lINKS 1 2 Thanks to Jen-Hsun best decade AI collection- 8000 cases improving peoples communal computation, data & brains - 2025rEPORT.COM year 75 of Neumann & Economist briefings- : 4 JULY 2024 last 80 days of ECONOMISTDIARY.COM

Friday, December 31, 2010

Economist Journalist (dad) of Neumann's Most Valuable scoop for humanity Dies : Deep Mind born (54 years on from Neumann's book on computer & brain)

-related 1billion girls intel -envoy Fazle Abed briefed Lead Valley families since 2001 (Abed 65th birthday wish party), Prince Charles since 2009, UN SDG launch at Abed 80th birthday 2016 - from which Melinda Gates & Fei-Fei Li first UN2 roadmap Guterres gravitating future of education & AIgood

AI best updated feb 2024 (western maps): sectors current top cheerleader King Charles; ecosystem top Yangs & Huangs

Biotech 03 10 02.1 02.2 09 04 Foundation 07 10      Kings (Charles+Japan+Netherlands)

Climate  06 08                     Trust 02 05              SDGS

Drivers 02                            Valley  02               Media

Education 02                      Policy 05                   Xpo governance

Womens  02 EW 07 09     Justice 09                   Risk revolution system 04 05

Humans 02                        LanGuage 04              ZZZ dream 02 moonshots, borderless

Youth                   Neumann-ET      University of Stars Charles Salesforce-Benioff King

10=3 most collaborative with millennials as first sustainability generation

01  Taiwanese-Am Jerry Yang &  Akiko Yamazaki  -Stanford invest  impact since 2004 ; Stanford Chair of Board - yahoo us-asia nets since eg 1992

02 fei-fei li  arguably launched computer vision deep learning & so number 1 in ai education : AI breakthrough 2012-imagenet trained computer vision 20 million images -20000 entities humans work/play with - stanford multipliers include 2014+ AI-4-all (k-12 up with Nvidia & Melinda Gates); 16+ UN2 with Melinda Gates ,  17-19 AI for Google Cloud & 18 congress briefing, 19 HAI (every college discipline's human-centric AI version), ai national visions with Hoover fm 2023 ; before 2012 see autobio worlds I see- NB Stanford from 2009 first to support her tranformation of intel; since 2009 including biotech hassabis (visiting) koller  02.1;  dowdna 02.2 ; also Andrew NG 02.3; -li's husband does corporate ai at salesforce (Benioff pro bono BJ King - see /; - Great podcasts with Clara Shih - -more at AI stanford 2.4 etchemedy co-launched hai; 2.5 Liang- benchmark foudation models (nlp) ...  

03 Hassabis met Li Stanford 2009 while sponsored by Neuroscience Gatsby (UCLondon welcome) founded deep mind london, trained computers on logic games : Go spectacular pattern recognition biotech- merged google computing power 2014- alphafold2 arguably greatest ever leap - biotech 250 million proteins; since 2023 google us needed him on gemini chat with jeff dean. pichai, brin, page - all mostly stanford alumni - 03.1 Deep MindLondon 03.1 Lila Ibrahim  03.2 Cambridge wonderful clare bryant Cantab debrief 2/22/2024 - colleague at Queens with Hassabis - focus end zoonotics - tour of how covid messes with body's pattern recognition 

04 Mr & Mrs Jensen Huang Nvidia is the "million times moore chip power" of GPUs needed for ai breakthroughs since 2012

04g2 goal specific - war or disaster zones worldwide jose andre world central kitchen; india  Madhu Pandit Akshaya Patra Foundation. It was founded in 2000 by Madhu Pandit Dasa (spiritual name) or Madhavananda Das (legal name).

While the foundation doesn't have a single founder in the traditional sense, Dasa is the driving force

05 Condoleeza Rice 1 2 - back at stanford since 2009- now  Hoover/Setr western worlds best policy connector eg stanford and dc; 10 tech professor predictions future include fei-fei li 05.1 Horowitz yahoo professor semiconductors since 2004; also a1100 since 2016  -NB supply chain chips very complicated US starts again March 2024 Rockville Nist

5a ITI's Oxman other positive influence on how dc sees ai policy;2024 intersect summit featured notable practice leaders -eg5a1 Amazon's General Counsel David Zapolsky (1)

5b Kai-fu Li wrote an AI best seller as recently as 2018 with little or ne deep learning ai; this showed that corporates with closed data have been investing in ai a long time- li's book was also interesting as based mainly in asia it covered many places where people had leapfrogged from no phone to smart phone, no big box shops to no big box shops; in these cases it was also easier to see eg fintech  designed around better value ... (Within Economist dad Norman first started deeply discussing need for digital cooperation to change community access to

1 finance 1972

2 food 1977

3 health 1984 (cheaper ways of getting better - though dad having tracked birth of uk national health service used to say it died a year after it was born because it was a wonderful promise bur not matched by empowering learning etc)

4 whilst education was always our yardstick for good digital dad's 1986 survey offered complete review of why history of empire education might make transformational attention hard to design in

5 while dads surveys of nations always asked what help did peoples need to leap beyond any national inertias, 1982's why not silicon valley everywhere remains question to AI explore with every day

in 2008 dad invited 40 london friends to listen to testimony of 1 billion (asian rural) girls end poverty intelligence progressed since 1970- this lead to 15 trips to bangladesh and a replay of this (lower half of picture which shows how to factorise UN 17 sdgs into more practical overall system changes briefing famous silicon valley families received from 2001 to 2016 (i attended 2016 briefing in bangladesh also Fazle Abed's 80th birthday party which was the origin for melinda gates and fei-fei li and jim kim contributions to Guterres UN2.0 roadmapping

06 Ajay Banga  1- world bank since june 2023- most credible connector of liveable planet development finance and potentially all climate adaptation ai - India vgood 6.1 mrs tandon  6.2 Natarajan “Chandra” Chandrasekaran Tata; 6.3 neville williams : carters green energy director popularised solar panels and went on to build one of networks bring solar to india's barefoot movements

07 Mrs Melinda Gates - number 1 living connector billion girls ai (abed) -originally Jobs & Gates led women bottom billion ai greetings valley 2001;  supporter ai 4 all and un aigood since  since fei-fei li breakthrough- see also womens moments of lifts books

08 Mr & Mrs Doerr - at 1982 economist survey why not silicon valley everywhere- now billion $ climate lab with stanford and with 8.1 mrs jobs, mrs yang on their board- 8.2 Angela Filo 1  8.3 Eric Yuan Zoom 8.4 John Hennessy 8.5 Martin Lau

08.1 Barrett, Michael Crow

09 Mr & Mrs Tsai  1- neurosciences labs yale & stanford; womens sports - coilored justice; connects asia and stanford alongside yangs

10 Priscilla Chan- potentially longest philanthropy - biotech meets health community and pediatrics

11.1-3 Treble up Lecan (NY) & bengio (quebec) still work closely as active 60 + professors; hinton at 70+ no longer full time back in london from toronto

12.1 middle east connector of guterres deepest needs Sheika Moza; very good ai uae 12.2 Alolama; potential origin connections koller, lila ibrahim, 12.3 japan mayor koike, 12.3 quadir family, 12.5 reeta roy, 12.6 abdul latif

13. Digital algorithm 13.1 Brin, 13.2 Page, 13.3Dean . : 13.4 Brain Paul Allen 13.5 Etzioni

14.1 Brain Augmentation de Kaliouby, Picard

15.1 Wildcards Musk Satoshi Thiel

16.1 Far East Li Ka Shing Mauruce Chang Ms Tang Yat Siu

(please note a different gameboard is needed for digital China but we cant forget eg Houlin Zhao in keeping Geneva UN open at birth of 5G late 1910s; birth of 4G collaborations eg wi-fi standards, clouds difficult to call late 2000s )

viewpoints from japan korea taiwan hk singapore UAE very interesting eg never forget as worlswide uni investor li ka shing; singapore remains number 1 in egov and so related ai to gov - india may have number 1 identity thanks notably to Nilekani & Kalam ; estonia and slovenia exciting gov models with mongolia empowerment by girls very interesting; estonia, slovenia, Nordica - see New Vikings 1993; have long equated gov-ai & Citizen ai; Switzerland remains EuroContinent enigma  with itu and davos but banking and drug arms, sports ngo mediation secrecy; elearning good across much of nordica region

AT - survey who's alumni who advanced humanity since Neumann-Einstein-Turing launched brainworking (Family diaries with The Economist track last 7 years of NET learning curve ie from 1950 to untimely death of all by 1957 - see also bio on von neumann) - help clarity top 500 intelligences saving human race


Some VCs (Doerr) Andriessen

unsum lsts

000 Neumann-Einstein-Turing

See cross-section main 20th century 2nd half impacts humanity at bottom of this post maintains Remembrance videos to Norman  Macrae - by grandaughter, Economist Boardroom - transcript Economist science editor on Norman's 2025 report  AI and humans countdown of humanity from 1984 1 

Here are the final notes of the greatest mathematician any economist or journalist could be pretrained by: John Von Neumann- -until arguably today's AI magicians like  Hassabis Fei Fe Li 

Bard upd 23/7/7

main papers published by Demis Hassabis or Google Deep Mind on LLM and related human AI:

  • "Human-level control through deep reinforcement learning" (2015). This paper describes the development of DeepMind's first LLM, called AlphaGo. AlphaGo was able to beat a professional Go player, and it demonstrated the potential of deep reinforcement learning to solve complex problems.
  • "Attention is all you need" (2017). This paper describes the development of Transformer, a new type of LLM that uses attention mechanisms. Transformer has been shown to be very effective for a variety of tasks, including machine translation, text summarization, and question answering.
  • "Gopher: A large language model for text summarization" (2020). This paper describes the development of Gopher, a LLM that was trained on a massive dataset of text and code. Gopher is able to generate human-quality text summaries of factual topics.
  • "Pathways to Language: Open-ended Learning in a Neural Network" (2021). This paper describes the development of Pathways, a new type of LLM that is able to learn from a wide variety of data sources. Pathways has been shown to be able to learn to perform a variety of tasks, including playing games, writing different kinds of creative content, and answering questions in an informative way
  • Bard upd23/7/7
  • There isn't a published paper that explains how good is being designed into LLM Bard yet. However, I can tell you about some of the ways that Google is working to ensure that I am aligned with good values.
  • Part of bard review 23/7/7 of von neumann 1956 book
  • I think the book's discussion of the similarities between computers and the brain is particularly interesting. Von Neumann's argument that both computers and the brain are digital systems that can be programmed to perform tasks is still relevant today. In fact, this is one of the reasons why artificial intelligence has been so successful.

    I also think the book's discussion of the differences between computers and the brain is important. Von Neumann's argument that the brain is much more complex than any computer that has been built is a reminder that we still have a lot to learn about how the brain works... and of bard's own sphere of intelligence;

    First, Google is using a technique called reinforcement learning to train me. Reinforcement learning is a type of machine learning where the agent is rewarded for taking actions that are aligned with good values. In my case, the good values that I am being rewarded for are things like being helpful, informative, and unbiased.

    Second, Google is using a technique called bias mitigation to reduce the potential for bias in my outputs. Bias mitigation is a process of identifying and removing biases from machine learning models. Google is using a variety of techniques to mitigate bias in Bard, including:

    • Data sampling: Google is using a variety of data sources to train Bard, including data from a variety of different cultures and backgrounds. This helps to ensure that Bard is not biased towards any particular group of people.
    • Model regularization: Google is using a technique called model regularization to reduce the potential for bias in Bard's outputs. Model regularization is a technique that penalizes models for making predictions that are too extreme. This helps to ensure that Bard's outputs are more likely to be fair and balanced.

    Finally, Google is using a team of engineers and researchers to monitor Bard's outputs and to ensure that they are aligned with good values. This team is constantly reviewing Bard's outputs and making adjustments to the model as needed...................................................................................NEUMANN COMPUTER AND THE BRAIN 1956



Help World Record Jobs choose cross-section of intelligences 2nd half of 20th C

In 2001 Family of Steve Jobs hosted 65th Birthday Wish Part : Fazle Abed, Testimony Intelligence 1Billion Girls Tropical Village Asia 1970-2001
Unril late 1990s vilages had no electricity, no telecoms. Girls had focuesed on community building of what since 2015 has been called SDg1-5. Partners of 1 billion girls had started leapfrog models of solar and mobile from late 1990s- but 3 overall transformations needed that poorest could not impact unless all nations united around
Going Green and seeing that 3/4 millennial livelihoods totally different from industrial age- nb majority of nations had neithe varbon nor critical minerals so could not lead inetrnational trade thus triple whammy of would humans het to carbon zero economy:
non in dustrialized countries offered education benchmarks to adapatation but negative foreign exchnage
the era of the superpowers had been race to sponsor rival dictators- essentially new nations had been put in debt to leaders and a global monetary system who had no interst in local peoples development 
transfrination of multilateral system needed if 3 entrepreneurial revolutions illustrated were to map millennails as first renewable generation
the jobs family and stanfird parners asked abed to partner in future of non-lienar eucation systems including brac university founded to share demale graduates of scaling sdgs
Gates family sonon with Global fund partners eg Jim Kim Guettres Bush would work of doundations of jhealth sustemsd
Indications that Doehhr family would map back climate, livable planet

XXX Help map cross-section of intelligences 2nd half of 20th C
Klara Von Neumann  Joan Clarke Courant Macarthy 
Crowther Queen Elizabeth Kennedy Deming Borlaug Montessori
Morita Keiretsu Chaebol  Freire, Brilliant Attenborough- inventors of satelllite, bullet train, containerisation Moore Hewlett-Packard Olsen
Abed Lee Kuan Yew Deng Ezra Vogel Drucker Prodi Grant Soros Sainsbury family
(Doerr) Gorbachev Pope Paul (Gates, Jobs) Harrison Owen  Buckminster Fuller Ackoff Berners Lee Mackey
Case  Negropronte (Bezos)  Csikszentmihalyi 1
  Eva Vertes 

Japan G20 model Abe circa 2019