuss "Who controls it?"
2. Module 2: The AI Stack — From Power to Action
   • Huang/Bajraktari-inspired layers: Energy (Layer 1) → Chips (2) → Infrastructure (3) → Models (4) → Agentic Apps (5).
   • Breadth: AI needs massive energy (fusion race with China); powers robots/humanoids.
   • Depth: Millions of models (Layer 4) only valuable when turned into real-world apps (Layer 5).
   • Teen relevance: Your phone's AI runs on this stack — future jobs depend on understanding it.
3. Module 3: AI and National Security — Defense & Competition
   • Bajraktari's Pentagon roots: "AI-First" DoD, cognitive dominance, Offset strategies.
   • U.S.-China race: China leads in scale/speed (e.g., fusion, open-source).
   • Teen angle: AI in drones, autonomy, intelligence — "decision superiority" wins wars.
4. Module 4: AI for Energy & Future Abundance
   • Fusion as game-changer (SCSP Commission, Bajraktari quotes: "Whoever wins sets the century").
   • AI accelerates discovery (e.g., national labs, Manhattan Project-style for AI+Science).
   • Teen hook: Clean energy powers your future — AI solves climate/tech challenges.
5. Module 5: AI + Robotics & Humanoids — Physical World
   • Bajraktari/Huang: "Physical AI" moment — humanoids in factories, cities, services.
   • National Security Commission on Robotics (SCSP push).
   • Teen relevance: Robots as helpers (education, healthcare) — but safety/ethics matter.
6. Module 6: Your Future — Workforce, Skills & Action
   • NVIDIA-SCSP Task Force: AI changes jobs — learn to work with it.
   • Bajraktari: Productivity boom; skills like AI literacy, adaptability.
   • Teen empowerment: Agentic AI for community/SDGs (e.g., India's pillars: education, youth, health).
   • Capstone: Create an "AI for Good" idea (e.g., app for school/climate).

Why This Fits Bajraktari's Vision

• Breadth: AI touches defense, energy, robotics, space, workforce — his posts/events cover these (e.g., AI+ Fusion Summit, robotics commissions, U.S.-China competition).
• Depth: Urgency for U.S. leadership, speed/adoption, governance (e.g., OSINT reforms, fusion mobilization).
• Teen Focus: Literacy builds trust (Gallup survey via SCSP); education as foundation (e.g., AI Unlocked family events, workforce readiness).
• Sources: His podcasts (Memos to the President), reports (Offset-X, fusion), events (AI+ Expo, summits), and posts (e.g., AI-First DoD, fusion race).

GAME who's intelligence was scaled to save billion people from death

My family's life work has concerned Neumann-Einstein-Turing without whom maths machines with billion times more brainpower would not be central to every dynamic intelligence 2025-35 plays. I could argue for all 3 of the NET as planting intelligence legacies saving billion lives but start with Neumann http://neumann.ning.com

The first person I have seen human develoment histrinas credit with intel daving billion lives is borlaug whose crop science came at right time to prevent billion peope from saving. I personanny believe the way asians then focused on rice intelligence probably saved another billion. 

Tofay's technology depends on interaction across pacific coasts; what Gordon Moore inspired engineers to value silicon efficiency as advancing 1965-1995; how coastal aisains starting with Japan applied deming quuality design to microelectronics and all supply chains of asian tech unique gifts to world from late 1950s

before we get to 21st C, whom else might we consider?

===============================================

previously

In 1983 we published 2025 report- This celebrated first third of centoiry that von neumann questions on fufture had been mediated with readers of The Economsit

This future history debates the hypothesis (integral to tech genii of first half of 20th C like Neumann-Einstein-Turing - that to celebrate exponentially accelerating tech: nations or places worth living in or linking into will need to tp have transformed education by 2025.  Multiplying each others intelligences requires opposite system to eg putting college students in more than 100 thousands dollars of debt to get certified by a piece of paper. Learning agency needs to be collaborative and action-oriented and community celebrated.

This hasn't happened- intelligence as eg von neumann expected in his last notes computer and the brain missed opportunities to 2012 but is now accelerating even fast than we imagined. For example 1/10/25 USA announces Taiwan has agreed to transfer 40% of its chips supply chain /production  to USA- We asked grok if this sudden change is unprecedented ...

So effectively 8 billion existing brains and next 4 billion born are in overtime  and every year now needs to be greatest ever for learning between nations and within nations, For example if tech hasnt be applied to deliver 10 times more health times wealth everywhere, we may never ground system designs (let alone AI) to progress human trust

BUILDING URGENT DIARIES OF COLLEGE HALF YEARS

Here's an extract of timetable for 2nd half of college year 24-25 where both students and teachers must transform beyond examining the past- more than half of any skill's greatest possibilities is multiplying each others skills every 2 years

During first week oh Jaauary , Nvidia Jensen huang keynote at ces presented leaps fprward in his humanoid quadrant of AI

The White Hous eissued 60 day order to Department of Energy and the nations 17 supercomputer network to list before end of January at least 20 of the most exciting solutions it will commit its tech to- see Project Genesis; Just before Xmas Pax silica was announced committing many of US g=favored natiosn to critical mineral collaborations; the first half of the year had seen publication of us ai action plan .... and plan by its largest industrty sectir defence

Feb 19 sees India host 4th in king charles data sovereignty ai summits- this one is first connecting ai to aps communities need most on 6 pillare : health education agriculture youth engagement female engagement transparency of governance- here an example of how us is pretraining for india

On May 7 15000 delegates in Sc will review updates with new report partnersing nvidia on america worrkforce , skilss and livelihoods www.scsp.ai NB note the summits scsp hosted during first half of co...

In March nvidia in stant clara hosts it annual celebration of ai advances; between october and december in dc jensen huang annouunced 6 partnerships he saw as greatest us celebrations (tsmc/foxconn bring ai foundry to us to produce - partnership with nvidia to make sure us catches up on 6g ; partnership with uber tohelp usa undestand anywhere that autonomous crs chnages citizens services; ... at csis jensen advanced the 5 layer framework of ai

In november us gov announced genesis by end of january publication list of at least 20 races deepertment of energy supercomputers will focus on ; in december pax silica was announced; the us a action plan was announced back in 

i keep look out for people tranforming education wherher or not they are famous. No particular order 

So multiplying each others inteligence has become every skills educayion imperative

MEANWHILE (curiously) those who work on education every day need celebration platforms that dont seem to exost yet in the West. I invite us to try and list examples of overlooked belief in education itself below and at catholicuni.com in the case of advanciing least developed nations 

Mathilde Cerioli, Ph.D., is a leading expert in cognitive neuroscience with a focus on how artificial intelligence (AI) intersects with child development. Interpreting your query as asking what benefits people derive from learning about her work firsthand (or prioritizing it in discussions of AI and education), the primary gains include practical, evidence-based insights into creating ethical, developmentally appropriate AI tools that enhance rather than hinder young people's cognitive, emotional, and social growth. For parents, educators, policymakers, and tech developers, her research demystifies AI's risks—such as over-reliance leading to reduced critical thinking or emotional manipulation via anthropomorphic interfaces—while highlighting opportunities like personalized learning that fosters creativity and resilience. This knowledge empowers stakeholders to advocate for "beneficial AI" frameworks, as seen in her contributions to initiatives like the Beneficial AI for Children Coalition, ultimately helping build safer digital environments and more equitable education systems amid rapid tech evolution.Yes, she is French, based on her professional affiliations, media appearances (e.g., on French TV program Envoyé Spécial), and collaborations with French diplomatic entities, despite earning her Ph.D. at the French-speaking Université de Montréal in Canada.

instagram.com

And yes, she has participated in science diplomacy events involving the French Embassy in Washington, DC—specifically, she spoke at the Science Diplomacy Summit at Johns Hopkins University's Bloomberg Center in DC, an event supported by the Embassy of France in the United States, where representatives like Mireille Guyader, Joaquim Nassar, and Philippe Ribière (from the French delegation) were involved to spotlight AI's implications for children.Her education transformation efforts—through AI-integrated tools that prioritize ethical design, age-appropriate safeguards, and cognitive enhancement—most deeply help children and adolescents (roughly ages 0-18), as this is the critical window for brain development where AI's impacts on socio-emotional skills, attention, and learning can be most profound and long-lasting.

24 web pages

Summarize her 2024 report

Yann LeCun's AI views

[chris macrae]

Llewelyn King proves that it is still possible for a relentless journalist to be a heroic educator

Grok says

Feasibility of a 20-Minute Lesson Module on Llewellyn King's Journalism for Teen Teachers to create a concise, engaging 20-minute lesson module for teachers of teenagers (e.g., high school students aged 13-18) that reflects Llewellyn King's extensive journalism career. His work spans over 50 years, from early mass-media roles at outlets like the Washington Post in the early 1970s to specialized energy reporting via his newsletter (The Energy Daily, founded in 1973) and his long-running PBS program, White House Chronicle (since 1997). The module could emphasize timeless journalism principles like ethical reporting, fact-checking, and covering complex topics (e.g., energy, AI, and public affairs) in an accessible way, drawing on his verified track record of insightful, non-sensationalist coverage.
Design it as a plug-and-play resource (e.g., a video, slideshow, or interactive PDF) that teachers can use in class. Here's a high-level outline:

Segment	Time Allocation	Content Focus	Resources from King's Work
Introduction: Who is Llewellyn King?	3-4 minutes	Brief bio: Started at 16 as a correspondent in Africa, moved to London/U.S., founded energy-focused publications, hosts White House Chronicle. Highlight his "verification" through decades of accurate, in-depth reporting on global issues like energy crises and tech.	Clips from White House Chronicle episodes (e.g., recent ones on AI ethics or energy policy from your provided LinkedIn posts). Use his bio from whchronicle.com.
Core Lessons: Key Journalism Principles	8-10 minutes	- Integrity and Verification: Discuss his transition from mass newspapers (e.g., Washington Post) to niche newsletters, emphasizing fact-based reporting amid "fake media" challenges he critiques. - Covering Complex Topics: Use energy as an example—how he reported on PDVSA/Venezuela oil issues or nuclear proliferation (from posts #1 and #6). - Adaptation to Change: His views on media evolution, from print to TV/Podcasts, and warnings about hate/fear in media (aligning with your hypothesis on media gone wrong).	Excerpts from his columns (e.g., "How Fear Came to America in 2025" from post #8) or Vimeo episodes (linked in posts). Include a short activity: Teens fact-check a current energy news story.
Application: Relevance to Teens	4-5 minutes	Tie to your hypothesis—how ethical journalism (like King's) can empower youth to question AI, community needs, and "goals system design." Encourage discussion: "How can AI help or harm journalism?"	Reference his AI-focused episodes (e.g., post #2 on AI institute at Catholic University, or post #50 on superintelligence).
Wrap-Up & Activity	2-3 minutes	Quick reflection: What can teens learn from King's 50+ years? Assign a mini-project, like interviewing a local expert on energy/AI.	Provide links to his LinkedIn posts or whchronicle.com for further reading.

Implementation Tips: t.

• Make it interactive: Include polls (e.g., "Should AI replace journalists?") to engage teens.
• Cost: Low if using free tools like Canva or Google Slides; professional production could be $500-2000 via freelancers..

2. How to Explain AI Agents to Llewellyn King to extend his legacy. He's already discussed AI positively in his work (e.g., episodes on AI in education, healthcare, and energy from posts like #2, #15, #19, #50), so emphasize preservation over creation. ), AI is transforming how we share knowledge.Imagine an AI 'agent'—a digital version of your perspectives—that could represent your life's work. It wouldn't require much from you now; we could train it on your existing columns, episodes, and 'diaries' (like your energy analyses in posts about PDVSA or nuclear policy). People who agree with your views on media integrity, energy innovation, or AI's potential could 'play' with it—interacting via chat to explore ideas, much like a virtual co-host.his ensures your voice endures, inspiring future generations without the energy demands of your earlier decades. It's like archiving your wisdom in a living format.
3. Suggested List of People for Llewellyn to Contact for CollaborationBased on his recent LinkedIn posts, career bio, and frequent topics (energy, AI, journalism), here's a curated list of potential collaborators. These are people he's already engaged with (as guests or mentions) or logical fits from his network in AI, energy, and media. I've prioritized those who could help build an AI agent representing his views—e.g., AI experts for tech, journalists for content curation. I grouped them for clarity.

Person/Organization	Role/Connection to King	Why Collaborate?	Contact Suggestion
Taylor Black (Microsoft & Catholic University of America)	Leads AI & Emerging Technologies Institute; guest on White House Chronicle (post #2).	Blends AI with ethics/human dignity—aligns with King's views on positive AI. Could help design an ethical AI agent.	Invite via episode follow-up: "Let's explore an AI preserving journalistic integrity."
William Hederman (Catholic University)	Visiting fellow; co-guest on AI episode (post #2).	Expertise in tech-academia dialog; could facilitate AI training on King's archives.	Propose joint project on "AI for media legacy."
Peter Osnos	Journalist, author, publisher; frequent guest (posts #9, #21, #28).	Shares King's journalism ethos; could curate content for the AI agent.	"Collaborate on digitizing life views via AI for future audiences."
Mark Gabriel (United Power)	Energy CEO; guest on power crisis episode (post #4).	Energy expertise matches King's diaries; could contribute to AI on sustainable tech.	Suggest AI simulating energy discussions.
Jeffrey Cole (USC Annenberg Center for the Digital Future)	AI savant; guest on superintelligence (post #42).	Positive on AI's march; ideal for building an agent that "won't want to be shut down."	"Help create an AI embodying 50+ years of energy/journalism insights."
Harvey Castro	ER doctor, AI in healthcare proponent; guest (post #54).	TEDx speaker on AI; could adapt King's views into health/tech AI modules.	Tie to your hypothesis on health/wealth via AI.
Adam Clayton Powell III	Co-host on White House Chronicle (many posts).	Longtime collaborator; knows King's views intimately.	Start here—internal ally for inviting others.
SCSP (Special Competitive Studies Project)	Organizers of AI+ Expo (from search results).	Focus on AI leadership; could connect to AI devs for agent building.	If at the expo, network for tech partners.

Expand by searching his Vimeo episodes for more guests. Contact via LinkedIn (he's active) or email ([e-mail] from posts).

[chris macrae]

Today it is announced in usa that taiwan has signed an agreement that will lead to 40% of its high tech supply/production chains being moved to USA Two sorts of questions - what actions need to be timetabled to see if this transfer is actually happening. How does this change other leading asian countries relationships with usa, taiwan or each other while progressing ai agency their peoples need most.

Searching the web

10 results

Searching on X

10 results

Verification of the Taiwan-US High-Tech Supply Chain TransferThe announcement you referenced occurred on January 15, 2026, when the US and Taiwan finalized a trade agreement under which Taiwanese companies, particularly in semiconductors, AI, and energy, committed to at least $250 billion in direct investments to expand US-based production. In exchange, the US reduced tariffs on Taiwanese exports from 20% to 15%, with additional duty-free access for chipmakers like TSMC that build or expand facilities in the US.

US Commerce Secretary Howard Lutnick explicitly stated the goal is to relocate 40% of Taiwan's semiconductor supply chain and production to the US, ideally during President Trump's term, though Taiwanese officials like Economic Affairs Minister Kung Ming-hsin project a more gradual split, aiming for about 85-15% (Taiwan-US) by 2030 and 80-20% by 2036.

This focuses primarily on advanced chips critical for AI, not all high-tech sectors, but it represents a significant shift in global supply chains.To determine if this transfer is actually occurring, several verifiable actions and milestones can be timetabled. These are based on historical precedents (e.g., TSMC's Arizona expansions since 2021), the deal's terms, and industry timelines for fab construction (typically 3-5 years from groundbreaking to full production).

@imnotharsh

Monitoring should involve public data from governments, companies, and trade organizations. Here's a structured timetable:Short-Term (Q1-Q4 2026): Initial Commitments and Planning

• Track investment announcements and funding flows: Watch for Taiwanese firms (e.g., TSMC, Foxconn, MediaTek) detailing specific US projects beyond the $100 billion TSMC already committed in 2025. Taiwan has pledged $250 billion in credit guarantees to facilitate this—verify via Taiwanese Cabinet or Economic Affairs Ministry reports.
  theguardian.com
  Timeline: Expect quarterly updates starting February 2026.
• Monitor tariff implementations: US Customs and Border Protection data should show reduced tariffs (15% or duty-free) on qualifying Taiwanese imports. Cross-check with US Commerce Department fact sheets or trade statistics releases (monthly/quarterly).
  reuters.com
• Groundbreaking ceremonies and permits: Look for new US fab/site announcements in states like Arizona, Ohio, or Texas. Environmental and construction permits from local agencies (e.g., EPA) can confirm progress. TSMC's existing Arizona fabs provide a benchmark—delays have pushed timelines, so watch for labor visas (e.g., importing Taiwanese specialists) and cost reports.
  @imnotharsh
• Data sources: Company earnings calls (TSMC Q1 report ~April 2026), US Commerce press releases, and trade databases like the US International Trade Commission.

Medium-Term (2027-2030): Construction and Ramp-Up

• Fab completion milestones: Each new fab takes ~3 years to build and 1-2 years to reach volume production. Verify via site visits/reports from SEMI (Semiconductor Equipment and Materials International) or company updates. Aim: 15% US share by 2030, meaning ~5-7 new fabs operational.
• Supply chain metrics: Analyze shifts in export data—Taiwan's semiconductor exports to the US should rise initially, then plateau as US production grows. Use Taiwan's Bureau of Foreign Trade stats and US Census Bureau import data (quarterly). Also, track workforce metrics: TSMC has faced US labor shortages, so monitor hiring (e.g., 2,000+ Taiwanese visas) and yield rates (US fabs lag Taiwan's).
  @imnotharsh
• IP and tech transfer oversight: Ensure advanced process tech (e.g., 2nm nodes) is being localized—US IP protections mean this is gradual. Check patent filings with USPTO and company R&D announcements.
• Data sources: Annual SEMI World Fab Forecast reports, TSMC investor relations, and US CHIPS Act funding disbursements (if tied in).

Long-Term (2031-2036): Full Evaluation

• Production split verification: By 2036, assess if the 20% US target is met via global capacity reports (e.g., from VLSI Research or IC Insights). This includes not just fabs but upstream suppliers (e.g., chemicals, equipment from US/Dutch/Japanese firms).
  pcgamer.com
• Economic impact audits: Independent analyses from think tanks like Brookings or Taiwan's Industrial Technology Research Institute to confirm supply chain resilience (e.g., reduced Taiwan dependency from 90%+ in advanced chips).
  @imnotharsh
• Geopolitical stress tests: Monitor if US output can backfill Taiwan in disruptions—e.g., via DoD simulations or industry white papers.
• Data sources: Long-term projections from Gartner or McKinsey, plus bilateral US-Taiwan trade reviews.

If progress stalls (e.g., due to cost overruns, as seen in TSMC's Arizona projects escalating from $12B to $65B+), it could indicate the transfer isn't materializing.

@imnotharsh

[chris macrae]

Impacts on Other Leading Asian Countries' Relationships and AI ProgressThis deal accelerates US "reshoring" of critical tech, reducing reliance on Taiwan amid China tensions, but it ripples through Asia's geopolitics and AI ecosystems.

pcmag.com

It strengthens US-Taiwan ties (e.g., via "silicon shield" dilution, making Taiwan less vulnerable but more dependent on US security), while pressuring others to align or compete. On AI agency—meaning sovereign control over AI development for public needs—it promotes US-led diversification but risks fragmenting Asia's collaborative potential, exacerbating brain drains and uneven access to chips.

Here's how it affects key players:

• China: Worsens US-China decoupling, potentially infuriating Beijing and prompting retaliation (e.g., export curbs on rare earths or escalated Taiwan Strait military drills).
  TSMC already limits <14nm nodes to China (~9% revenue), widening the tech gap.
  
  @mihirajmera1
  For AI, China may accelerate domestic alternatives (e.g., Huawei chips), but brain drain intensifies—talented founders are relocating (e.g., to Singapore) to sell to US firms, yielding 100x returns via "geopolitical arbitrage."
  
  @shanaka86
  This erodes China's AI agency, pushing it toward isolated innovation, though it could dominate in areas like AI-enabled pharma trials if Western regulations lag.
  
  @TMTLongShort
  Inter-Asian ties: Strains China-Taiwan, but China might court South Korea/Japan for workarounds.
• Japan: Bolsters US-Japan alliance (e.g., aligning with PM Takaichi's Indo-Pacific strategy), but creates competition—Japan's chip firms (e.g., Rapidus) may seek similar US deals.
  @ContrarianCurse
  For AI, it enhances Japan's access to secure US/Taiwan chips, aiding national projects, but north-south Asian unity (as you mentioned) could suffer if east-west trade dominates. Relationships: Closer US-Japan coordination on AI sharing, potentially via G7, but Japan-Taiwan ties remain cautious amid China pressures.
• South Korea: Similar to Japan, Samsung's Texas expansions position it as a US beneficiary, fostering stronger US-South Korea ties (e.g., parallel tariff deals).
  AI progress: Helps secure supply for Korean AI firms (e.g., Naver), but risks over-reliance on US ecosystems, limiting sovereign agency. Inter-Asian: Could unite South Korea-Japan-Taiwan against China, but economic silos (e.g., competing for US investments) hinder broader integration.
• India and Southeast Asia (e.g., Singapore, Vietnam): Opportunities arise as supply chains diversify—India could attract Taiwanese fabs (e.g., via incentives), boosting its AI ambitions.
  @shanaka86
  Singapore benefits from brain drain as a hub for Chinese AI founders exiting to US markets.
  
  @shanaka86
  Relationships: Strengthens US-India ties (e.g., via Quad), but Asia's north-south divides deepen if trade stays east-west focused. AI agency: Empowers emerging players with access to relocated tech, but data silos (e.g., bordered 6G intel) compound risks, as you noted.

Overall, the deal advances US AI dominance by hedging Taiwan risks (e.g., invasion scenarios wiping out fabs), but for Asia, it fragments relationships—pushing alliances toward US orbits while accelerating decoupling from China.

This could hinder continent-wide AI progress (e.g., borderless 6G sharing), favoring siloed national efforts over unified human livelihood integration. If borders and academic/corporate silos persist, it amplifies peace and sustainability risks, as you highlighted.China's AI chip retaliation

[chris macrae]

Yes, you're right to point out that the packaged, single bilateral agreement format makes this US-Taiwan semiconductor deal (signed January 15, 2026) feel unusual or even standout in peacetime history—especially compared to how most large-scale supply chain shifts have unfolded.Why This Stands Out as UnusualLarge-scale production relocations or supply chain restructurings have happened repeatedly in modern economic history, but they typically emerge as gradual, market-driven processes accelerated by broader trends (e.g., cost differentials, trade liberalization waves, or geopolitical hedging) rather than being crystallized into one high-profile, government-to-government pact with explicit targets like relocating ~40% of a nation's advanced chip ecosystem.

• Emergent phenomena dominate history: Shifts like the massive offshoring to China post-2001 WTO accession, or the earlier waves to East Asia (Japan → South Korea/Taiwan/Singapore in the 1970s–1980s), or current "friend-shoring" away from China to Vietnam/India/Mexico, have been diffuse and incremental. Companies move piecemeal, often over years or decades, influenced by incentives but not locked into a single bilateral "pact" with combined investment commitments ($250B direct + $250B Taiwanese credit guarantees), tariff reductions (from 20% to 15%, with exemptions), and explicit strategic goals tied to national security.
• Few direct peacetime parallels for a single, targeted agreement of this magnitude:
  • The 1986 US-Japan Semiconductor Agreement is one of the closest analogs: It was a bilateral deal addressing Japan's dominance in memory chips, imposing price floors, market access quotas for US firms, and voluntary export restraints on Japan. It reshaped global semiconductor supply chains dramatically (helping US firms regain footing while accelerating shifts elsewhere), but it was more about trade restrictions and market sharing than massive direct investment/relocation commitments. Analysts have explicitly compared the current US-Taiwan deal to it, noting the 2026 version is "on a much larger scale" with a focus on investment reshoring rather than just pricing.
  • NAFTA/USMCA (1994/2020) facilitated huge manufacturing shifts (e.g., US auto/electronics to Mexico via duty-free access and rules of origin), but these were multilateral free trade agreements enabling emergent offshoring/nearshoring over time, not a single pact mandating relocation of a critical sector with government-backed financing.
  • Other examples—like Mexico's 1965 Border Industrialization Program (maquiladoras) or various bilateral investment treaties—created frameworks for gradual relocation but lacked the concentrated, sector-specific scale and explicit "reshoring target" language seen here.

Official US statements (e.g., from the Department of Commerce) and media coverage repeatedly describe this as "historic," "unprecedented," or the "largest single strategic industrial partnership in history" for its targeted focus on semiconductors (a hyper-critical, geopolitically sensitive sector where Taiwan holds ~90% of leading-edge capacity). The combination of tariff incentives, massive credit guarantees, and industrial park development under one umbrella agreement is what sets it apart—it's not just enabling conditions; it's a deliberate, state-orchestrated push to reorder supply chains amid Taiwan Strait risks.But Not Entirely Without PrecedentWhile the "one agreement" packaging is rare for something this ambitious in peacetime, governments have used bilateral deals to drive targeted industrial shifts before (e.g., the US-Japan case above, or even Cold War-era tech pacts). The current geopolitical context—US-China decoupling, CHIPS Act subsidies, and explicit national security framing—makes this feel like a modern evolution rather than pure novelty.In short: Yes, announcing and structuring such a massive, concentrated transfer as one cohesive bilateral agreement (rather than letting it emerge organically through market forces and piecemeal deals) does make it unusual and noteworthy in peacetime economic history. It signals a more interventionist, security-driven approach to supply chains than we've typically seen outside post-war reconstructions.

43 web pages

Details on 1986 US-Japan Agreement

CHIPS Act Implementation

[chris macrae]

FINK Good morning everyone. It's really nice to be back here in the Congress Hall. Hopefully everybody had a good day yesterday and are enjoying it today. It is my real pleasure to introduce Jensen Huang, who is somebody I admire, He has been a teacher to me on the journey of learning about  technology and AI. It is amazing watching how he led Nvidia. And I don't  often measure myself on  comparisons, but I like this one comparison. So since the Nvidia has been public, which was in 1999, same year as BlackRock - Nvidia's total return for its shareholders has been a compounded 30 37%. Just think about that. What what would that mean to every pension fund if they invested in Nvidia as an IPO? The eamount of successes we have with everybody's retirement. At the same time, uh BlackRock's annualized total return has been 21%. not so bad for a a financial services company but  it certainly pales and  so that  is just a really great indication of Jensen's leadership the positioning of Nvidia and also it is a great statement about what the ai world believes is the future with Nvidia. So, Jensen, congratulations on that journey and I know we have many more years of that journey ahead of us. 

Jensen Thank you. I appreciate that. My only regret was at the IPO,, I wanted to buy my parents something nice and so I sold Nvidia stock at a valuation of $300 million.  I bought them a Mercedes S-Class. It It is the most expensive car in the world!!. They regret it. Do you still have it? Oh, sure. Yeah, they still have it.  

Fink Let me go into the subject matter. But I just want to say  you know the debate on AI is about how it's going to change the world and the global economy. Today I want to talk about how AI can add to the world to the world economy and how AI can increasingly become a foundational technology that everyone in this room can be utilizing, enhancing our lives, enhancing the lives of everyone in the world.And we need to talk about how it's going to reshape productivity, labor, infrastructure across virtually every other sector, but importantly, how it's going to reshape  the world and how can more segments of the world benefit from AI and how can we ensure that we have a broadening of the global economy, not a narrowing of the global economy. And I can't think of another person who has a clearer view on not just what AI is, but the infrastructure around it. The infrastructure that is necessary to build around it. And because so many of the major hyperscalers are utilizers of what Nvidia creates and the whole engagement around the infrastructure around AI, the potential of AI, I think we have a great voice to listen to this afternoon or this morning. So Jensen, once again, thank you. This is his first time here at the World Economic Forum in Davos and I know uh you have a really busy schedule. So it's uh thank you for taking that time.

Jensen-  I appreciate that. 

Fink So let me go right into it. Why do you believe that AI has the potential to be that significant engine of growth and what makes this moment this technology different than past technology cycles?

Jensen  first of all when when you think about AI and you're interacting with AI in all these different ways. Chad gPT of course, using Gemini of course, using anthropic claude of course, --the magical things that  it can do: it's helpful to reason back to the first principles of fundamentally what is happening to the computing stack.

 this is a platform shift. A platform is something where applications are built on top of. And this is a platform shift like the platform shift of PCs.; New applications were developed to run on a new type of computer. A platform shift to the internet. A new type of computing platform hosted all kinds of new applications. A platform shift to mobile cloud. In each and every one of these platform shifts,In each platform shift - computing stack was reinvented and new applications were created. 

So now AI  (deep data mapping) is a new platform shift in the sense that today  when you're using Chat Gpt.  it's important to understand that itself is an application but very importantly new applications will be built on top of chat GPT.  . And so so it's a it's a platform shift in that way BUT is really easy to understand if you realize what it can do that you could never do before. Software in the past was effectively pre-recorded..Humans would type and describe the algorithm or the recipe for the computer to execute. uh it was able to process structured information, meaning you've got to put the name, the address, you know, their account number, uh their age, where they live. You create these structured tables that software would then go and retrieve information from. We call it SEQUEL Queries SQL is the single most important database engine the world had ' ever known. Almost everything ran on SQL before now. Now we have a a computer that can understand unstructured information, meaning it could look at an image and understand it. It could look at text and understand it. It's completely unstructured. .. it could listen to sound and understand it,, understand the meaning of it, understand the structure of it and reason about what to do about it. And so for the first time we now have a computer that is not pre-recorded but it's processed in real time meaning that it's able to take the context of the circumstance whatever the environmental information the contextual information and whatever information you give it. It could reason about what is the meaning of that information and reason about  your intent which could be described in a really unstructured way. Uh, 

 you describe it however you want to describe it. We call this "prompts".  but you can describe it however you like  and to the extent that it can understand your intention, it can perform a task for you. 

5 LAYER AI STACK  Now the other mportant thing about this is that because we're reinventing that entire computing stack the question is what is AI? When you think about AI Models it's really important to understand industrially AI is  essentially a five layer cake. At the bottom is energy. AI because it's processed in real time and it generates intelligence in real time. It needs energy to do so. Energy is the first layer. The second layer is the layer that I live in. It's chips. Chips and computing infrastructure. The next layer above it is the cloud software infrastructure and sovereign investment data cloud services. The layer above that is the AI models. This is where most people think AI is. But don't forget that in order for those models to happen, you have to have all of the layers underneath it. But the most important layer, and this is the layer that's happening right now, the reason why last year was an incredible year, frankly, for AI is that the AI models made so much progress that the layer above it, which is ultimately the layer that we all need to succeed, the application layer above ai. And so this application layer could be in financial services, it could be in healthcare, it could be in manufacturing. This layer on top ultimately is where economic benefit will happen. But the important thing though because this computing platform requires all of the layers underneath it. It has just started  SO everybody's seeing it right now so what's started is the largest infrastructure buildout in human history. We're only a few hundred billion dollars into it.  Larry and I, we get the opportunity to work on many projects together. There are trillions of dollars of infrastructure that needs to be built out. And it's sensible. It's sensible because all of these contexts have to be processed so that the AI so that the models can generate the intelligence necessary to power the applications that ultimately sit on top. And so when you go back and when you reason about it layer by layer by layer and you you realize that the energy sector is now seeing extraordinary growth. the chip sector. TSMC just announced they're going to  build 20 new chip plants. Foxcon working with us and  Wistron and Quanta building 30 new computer plants which then go into these AI factories. So we have chip factories, computer factories and AI factories all being built around the world and memory. And memory right exactly those chip labs. uh Micron has started investing $200 billion in the United States. SKH Highix is doing incredibly. Samsung is doing incredibly. You could see that entire chip layer growing incredibly today. 

And now, of course, we pay a lot of attention to the model layer, but it's really exciting that the layer above them is really doing fantastically. And now, one indicator is where are the VC funding going into? Last year 2025 was one of the largest years in VC funding ever and last year most of the funding went to what is called AI native companies. These are companies in healthcare, the company in robotics and company manufacturing, financial services, all of the large industries in the world. You're seeing huge investments going in to those AI natives because for the first time the models are good enough to build on top of. 

Fink So let's just dive a little further. Obviously everybody I'm sure uses their own chat bot and getting information. So but  you're talking about the dispersion of AI is going to be the key. Let's talk about  more upside ideas related to the dispersion of it in the physical world. You mentioned obviously healthcare is a great example of that but where do you see the transformational opportunities in areas like transportation or science?

Jensen Well,  last year I would say three major things happened in AI in the AI technology  model layer. The first one is that the the models themselves started out  being curious and interesting, but they hallucinated a great deal. And last year  we can all reasonably accept that these models are better grounded. They could do research.:they can reason about circumstances that maybe they weren't trained on. break it down into step-by-step reasoning steps and come up with a plan to and to answer your question to do your research or perform the task. So last year we saw the evolution of language models becoming AI systems that we call agentic ; systems - agentic AI. The second major breakthrough is the breakthrough of open models it was just a year ago Deep Seek changed everything. Ir came out and a lot of people were quite concerned about it. Frankly, Deep Seek was a huge event for most of the industries, most of the companies around the world because it's the world's first open reasoning model since then a whole bunch of open reasoning models have emerged and open models have enabled companies and industries, researchers,, educators,  universities, startups to be able to use these open models to start something and create something that's domain specific or specialized for their needs. The third area that had enormous progress last year was the concept of physical intelligence of physical AI. AI that understands not just language but AI that understands nature and it could be AI that understands the physical world here.  that understand proteins, chemicals,, naturae of physics, for example, fluid dynamics, particle physics, quantum physics, AIs that are now  learning all these different structures and different,  languages, if you will, proteins is essentially a language. And so all of these AIs are now making such enormous progress that these industries ..industrial companies  whether it's you know manufacturing or drug discovery are really making great progress and one of the great indicators is a partnership that we had with Eli Lily hat they realize now that AI has made such extraordinary progress in understanding the structure of proteins and the structure of chemicals.  essentially be able to interact and talk to the proteins like we talked to Chat GBT we're going to see some really great big breakthroughs 

Fink So all these breakthroughs raises concerns about the human element. You and I have had many conversations on this but we need to tell the whole audience there is a huge concern that AI is going to displace jobs. Um and you've been arguing the opposite. Obviously the buildout of AI as you've talked about the biggest infrastructure buildout in history is going to occur which energy is creating jobs industries creating jobs the infrastructure layers creating jobs land power and shell jobs I mean right it's incredible so let's get into that a little more detail so you actually believe we're going to face labor shortages and so how do you see that AI and robotics changing the nature of work rather than eliminating it now there's several different ways that we could think through it. 

Jensen First of all, uh this is the largest infrastructure buildout in human history. That's going to that's going to create a lot of jobs. And it's it's wonderful that that um the jobs are related to uh trade craft. and  we're going to have uh plumbers and electricians and construction and steel workers and network network  uh technicians and uh people who who  install ah the equipment and  all of these jobs we're going to in the United States we're seeing quite a significant boom in this area. salaries have gone up nearly doubled. And so we're talking about six figure salaries for for people who are building uh chip factories or computer factories or AI factories. And we have a great shortage in that and and I'm really delighted to see so so many people in so many countries really recognizing this important area. You know, everybody should be able to make a great living. You don't need to have a PhD in computer science to do so. And so I'm delighted to see that. the second thing to realize and so we theorize about  the automation of tasks and things like that and what is the implication to jobs. I'll just offer some anecdotes. These are real world anecdotes of what has actually happened. 

Remember 10 years ago one of the first first professions that everybody thought was going to get wiped out was radiology. And the reason for that was the first AI that became superhuman in capability was computer vision. And the one of the largest applications of computer v vision is studying scans by radiologists.Well, 10 years later, it is true that AI has now completely permeated and diffused into every aspect of radiology. And it is true that radiologists um use uh AI to study scans. Now it the impact is 100% and the impact is completely real. However, not surprisingly I say not surprisingly if you reason from first principles not surprisingly the number of radiologists have gone up. Is that because a lack of trust oor is that because the human interaction with the with the results of AI exactly is a better outcome? 

Exactly. The reason for that is because a radiologist their job their purpose of their job is to diagnose disease to help patients . That's the purpose of their job. The task of the job includes studying scans. The fact that they're able to study scans now infinitely fast allows them to spend more time with patients diagnosing their disease, interacting with the patients, interacting with other clinicians. Well, surprisingly, also not surprisingly,actually, as a result of that, the number of patients that the hospital can see has gone up because, you know, there a lot of people waiting a long time to get to get their scans done. And so now because the the number of patients have gone up, the revenues of the hospital has gone up, they hire more radiologists. This is the same thing is happening to nurses. We're 5 million nurses short in the United States a result of using AI to do the charting and the transcription of  the patientpatient visits. uh nurses spend half of their time charting and now they could use AI technology in one particular company a bridge their a partner of ours doing incredible work as a result of that the nurses could spend more time visiting patients touch that's right and because you could now see more patients and we're no longer bottlenecked by the number of nurses more patients could get into the hospital sooner as a result hospitals do better they hire more nurses 

And so surprisingly AI is increasing their not surprisingly AI is increasing their productivity. As a result the hospitals are doing better. They want to hire more people. You have too many people waiting too long to get into hospitals. And so these are two perfect examples. Now the easiest way to think about whether what is the impact of AI on a particular job is to understand job what is the purpose of the job and what is the task of the job.

if you if you just put a camera on the two of us and just watched us, you  would probably think the two of us (Huang & Fink) are typists because I spend all of my time typing and so if AI could automate so many so much word prediction and help us type. then we would be out of jobs but obviously that's not our purpose and so the question is what is the purpose of your job in the case of radiologists and nurses is to care for people and that t purpose is enhance hands that made more productive because the task has been ma has automated and so to the extent that you can reason about each one of the people's purpose versus the task I think it's a helpful framework

27:45 fink let's let's move this beyond the developed economies; helping understand how AI is it abroad the world and help the world I read a I an anthropic piece this past weekend that basically said the utilizization of AI most recently is very dominant by the educated society and they're even seeing the educated component of each society being heavily more utilized and they're obviously they're they're using it against their own model caught so it maybe it may have its own biases um so how do we ensure that AI is a transformational technology maybe like what Wi-Fi and 5G was for the emerging world and when you intersect that what does it mean for the emerging world and John how do we broaden the global economy and two you know getting back to the whole job situation with robotics and AI there is going to be some substitution there and there's substitution in the United States already going on we may be creating more plumbers and electricians but we probably need less analysts at financial institutions, lawyers need less anal and you know because they're able to accumulate the data faster. So let's just pivot on to the emerging world for a second in the developing world. How do you see that play out? 

 

Jensen Well, first of all, um AI is infrastructure and there's not one country in the world I can't imagine that you need to have AI as part of your infrastructure because every country has its electricity, you have your roads, you should have AI  as part of your infrastructure. .you could always import AI um but AI is not so incredibly hard to train these days and because there are so many open models these open models with with uh your your local expertise you should be able to create models uh that are helpful to your own own country and so I I really believe that that every country should get involved to build AI infrastructure build your own AI take advantage of your fundamental natural resources which is your language and culture, develop your AI, continue to refine it, and have your national intelligence be part of your  ecosystem. And so I I think that's number one. And number two, remember AI is super easy to use. It is the is the easiest software to use in history. And that's the reason why it's the fastest growing and fast most rapidly adopted. I mean in just a couple of two three years it's coming up to almost a billion people. Um I think first of all claude is incredible. They've anthropic has made a huge progress huge leap in developing claude.  we use it all over our company ,the coding capability of claude  its reasoning capability it's you know it its ability is just really incredible and and anybody software company really ought to get involved and and use it. on the other hand uh chat GPT is probably the most successful consumer AI in history and its ease of use and its approachability I think everybody should get involved and whether whether it's um somebody in a developing country or you know somebody a student it is very clear that it is essential to learn how to use AI how to direct an AI how to prompt an AI how to manage an AI how to guard rail the AI evaluate the AI. These skills are no different than leading people, managing people, things that you and I do all the time. So, in  the future, instead of biological, you know, carbon based AIS, in the future, we're also going to have um digital versions of AIS, silicon versions of AIS, and and we'll have to manage them. They're just part of our  digital workforce, if you will. And so I I would I would advocate that for the developing countries .. build your infrastructure, get engaged in AI and and and recognize that AI is likely to close the technology divide, right? Because it is so easy to use and so abundant and so accessible. And so, you know, I I'm I'm actually fairly optimistic about the potential of AI to lift  the countries that are that are um uh that are emerging. And fpr many people who haven't had computer science degree, uh all of you can be programmers now, you know, and so in the past we had to learn how to program a computer. Now, you program a computer by saying to the computer, how do I program you? you know, and if I if you don't know how to use an AI, just go up to the AI and say, "I don't know how to use an AI. How do I use an AI?" And it would explain it to you. And you know, you you say, "I like to I'd like to write a program to create my own website. How do I do that?" And it says it would ask you a whole bunch of questions about what kind of website you would like to build and then write you the code. And so it is that easy to use. And that's of course the the incredible, you know, power of AI, which which is exciting. 

 

Fink Two quick questions, then we're going to run out of time. We're sitting here in Europe. When we were talking about a lot of companies, we mentioned a lot of US companies and Asian companies. Um, talk to us about how AI uh and the success of Europe and the future Europe can intersect and what and how do you see Nvidia play that role here in Europe? 

 

Jensen Well, I get I have the benefit Nvidia has the benefit of working with every AI company in the world and uh because we're  in the infrastructure layer and we power AI across the board and we power AI that are languages the you know their biology their physics their  world models and related to manufacturing and robotics and and the the thing that's really  exciting for Europe is remember your industrial base is so strong. The  industrial manufacturing base in Europe is incredibly strong. This is your opportunity to now leap past the era of software. United States really led the era of software. AI is software that doesn't need to write software. You don't write AI, you teach AI. And so get get in early now so that you can now fuse your industrial capability, your manufacturing capability with artificial intelligence and that brings you into the world of physical AI or robotics. You know robotics is is a once in a generation opportunity for the for the European nations and whether whether it's you know uh well all of the countries that I visit here uh industrial base is really really strong. Um the other thing to realize is that that so much of of uh the deep sciences are still very very strong here in Europe, right? And the deep sciences now have the benefit of applying artificial intelligence to accelerate your discovery. And so I I um I think that that it's fairly certain that you have to get serious about increasing your energy supply so that you could invest in the infrastructure layer so that you could have a rich ecosystem of artificial intelligence here in Europe. 

 

Fink So what so what I'm hearing is we're far from an AI bubble. The question is are we investing enough? let's turn the turn it around because there's so many people talking about a bubble but the question is what I'm hearing from you is you know are we investing enough to do what we need to do to broaden the global economy 

 

Jensen  one good test on the AI bubble is to recognize that Nvidia has now has now millions of NVIDIA GPUs in the cloud  we're in every cloud um you know we're used everywhere and if you try to rent an Nvidia GPU these days it's so incredibly hard And the spot price of GPU rentals is going up. Not just the latest generation, but two generation old GPUs. The spot price of rentals are going up. And the reason for that is because the number of AI companies that are being created, the number of companies shifting their R&D budget. 

Lily is a great example. three years ago, most of their R&D budget, all of their R&D budget was probably wet labs.  notice the big AI supercomputer that they've invested in the big AI lab. Increasingly that R&D budget is going to shift towards AI and so the AI bubble comes about because the investments are large and  because we have to build the infrastructure necessary for all of the layers of AI above it. And so I I think the opportunity is really quite extraordinary and everybody ought to get involved. Everybody ought to get engaged. Uh we need more energy. I think that we all recognize that we need more land power and shell. Um uh we need more uh trade skill workers and in fact that population of workforce is so strong here in Europe. Yes. In a lot of ways, the United States lost that um in the last, you know,  but it's still incredibly strong here in Europe. It's it's an extraordinary opportunity you got to take advantage of. And so I I would, you know, in I know that where where Larry and I work, uh we uh we see the the investment  opportunities um and the investment uh scale is going up. , number of startups as I mentioned earlier that L2025 the largest investment year in VC history over a hundred billion dollars around the world -most of it was AI natives and so these AI companies are building basically the application layer above they're going to um you know and go build this future and I actually believe it's going to be a great investment for pension funds around the world to to be a part that to grow with this AI world. And this is one of my messages as so many political leaders. We need to make sure that the average pensioner, the average saver is is a part of that growth. If they're just watching it from the sidelines, you know, they're they're going to feel left out. And we want to invest in infrastructure, right? In infrastructure is a great investment option. This is the single largest infrastructure buildout in human history. Get involved.

 

FINK  We're out of time. Hopefully everybody in the audience and everybody on the web streaming seeing the the power of Jensen Wong as a leader not just a leader in technology and AI but a leader uh in business and also a leader in in heart and soul which is really important today having that leadership from the heart and the soul. So thank you everyone.