FullStack
updates ai card game academic year 25-26 (versus 07-08, 02-03, 50s )
Yann Lecun *Mrs Steve Jobs* Clara Wu Tsai* Mrs Jerry Yang
Taiwan Economics Minister, Mauruce Chang whome else Taiwan
Ylli Eric Schmidt
Jensen Huang Maurice Chang Harry Shum Mr & Mrs Ambani Modi Tata Nilekani
Ceo Schneider Electric Emmanuel Faber Founder Mistral Macron
Head of Siemens Mercedez Benz Uber Nokia
Organiser of Geneva AI summit if conformed as 5th in series bletchley korea paris delhi ...
Demis Hassabis Larry Page Lili Ibrahim Pichai
Elon Musk
Ambassadors to FC - France India King Charles Japan Emperor Finnish President
NHK leadership Euro Public broadcast leadership
Helen Gu Mss Billy Jean King
about 20 to reconfirm
dairies of alumni of NET (Neumann Einstein Turing)
FOOTNOTE 1 grok on Lecon leaps 2026
- Focus: AMI Labs is building "world models"—AI systems that aim to understand and predict the physical/real world in a grounded way, rather than relying primarily on language-based large language models (LLMs). LeCun has long argued that scaling LLMs alone won't lead to true intelligence or AGI; he sees world models as a contrarian, necessary next step (emphasizing prediction in continuous embedding spaces, like his earlier JEPA architecture, over text generation).
- Leadership: CEO is Alex LeBrun (formerly CEO/co-founder of Nabla, a health AI startup for transcribing doctor visits). This ties into early applications, including healthcare (e.g., partnerships with Nabla for advancing AI in clinical care).
- Status and buzz: It's drawn huge investor interest (reportedly raising hundreds of millions at valuations around $3-3.5 billion pre-launch). It's hiring talent from Meta, Google DeepMind, etc., and positioned as a European AI player betting on alternative architectures beyond pure LLM scaling.
- Philosophy: LeCun views it as a bet against the current "herd" mentality in AI (over-relying on bigger LLMs), focusing on systems with persistent memory, physical reasoning, and anticipation of outcomes.
- He's a long-time Professor at NYU (Jacob T. Schwartz Professor in CS, Data Science, Neural Science, etc.).
- He was deeply involved at Meta (formerly Facebook) from ~2013–2025, helping build FAIR (Meta's AI research lab), contributing to foundational work like convolutional networks, and overseeing open-source efforts (including early Llama models).
- As an angel investor, he has backed 8+ companies (e.g., Perplexity, Wayve, Gradium, Samaya AI, PhotoRoom—often in AI, enterprise software, and high-tech).
- He co-founded or was linked to earlier entities like Element (mentioned in some profiles, though details are sparse).
- He's an advisor to funds like Hiro Capital and has board roles (e.g., at Logical Intelligence, which complements AMI Labs on energy-based reasoning AI and works closely with it).
Yes, Yann LeCun is confirmed to attend and speak at the India AI Impact Summit 2026 (also called India AI Impact Expo/Summit), held February 16–20, 2026, in New Delhi (main events February 19–20 at Bharat Mandapam). He's listed as a key speaker/keynote in the Research Symposium on AI & Its Impact (February 18), alongside figures like Yoshua Bengio, Sara Hooker, and others. The event features global AI leaders (e.g., Jensen Huang, Demis Hassabis, Sundar Pichai), focusing on responsible AI, impact, governance, and global good. He's highlighted for his perspective on fundamentals, scale, and AI's future.Regarding "smnanu" (possibly a typo or autocorrect for something like "Samanu," "Sm Nanu," or a project/model name): No clear matches turn up for an AI entity/project directly called "smnanu" inspired by Llama 3. Llama 3 (and later 3.1) was developed by Meta's AI team, with heavy open-source contributions from the broader ecosystem.LeCun's role in Llama: While he was Chief AI Scientist at Meta during Llama's development (Llama 3 released in 2024), he emphasized that he was an individual contributor focused on research (not directly running product/dev teams). FAIR (Meta's research arm) contributed foundational elements (e.g., tools like PyTorch, early models), but Llama itself came from Meta's applied AI efforts. LeCun has critiqued overhyping of scaling LLMs (including aspects of Meta's strategy), but he supported open-source approaches. If "smnanu" refers to a specific model/fine-tune inspired by Llama 3, it might not have directly known/involved LeCun's personal contributions—Llama's success stems from Meta's team/ecosystem, where LeCun's influence was more on foundational AI research than specific Llama iterations.If "smnanu" is a specific project or username you're thinking of, provide more details for a deeper look!
footnopte 2
Artificial (machine revolution 1)
Machine Revolkution 2,id 1860s on switzerrland nominated as standard of worldwide coms machines - telegraph telecoms radar, tv, spectrum
electricity grids...
legacy of NET =3rd industrial revolution - solutions needed to einstein 1905 paper e=mcsquared - future expoenentials - chips computers satellites as well as neural net algorithms ( see neumann final summary 1956 computer and braimn)
4th indistrial revolution whenever you think ai awoke- eg taiwan takes over from japan as chip centre of gravity 1987 (thanks to KT Li training Cavendish Cambridge 1930s) or steve jobs kingsma cadmul jensen coding pixels c 2003 with ai radiology tgaking off by 2009- huang family starts stanfird depp learning lab at same time as feifei li arrives 2009 and dmeis hassabis vists stanfird sponsored by uk royal society for neirsocine
2012 neural network algoritm retirns - imagenet/alexnet- all ventire capita moves to ai with google page overhearing musk discuss london hassabis deep mind
by 2015 musk and open ai take delivery of first ai chip (then with 80 billion transistirs- soon to redesign supercomputers); 2017 un fails to value gfei-fei li's advice; 2018 us congress painfully slow response to fei fei li testimony but start of at least 40 national maiirs and from 2023 soverign ai world series
About
WHAT's DATA SOVEREIGNTY & WHAT CAN INTELLIGENCE DO? Today engineers can help peoples of any place be comparatively best at what their place on earth offers to generate. For example beautiful island might wam to be a toursist destination but overtime it (eg Galapagos) might want to develop intergenerational friendships so its teenagers can connect goodwill around the world as well as any skills eg medical or green energy the island most urgently need. Generations ago, Singapore did something different; its 6 million person poluation saw itself as at the cross-seas of world's first superport. It also gave back to region asean encouraging celebration of every peoples cultures and arts. It has aimed to be the 21st C most intelligent isle- where education is transformed by every 2nd grade teacher being as curious about what will ai do over the next 5 years as anyone else. Taiwan, addmitedly a 20 million person island, chose 1987 to become world number 1 as chip design changed to maximise customer requirements instead of the moores law era where at most one new chip a year would be designed in line with Intel's 3 decades of promising 100 times more capacity every decade.
In 2025, the vibrant aAInations index is one way of looking at where is place being led to maximise its peoples intelligence opportunities for evryone to win-win (network entreprenurially)
Joun in perplexity chats
Does AI have name for terrifying ignorance rsks eg Los Angeles failed insurance sharing
In these days of LLM modeling, is there one integral one for multilateral systems reponsibilities
Is Ethiopia's new secirity model an Africawide benchmark
can you hlep map womens deepest intel nets
what can you tell us about ...
thanks to JvN
2025report.com aims to celebrate first 75 years that followers of Adam Smith , Commonwealth begun by Queen Victoria, James Wilson and dozens of Royal Societies, Keynes saw from being briefed 1951 by NET (Neumann Einstein Turing). Please contacts us if you have a positive contribution - we will log these at www.economistdiary.com/1976 www.economistdiary.com/2001 and www.economistdiary.com/2023 (admittedly a preview!!)
First a summary of what the NET asked to be meidiated to integrate trust during what they foresaw as a chaotic period.
Roughly they foresaw population growth quadrupling from 2 billion to 8 billion
They were most concerned that some people would access million times moore tech by 1995 another million times moore by 2015 another million times moore by 2025. Would those with such access unite good for all. If we go back to 1760s first decade that scots invented engines around Glash=gow University James Wat and diarist Adam Smith we can note this happened just over a quarter of millennium into age of empire. WE welcome corrections be this age appears to have been a hectic race between Portugal, Spain, France Britain Netherlands as probbly the first 5 to set the system pattern. I still dont understand was it ineviatble when say the Porttuguese king bet his nations shirt on navigation that this would involve agressive trades with guns forcing the terms of trade and colonisation often being a 2nd step and then a 3rd steb being taking slaves to do the work of building on a newly conquered land. I put this way because the NET were clear almost every place in 1951 needed to complete both independence and then interdependence of above zero sum trading games. Whils traidning things runs into zero sums (eg when there is overall scarcity) life critical knowhow or apps can multiplu=y value in use. Thats was a defining value in meidting how the neyt's new engineering was mapped. Of course this problem was from 1945 occuring in a world where war had typiclly done of the following to your place:
your capital cities had been flattened by bombing - necessitating architecture rebuild as well as perhaps an all chnage in land ownership
your peoples had gone through up to 6 years of barbaric occupation -how would this be mediated (public served) particularly if you were a nation moving from radio to television
yiu mifgt eb britain have been on winning side but if huge debt to arms you had bought
primarily you might be usa now expected by most outside USSR to lead every advance'
in population terms you might be inland rural (more than half of humans) where you had much the least knowledge on what had hapened because you had been left out of the era of connecting electricity and communications grids
The NETts overall summary : beware experts in energy will be the most hated but wanted by national leaders; and then far greater will be exponential risk is the most brilliant of connectors of our new engines will become even more hated and wanted. We should remember that the NET did not begin with lets design computers. They began with Einstein's 1905 publications; newtonian science is at the deepest limits systemically wrong for living with nature's rules.
WE can thrash through more understanding of how the NET mapped the challenges from 1951 at https://neumann.ning.com/ Unfortunatnely nobody knew that within 6 years of going massively public in 1951 with their new engineering visions, all of the net would be dead. One of the most amzaing documents I have ever seen is the last month's diary of von neumann roughly October 1955 before he became bedridden with cancer. All over usa engineering projects were receiving his last genius inputs. And yet more amazing for those interested in intelligence machines is his last curriculum the computer and the brain scribbled from his bedroom in bethesda and presented posthumously by his 2nd wife Klara at Yale 1957 before she took her own life about a year later. A great loss because while neumann had architected computers she had arguably been the chief coder. Just to be clear Turing also left behind a chief coder Jane who continued to work for Britain's defence planning at cheltenham for a couple of decades. Economistwomen.com I like to believe that the founders of brainworking machines foresaw not only that women coders would be as produytive as men but that they would linking sustainability from bottom up of every community. At least that is a valid way of looking at how primarily 1billion asian women batted the systemic poverty of being disconnected from the outside world even as coastal places leapt ahead with in some cases (G Silicon Valley, whatever you call Japan-Korea south-Taiwan-HK-Singapore access to all of 10**18 times moore
Epoch changing Guides
1 AI Training AI Training.docx
2 Exploring cultural weaknesss of encounters with greatest brain tool.docx
help assemble 100000 millennials summitfuture.com and GAMES of worldrecordjobs.com card pack 1 i lets leap froward from cop26 glasgow nov 2021 - 260th year of machines and humans started up by smith and watt- chris.macrae@yahoo.co.uk-
WE APPROACH 65th year of Neumann's tech legacy - 100 times more tech decade - which some people call Industrial Rev 4 or Arttificial Intel blending with humans; co-author 2025report.com, networker foundation of The Economist's Norman Macrae -
my father The Economist's norman macrae was privileged to meet von neumann- his legacy of 100 times more tech per decade informed much of dad's dialogues with world leaders at The Economist - in active retirement dad's first project to be von neumanns official biographer - english edition ; recently published japanese edition - queries welcomed; in 1984 i co-authored 2025report.com - this was celebrating 12 th year that dad( from 1972, also year silicon valley was born) argued for entrepreneurial revolution (ie humanity to be sustainable would need to value on sme networks not big corporate nor big gov); final edition of 2025report is being updated - 1984's timelines foresaw need to prep for fall of brlin wall within a few months; purspoes of the 5 primary sdg markets were seen to be pivotal as they blended real and digital - ie efinance e-agri e-health e-learning and 100%lives matter community; the report charged public broadcasters starting with BBC with most vital challenge- by year 2000 ensure billions of people were debating man's biggest risk as discrepancy in incomes and expectations of rich & poor nations; mediated at the right time everyone could linkin ideas as first main use of digital webs--- the failure to do this has led to fake media, failures to encourage younger half of the world to maxinise borderless friendships and sdg collabs - see eg economistwomen.com abedmooc.com teachforsdgs.com ecop26.com as 2020s becomes last chance for youth to be teh sustainability generation
© 2026 Created by chris macrae.
Powered by
