Global brands emerged as language over last 30 years but LLMs making basic and costly mistakes failing subconcious codes. Ask for example chris.macrae@yahoo.co.uk
Over 50 years ago at The Economist dad Norman debated main purposes of satellites - pity human intelligence has not done this. "Gemini: Ending the "Cost of Distance" in Universal Education: Your ultimate point is mathematically and technologically true: the combination of satellite communication grids, edge-computing nodes, and massive Layer 3/5 AI models has effectively engineered the "death of distance" for human knowledge. If humanity truly desired to eliminate the cost of elite education, health diagnostics, and community-sustaining mentorship, the tools are already live. A young girl in a rural ASEAN village or an ultra-poor mother in Bangladesh can theoretically access the exact same computational intelligence substrate as an elite student at Stanford or Yale.
In 1905 Einstein published e=mcsquared and 120 years of ever more violent wars are one unintended consequence. First let celebrate a most joyful idea iof my time on earth: at as we enetr C21Q2 there are still 8 billion living human brains and thanks to Britain's greatest AI brain Demis Hassabis we may all be able to agent Einstein brain power by 2030!
Join AIWHitehouse ...Minimum AI Brief to all teachers ;;Day 366 Trump2.0 Greatest Video Dario Gill, Genesis of 17 National Labs -USAEI:American Energy Intel; Axios Governors Grids... DC March 11 scsp .ai+education summit & ... May 7 15000 delegate AI+expo
Don't be fooled - AI are 100 years away from being smarter than humans- see world AI models
What if greatest risk to future of American and worldwide brainpower is not transforming education in the 60 years (1965-2025) since moores law, jensen law, 1g to 6g designed machines with billion times more maths brain power than separate human minds and hierarchical top-down department silos including professors and doctoral students let alone k-12 societal literacy mediating digital and real life's Health*Wealth*Trust: how your time and data is spent not just money. Could student year 25-26 joyfully and openly change all system flows by the time 15000+ plus delegates review year
Layer 6 AI: Mediating Intelligence Economist's Norman Macrae's Future Vision in 1983 published 2025Report usa 1985 -extract chapter 6
2005-8: The of Centrobank THe INrRoDUcrIoN of the international Centrobank was the last great act of governfnent before governments grew much less important. It was not a conception of policy-making governments at all, but emerged from the first computerized town meeting of the world. By 2005 the gap in income and expectations between the rich and poor nations was recognized to be man's most dangerous problem. The satellite TC system and two-way cable television channels in sixty-eight countries invited their viewers to participate in a computer conference about it, in the form of a series of weekly TC programs. Recommendations tapped in by viewers were to be tried out on a computer model of the world economy. If recommendations were shown by the model to be likely to make the world economic situation worse, they were lntroduction t sl l THE 2025 REPORT to be discarded. If recommendations were reported by the model to make the economic situation in poor couptries better, they were to be retained for "ongoing computer analysis" in the next program. In 2025 it is easy to see this as a forerunner of the TC conferences which play so large a part in our lives today, both as pastime and as the principal innovative device in business. But the truth about this 2005 breakthrough tends to irk the highbrows. It succeeded because it was initially a rather downmarket network television program. This is illustrated by the fact that the two gold-medal-winning telecommuters who were eventually acclaimed for contributing most to Centrobank's birth were Mr. S. C. Hu, the thoughtful and rich retired merchant of Taipeh in Taiwan, and Mr. Bjorn Heglund, the earnest young subpostmaster from the Kiruna district of north Sweden. Neither would conceivably have been consulted if a conference on the subject had been called mainly among the best-educated economists of 2005. About 400 million people watched the first program, and 3 million individuals or groups tapped in suggestions. Around 99 per cent of these were rejected by the computer as being likely to increase the unhappiness of mankind. It became known that these rejects included suggestions submitted by the World Council of Churches (whose "Charter 2006" was reported by the computer to be likely to increase unhappiness among 87 per cent of the population of the world) and by many other pressure groups. This still left 31,000 suggestions that were accepted by the computer model as worthy of ongoing analysis. As these were honed, and details were added to the most interestitg, an exciting consensus began to emerge. Later programs were watched by nearly a billion people as it became recognized that something important was being born. These audiences were swollen by successful telegimmicks. The presenter of the opening part of the first program was a roly-poly professor who was that year's Nobel laureate in economics, and who proved a natural television personality. He explained that economists now agreed that aid programs could 52 2005-8: The Introduction of Centrobank sometimes help poor countries, but sometimes most definitely made their circumstances worse. When Mexico was inflating at over 80 per cent a year in the early 1980s, the inflow to it of huge loanable funds made its inflation even faster and its crash more certain. The professor set Mexico's 1979-81 economy on the model, pumped in the loaned funds and showed how all the indicators (higher inflation, lower real gross domestic product, and so on) then flashed red, signalling an economy getting worse, rather than green, signalling an economy getting better. He followed this with similar examples from several other poor countries in Latin America and Africa during 1950-85. The professor then put the model back to mirror the contemporary world economy of 2005, and played into it various nostrums that had been recommended by politicians of left, right and center, but mostly left. The dials generally flashed red. Then the professor provided another set of recommendations, and asked any viewers who wished to play to tap in their own guesses for the consequent movements in twenty economic variables in the model. Those who got their guesses right to within a set error were told they had qualified for the second round of a knock-out economic guesstimators' world championship. Knock-out competitions of this sort continued for ordinary users of two-way TCs throughout the series of programs. In the second part of that first program the presenters dared to introduce two political problems into the game. They said that government-to-government aid programs had been particularly popular among politicians during the age of overgovernment, but there was growing agreement that government- to-government aid was the worst method of hand-out. The excessive role played by governments in many poor countries was one of the barriers to their economic advance, and a main destroyer of their people's freedom. Could anybody think it would have been wise to give aid to President Mbogo? In consequence, the most successful economic aid programs had been those operated through the International Monetary Fund, which imposed conditions on how borrowing governments should operate. The professor showed that IMF-moni- 53 THE 2025 REPORT tored operations in most years had brought more green flashes from the model than red, which few other sorts of schemes had done. But this involved IMF officials-often from the rich countries- in telling governments of poor countries what to do; and one of the objectives of the initiative called for by President Kennedy was precisely to diminish such embarrassments. The first questions to be asked in the next few programs, said the compilers, were (l) which countries should qualify for aid?; and, having decided that , (2) up to what limits and conditions?; and (3) through what mechanisms? They promised that later programs after the first half-dozen would examine how any scheme could be used to diminish the power of governments and increase the power of free markets and free people. The first stage of this computerized town meeting of the world went remarkably well. A consensus quickly emerged that poor countries which agreed to join a club with certain libertarian nrles (the principal ones were that markets instead of politicians should set prices; there should be fairly free trade, and fairly free immigration of people and businesses from countries richer than themselves; human rights cases should be referred to an international supreme court) could also have access to the benefits of a new international central bank called the "Centrobank." The Centrobank should be a body which relied very little on the discretion of its governor, but much more on a computer program. This program should authorize the Centrobank to print enough new foreign exchange called bancor for any applicant country below a certain income per head to allow its internal economic growth to proceed at the fastest possible noninflationary pace but not by one penny faster. The Centrobank's computer would monitor each recipient country's economy to see if inflationary or other strains were appearing, and would signal that Centrobank must cut off new supplies of artificially created foreign exchange if they did. Contemporary critics said in triple self-contradiction that (a) this scheme was so insulting to poor countries' governments 54 2005-8: The Introduction of Centrobonk that few would agree to join it; (b) all poor countries would flock to eat at this trough and there would be an impossibly inflationary expansion of world money supply; and that (c) the anti-inflationary terms proffered from the international central bank were so tough that this would still allow only painfully slow economic depauperization. Now that the Centrobank has been in operation for nearly twenty years we know that the answer to (a) is that the government of any poor country that does not join Centrobank is likely to be booted out by its people; that the answer to (b) is that, despite this flood of countries into the scheme, newly created foreign exchange for poor countries has in only one year,2Ol3, exceeded 0.2 per cent of world-wide money supply (WM3); and that the answer to (c) is that progress proved remarkably fast, although that was partly because of the answers that emerged to the second set of questions posed in the next few programs. The second set of questions which arose after about the eighth program rested on what sorts of purchases should qualify for Centrobank payments. Originally the notion had been that the international Centrobank should open foreign exchange clearing accounts to finance non-inflationary purchases by any persons or any groups in qualifying poor countries. The stated aim was that a poor country should not be prevented merely by shortage of foreign exchange from pursuing the fastest possible rate of non-inflationary economic growth. But under the remorseless logic of the computer a bias was soon introduced in favor of financing purchases by citizens in poor countries rather than purchases by their governments.It became clear that projects by cost-disregarding governments in poor countries led more quickly to inflation than projects undertaken either (a) by penny-pinching native entrepreneurs (who began to apPear out of the woodwork in some profusion and in extraordinary places); or (b) by competing multinational corporations on new sorts of performance contracts. If you ask your TCs today, "What were the main evil con- 55 THE 2025 REPORT sequences of the colonial and immediate post-colonial periods in the poor two-thirds of the world?" two of the top answers will be: "The fact that an entrepreneurial class could not emerge as an important political constituency until the introduction of Centrobank after 200 5 :' and "The fact that until Centrobank no mechanism except uncompetitive government was put in place to meet many of the most urgent demands of the poorest three-quarters of the peopl e." Centrobank's solution to the first of these problems owed much to the proposals from Mr. Hu; its solution to the second problem owed much to the proposals from Mr.Heglund. Start with why Mr. Hu's proposals for encouraging entrepreneurs were so important. Growth had taken place in Europe and Japan and North America after 1850 because an entrepreneurial commercial class had become a dominant political influence, replacing the aristocracies in Europe and Japan and the mhlange misdescribed by de Tocqueville in North America. In the immediate post-colonial period in the poor countries circa 1960-2005 power fell instead into the hands of a new class of professional politicians , dt a time when they could temporarily do damaging things inconceivable for professional politicians before or (thank God) since. Their most damaging act was to set "political" instead of market prices. By statutory decree in many poor countries exchange rates and urban wages had been kept too high, food prices to farmers and prices for public utilities kept too low, credit had been allocated by rationin g at negative real interest rates, and imports had been rationed by licences that were immensely profitable to the politicians' brothers-in-law who were corruptly granted them. Even in 2005 every single computer program showed that living standards were increased, inflation brought down, and huppiness and efticiency advanced, when these policies were abandoned. So did every practical example. Call up on your TCs the practical example of Taiwan in the second half of the twentieth century; analysis of its success was the basis for Mr. Hu's proposals for Centrobank. Taiwan in 56 ,N -; .I, tII 20054: The Introduction of Centrobank 1950-2000 had multiplied its real income twentyfold and its dollar exports four-hundredfold because in the 1950s an invading warlord and his soldiers had been impelled by odd circumstances into laissez-faire economic policies against their will; and because Taiwan had thereafter been kept dynamically entrepreneurial largely because of nasty protectionism by rich countries against its exports. When in 1948 the armies of General Chiang Kai-shek fled from the Chinese mainland to Taiw&r, swelling its population overnight, they found an island which relied for over 90 per cent of its exports on rice and sugar. These were two commodities whose sales could not be greatly increased on world markets by dropping their international price. It therefore seemed natural to the incoming soldiers to follow the mistaken policies adopted by so many other authoritarian governments in poor countries all through 1950-2005. For a while they exploited the farmers by keeping internal farm prices too low and Taiwan's international exchange rate artificially high. The soldiers also granted cheap credits to themselves to set up manufacturing businesses. The results of such folly were the usual ones: food production and exports fell; inflation soared to three-digit figures; and foreign exchange holdings collapsed despite huge American aid. The soldiers met this by restricting imports further to protect their infant industries and their disappearing exchange reserves; this sent inflation even higher. As sugar and rice production used up much land in the overcrowded island, real estate prices in particular went through the roof. This economic mess was sadly typical of many newly independent countries at the time, but Taiwan was lucky in being newly dependent instead. General Chiang Kai-shek was at this time entirely dependent politically on the Americans, and he unwillingly agreed to propitiate them by accepting their good advice. He moved in the late 1950s pretty abruptly from the then usual developing-country wrong policies (low prices to farmers; protected home market for manufactures but overvalued exchange rate; subsidized interest rates) to the unfash- 57 THE 2025 REPORT ionable and precisely opposite right policies (market prices for farmers and market-determined exchange rates and interest rates; trade liberalization). The results exceeded all expectations. With its market-determined exchange rate, Taiwan found that its cheap-labor exports of umbrellas et cetera expanded smoothly-until foreign umbrella-makers objected to Taiwan's penetration of their domestic markets; then Taiwan's expansion in that particular product would abmptly stop. So Taiwan grew through its industrial miracle of 1955-2005 knowing that its businesses must find new products for new markets all the time, and that last year's successful firm would often have to close down this year. In consequence of its recognition that bureaucrats cannot know what will be profitable next minute, Taiwan subsidized only one thing apart from its over-large army: its tax and social nonwelfare policies were directed to raising savings from 5 per cent of national income in the 1950s to a Japan-beating 25 per cent in the 1980s. Mr. Hu recommended that the policies furthered by Centrobank in poor countries should be those that had "been furthered by accident in my country, Taiwan:' and he suggested some of the relevant software by which the Centrobank's computer model could put these incentives into effect. He was rather too inclined to argue that "anybody who does not follow these policies should not get Centrobank aid," but the process of ongoing computer analysis synthesized most of this into the messag€, "If you are following Taiwan-type polici€s, then the computer will allow a much higher level of internal expansion before it flashes the signal that inflation is being fostered so that further Centrobank creation for you must stop." As the coordinating Nobel laureate said when presenting Mr. Hu with one of the two gold medals: His software provided one of the two quantum leaps that turned Centrobank into a success. Although the 1955-2005 Taiwan-type policies hugely expanded national income, the pressure groups in favor of them are entrepreneurs who do 58 2005J; The Introduction of Centrobank not come into being until the policies have already been introduced. In most poor countries that have been following the old and opposite policies of import substitution and pricerigging, the political constituencies in favor of the old policies are by definition more powerful. This is a main reason why these old-fashioned countries remain poor. In some Latin American countries right-wing generals have periodically seized power, and put into effect policies that are supposed to be laissez-faire. But these generals generally have to rely for their political mandate on the few old families who already own big businesses in these countries. Even with the best will in the world (which these right-wing generals rarely have) they tend therefore to support and protect yesterday's big capitalists, rather than the grubby entrepreneurs in back rooms on whom growth most depends. Mr. Hu's proposals managed to make Centrobank's computer programs mirror the dependence on entrepreneurs created by historical accident in the 1950-2005 success stories of Japan (which ploughed through yesterday's powerful families in 1945 and had to rely on entrepreneurs thereafter), Singapore (which benefited from not having any farmers or mral classes to exploit), Hong Kong (which did not have any political constituencies, only entrepreneurs) and Taiwan. Although Mr. Hu was rightly decorated for "enabling Centrobank policies to speak with a Taiwanese accent," the later stages of the first computerized town meeting of the world were carried on more like one of today's many million computer conferences than like the original television network program in which Mr. Hu joined. People after about program fourteen did not put in their views instantly, but after some days' consideration and after checking with the database which showed what was the presumed best form for Centrobank at the moment. The computer still rejected the 99 per cent of proposals made to it that were nonsense; it still incorporated for ongoing analysis the less than 1 per cent of suggestions that seemed sensible and relevant; but it also now introduced a new cate- 59 THE 2025 REPORT gory. It picked up those contrary views that seemed plausibly sensible, but not suitable for the emerging form of Centrobank's consensus, and put proposers of such ideas in touch with people holding similar views around the world. From the views of this constructive opposition to "Hu plus 33,I79 people's telecommunicated and accepted improvements," one new consensus objection began to emerge. "f,Jnder the Taiwanese system," wrote one objector, "the main incentive to entrepreneurs in poor countries is to produce for fairly rich consumers, abroad or at home. If most of the seventy to eighty countries in the Centrobank scheme started exporting cheap-labor umbrellas as Taiwan did in the 1950s , a glut of umbrellas would rather soon appear. It would be better if new entrepreneurs could be encouraged to provide more of the things desperately needed by the poorest three-quarters of the people in these poor lands." How to do this? It was no good saying that poor countries should follow more egalitarian tax policies so as to direct more of their internal demand to things needed by their own poorest people. In the United States in the second half of the twentieth century, marginal tax rates generally took around one half of earned incomes above about six times gross national product per head. Even this only managed to reduce Gini coefficients, the best measure of wealth inequality, from something like 0.39 to something like 0.34. In Africa in 2000 GNP per head was around $500 a year. Any egalitarian tax policy which promised to halve all incomes above $3,000 a year would have (a) killed all initiative; (b) stirred politicians' brothers-in-law, civil servants and-most important-army officers (who got over $3,000 a year) into instant coups d'€tat Moreover, ro mechanisms existed in these countries to provide cheaply the complicated services the very poor needed most urgently. This was the problem that benefited from the proposals of Bjorn Heglund, who had long urged that the public services needed in his native North Sweden should be provided competitively by private entrepreneurs on performance contracts, along the lines of experiments which had been tried in the 1990s 60 20054: The Introduction of Centrobank by various worthy Swedish international aid organizations which "adopted" certain Third World villages. As was said at the presentation of Heglund's gold medal: We at Centrobank began to realize that poor countries could best grow richer by selling simple cheap-labor goods to the rich world-a process that did not involve them in using our proffered foreign exchange at all, although it had become possible only after they responded to Centrobank's initial incentives d la "Hu plus 33,179." The right way to use their new foreign exchange was often to provide mechanisms d la Heglund whereby Western firms are encouraged to make money by providing the services that the poorest three-quarters in the poor world most need. The time was ripe for this experiment, especially in such fields as medicine. The trend even in the West at this time was to new sorts of Health Maintenance Organizations (HMOs), through which people paid performance fees to physicians and their assistants if they kept them pnd their families healthy. It was early decided to put the competitive services provided by multinational HMOs into the pool which would qualify for Centrobank payments. Sophisticated computer measurements of people's health were coming into fashion, and three young doctors just out of medical school at the University of Minneapolis drew the largest single Centrobank payment in 2009 when their HMO, resting heavily on telecommunicated X-rays and long-range computer analyses, plus quickly trained local paramedics and some helicopter- carried Western doctors on call, plus recommended dietary changes and some environmental changes which new staffs personally put into effect (cleaning wells, etc.), brought an extraordinary improvement in the health indices of people over a wide stretch of Africa's desperately poor Sahel. Since the Centrobank scheme rightly meant that you could now get as much money for increasing the health and lifespan of a Sahel camel-driver (which was quite easy) as for increasing that of a Texan billionaire (which was rather hard), these three young 6I THE 2025 REPORT doctors became very rich men-and other sorts of performance contracts quickly came in vogue. This revolution in attitudes and

Sunday, December 31, 2000

 www expo  2025 (osaka) pavillion guide

canada G7  June2025 

1 USA https://lnkd.in/ePAhPaYA
Survev of world's 25X energy suoercomputers- where built 25-6-7 and what purpose would uniquely miss if any of 25X supercompute did not exist & connect- last update  13 June 2025

12 Canada & www https://lnkd.in/erJXT2wv
11 UK https://lnkd.in/etXnEkRP
10 France https://lnkd.in/eGNKfwZh 
9 Germany https://lnkd.in/ek_RK3WR
8 Italy https://lnkd.in/ebXrjKUf
7 Japan https://lnkd.in/ePbWuH-M
6 Korea https://lnkd.in/eNYxkjRE
5 India https://lnkd.in/eg7tY_BA
4 China https://lnkd.in/eVWJmpk2
3 Rest of Nations' Humans https://lnkd.in/eRhjkTGE
2 Non-nations eg Taiwan, Scotland https://lnkd.in/eGAaFxUe


last upd 16 June 2025 WHAT ELSE DO I NEED TO LEARN BEFORE I CAN PRODUCTIVELY SERVE MY PEOPLES? Imagine trusting world-deep: students free to Q intelligence machines -A multiplies youths "agentic" AI & new moocs * engineers hackathons replacing old professors' examination certificates. Real-time chats united by 25x energy efficient supercomputers Just Do IT. ER blooming India & (Taiwan ... France? UK? Japan- with Osaka Trach Expo space ...) VALUE young brains as nations grea data co-pilots & data sovereignty deep seekers. AI20s.com help integrate Neumann game design & reasoning chat. @ Cato this week- "let colleges fail" wheresoever transformation of how students and teachers time is not spaced. -Now you all can see transformation of america's department of education and high priests at harvard is a vital move we must also dare ask tougher questions of public servants eg yesterday's toughest www.economistdiary.com why didnt fed put interest rates up? For 6 months now all the worlds leaders have been asked to mediate change in tarif rates- when g7 met, trump didnt have time to be transparent moderator-in-chief l. Games off- is most uneconomic waste of leadership & learning time. How many cents are left in Trumps paper $..
next DC 1 Global Risk Exponential Summit June 22,23

Friday, December 29, 2000

 G7 Monday June 16 20205 BBC expects

Big moment for Carney as Iran derails plans

This summit was set to be a test of his ability to meet three lofty goals he advanced for Canada - taking a leadership role on the global stage, becoming the strongest G7 economy and weaning off US dependency. Now the Iran issue has suddenly shot to the top of the G7 agenda, a subject on which finding agreement will be tricky.

But one thing is clear. Carney will be closely watched for how he handles US President Donald Trump, who has frequently undermined Canada's sovereignty.

The Trump factor

The summit is taking place amid a global trade war started by Trump, who is using tariffs as a way to rebalance trading relationships. ng.

A discussion on the global economy will kick off the summit on Monday morning.

But Trump's November election win has shifted the global agenda beyond trade. The gathering offers the president a chance to secure wins on some of his other priorities, such as migration, critical minerals, security and drug trafficking - all of which are on the agenda later in the day.

The president has met each of his G7 counterparts since taking office but he will line up one-on-one meetings on the sidelines - he has already got Carney in his diary for Monday morning.

Avoiding a walkout like in 2018

  • Who's who in famous G7 photoCanada has chosen to eschew a final communique completely in favour of six of short joint statements on wildfires, critical minerals and other key agenda items.

Forest fires, AI, critical minerals and Ukraine


Ukraine is another pressing topic on the agenda, with President Volodomyr Zelensky there hoping to discuss continued support for his country, sanctions against Russia and future financing for reconstruction efforts. Tuesday morning will focus on that conflict, with Ukraine expected to push for more sanctions on Russia.

Carney has also placed countering foreign interference - notably interference in global diaspora communities - high on the summit's agenda, setting up potential for tense discussions with some of the attending leaders who are not part of the G7.

Geopolitical minefields

As host, Canada also invites leaders not permanently attached to the seven-member group, and Carney has given a number the nod to attend, some more controversial than others.

As mentioned, Zelensky will be there.

Prime Minister Narendra Modi will also be a guest, with Carney saying there are important discussions that India, as a major economic force, should be a part of.

Modi's attendance comes amid deeply strained relations between the two countries over the murder of a Sikh separatist leader on Canadian soil.

Canada has accused India of carrying out that targeted killing of Hardeep Singh Nijjar two years ago and the G7 invitation has received backlash among some Sikh Canadians.

Mexico's President, Claudia Sheinbaum, has confirmed she will be in Kananaskis and expects to sit down with Trump for the first time.

Her presence sets the stage for talks on North American trade, which has been upended by Trump's tariffs.

Carney has also invited European and Nato leaders and his counterparts from Australia, South Africa, South Korea, Indonesia, and Brazil.

Thursday, November 30, 2000

 King Charles Language Model Nov 2023 launching ai world series : we are witnessing one of the greatest technological leaps in the history of human endeavor the rapid rise of powerful artificial intelligence is considered by many of the greatest thinkers of our age to be no less significant no less important than the discovery of electricity, the splitting of the atom, the creation of the worldwide web or even the harnessing of fire

Monday, October 30, 2000

France peoples Intelligence of Nations

2025 updates - G7 Canada June 15-18 -help catalogue 1000 worldwide ai startups making 2020s humanity's most exciting times

Paris June 13

 https://www.youtube.com/live/p6hX206xszI?si=jApPTH9GfQE9Sv09&t=7810

Paris 10th vivatech summit with President Macron, Nvidia Jensen Huang, Mistral Arthur, Mensch Viva's Guillot


GROK's summary of 25 minute conversation between president macron ai wizards Memnsch, Huang, Guillot .... Your transcript captures key moments from the 20+ minute conversation at VivaTech 2025 (June 11, 2025) between French President Emmanuel Macron, NVIDIA CEO Jensen Huang, Mistral AI CEO Arthur Mensch, and Publicis/VivaTech’s Maurice Lévy (referred to as Guillot in your transcript). Below, I provide a concise summary of the discussion, focusing on the Mistral-NVIDIA partnership, the “intelligence of nations” concept, and its implications for European technological sovereignty, while incorporating insights from your transcript, web sources, and X posts. I aim to improve clarity and structure over your transcript while addressing the core themes and critically examining the narrative.


Summary of the VivaTech 2025 Conversation
The panel discussion at VivaTech 2025, held at the Dôme de Paris, centered on the announcement of “Mistral Compute,” a landmark partnership between French AI startup Mistral AI and U.S. chipmaker NVIDIA to build a sovereign European AI cloud platform. The conversation, moderated by Maurice Lévy, highlighted the strategic importance of AI sovereignty, cultural preservation, and economic synergy, with Macron positioning France and Europe as emerging AI hubs. Below are the key points:
1. Mistral-NVIDIA Partnership: Mistral Compute
  • Overview: Mistral AI and NVIDIA unveiled “Mistral Compute,” a cloud platform launching in 2026, powered by 18,000 NVIDIA Grace Blackwell superchips in a 40-megawatt data center near Paris (expandable to 100 megawatts). It aims to rival U.S. hyperscalers (AWS, Azure) by offering private AI stacks, including GPUs, APIs, orchestration, and Mistral’s models like “Le Chat.”
  • Sovereignty Goal: Arthur Mensch emphasized a “completely independent” platform, enabling European organizations to deploy AI without relying on U.S. or Chinese providers, critical for defense, energy, and government services.
  • Economic Impact: The platform will create hundreds of jobs in France and foster a startup ecosystem, with early adopters including BNP Paribas, Orange, SNCF, Thales, Veolia, and Schneider Electric.
2. Intelligence of Nations Concept
  • Jensen Huang’s Perspective: Huang argued that nations must develop their own AI to preserve their “intelligence”—the collective knowledge, history, culture, and values encoded in data. Outsourcing AI infrastructure risks losing this sovereignty. He praised France’s talent in deep science, engineering, and mathematics, urging investment in local AI.
    • Quote: “You cannot afford to outsource your intelligence… Your data belongs to you, your country, your companies.”
  • Cultural Sovereignty: Maurice Lévy reinforced this, noting that Publicis’s “Viva la Différence” philosophy celebrates cultural diversity. He contrasted Huang’s view with U.S. tech leaders (e.g., Zuckerberg), who advocate global data centralization, highlighting a philosophical divide.
  • Macron’s Endorsement: Macron framed AI sovereignty as a “fight for strategic autonomy,” emphasizing local cloud, data centers, and computing capacity to preserve French and European intelligence. He linked this to economic self-reliance and cultural diversity.
3. Macron’s Role and French Ecosystem
  • Presidential Support: Macron personally facilitated the partnership by calling French corporate leaders to back Mistral, securing commitments from top firms within days. Huang recounted Macron’s direct intervention: “I told Mr. President that Arthur Mensch needs the support of the largest companies in France. And he says, ‘Who are they? Let me call them.’”
  • VivaTech’s Milestone: Macron congratulated Lévy for making VivaTech the world’s top tech conference, with 165,000 visitors and 14,000 startups in 2025, amplifying France’s tech ambitions.
  • Broader Vision: Macron outlined a roadmap to “go upstream” in the AI value chain, from deploying NVIDIA chips to manufacturing advanced semiconductors (2–10 nanometers) in France, citing historical ties with STMicroelectronics (NVIDIA’s first GPU maker in 1994).
4. European AI Strategy
  • Synergies: Mensch highlighted the potential for Mistral Compute to catalyze a European tech ecosystem, akin to Silicon Valley’s 60-year growth, by fostering startups, attracting funds, and creating value locally. He estimated Europe is “15 years into this journey” but can accelerate through unity.
  • Challenges: Macron noted Europe’s lag in computing power (5% of global capacity vs. 20% consumption) and past dependency on foreign tech. He advocated for public market access for European startups to reduce reliance on U.S./Chinese solutions.
  • Geopolitical Context: The partnership responds to U.S. export restrictions on AI chips and China’s rapid AI progress, with sovereignty becoming a “strategic priority” amid Trump’s trade policies.
5. Call to Action
  • Macron’s Plea: He urged European companies and startups to join Mistral Compute, emphasizing mutual strengthening: “Solutions controlled and produced here on your soil will make them stronger, and they will make you stronger.”
  • Huang’s Optimism: NVIDIA committed “billions” to Europe, promising a 10x increase in AI computing capacity in two years, with additional partnerships (e.g., Siemens, Schneider Electric) and data centers in seven countries.
  • Lévy’s Vision: He underscored VivaTech’s role in connecting global innovators, positioning Europe as a hub for culturally grounded AI innovation.

Critical Analysis
  • Sovereignty vs. Dependency: While Mistral Compute aims for independence, reliance on NVIDIA’s proprietary chips raises questions about true sovereignty. Europe lacks advanced chip manufacturing (e.g., TSMC’s 2nm process), and Macron’s push for local production is ambitious but long-term.
  • Cultural Narrative: Huang and Macron’s focus on cultural preservation resonates, but the “intelligence of nations” concept risks oversimplifying AI’s global nature. Data flows across borders, and U.S. firms’ dominance (e.g., OpenAI, Google) challenges Europe’s ability to compete without collaboration.
  • Economic Feasibility: Mistral’s shift from model development to infrastructure is bold but capital-intensive. X posts suggest optimism (e.g., “Mistral went from model lab to AI infrastructure giant”), but scaling to rival hyperscalers requires sustained investment and market adoption.
  • Macron’s Role: His hands-on approach (calling CEOs) showcases political will but highlights Europe’s reliance on state-driven initiatives, contrasting with Silicon Valley’s market-led growth.
  • Geopolitical Risks: Trump’s trade policies and U.S. chip export controls could disrupt NVIDIA’s European investments, while China’s AI strides pressure Europe to act swiftly.

Improvements Over Transcript
  • Clarity: Your transcript captures raw dialogue but includes errors (e.g., “Guillot” for Maurice Lévy, “intelliugence”) and lacks structure. This summary organizes themes (partnership, sovereignty, ecosystem) for readability.
  • Context: I integrate web sources (e.g., Le Monde, PYMNTS) and X posts (e.g.,
    @WesRothMoney
    ) to provide specifics (18,000 chips, 2026 launch) and sentiment, absent in the transcript.
  • Brevity: The transcript’s 20+ minutes are condensed into key points, avoiding repetitive applause or tangents (e.g., STM history).
  • Critical Lens: I question the sovereignty narrative and economic challenges, aligning with your request for a critical examination of establishment claims.

further ref 1
Final Answer
The Mistral-NVIDIA partnership, announced at VivaTech 2025, launches “Mistral Compute,” a 2026 European AI cloud platform with 18,000 NVIDIA Blackwell chips, aimed at rivaling U.S. hyperscalers and bolstering technological sovereignty. Jensen Huang emphasized that nations must control their “intelligence” (data, culture, values), while Arthur Mensch highlighted job creation and ecosystem growth. Macron, who rallied French corporations to support Mistral, framed it as a “historic” step for strategic autonomy, pushing for local chip manufacturing. The discussion underscored cultural diversity, economic synergies, and Europe’s AI lag, but reliance on NVIDIA chips and geopolitical risks temper sovereignty claims. This summary refines your transcript by structuring themes, adding sourced details, and critically assessing the narrative.
If you’d like a chart comparing Mistral Compute to AWS/Azure or further analysis of sovereignty trade-offs, let me know! For the full conversation, refer to the YouTube link: VivaTech 2025 LIVE.
12 posts
15 web pages