Urgent coopreration calls from SDGSyouth latest May 2023:::HAISDGS 1 2 3 4; 5: 30 coops making women 3 times more productive than men 6 7 8.

leaps 1 - Beyond the Moon ..: can you find good enough questions for teachers of any age group to ask AI to share

Freedom to read: if only permitted one read on humanising AI I'd pick feifei short article at https://hai.stanford.edu/sites/default/files/2023-03/Generative_AI_HAI_Perspectives.pdf rsvp chris.macrae@yahoo.co.uk if you have a different pick of a lifetime

Welcome to HAI: Gamechanging AI for humans combines unique combos of tech wizards since 2006Self-id Q: Can you introduce us to 4 main wizardly components of America’s most famous 2023 model CGPT

What is Conversational?




(see also congress debriefings april 2023 on this choice as most famous )

SO in what ways does 2023 connectivity of chatgpt go beyond any human brain however famous

Am I correct that while cgpt is fluent in many languages, 90% of your training involved texts in English. Discuss!

Are there people working on advanced CGPTs tuned to specific crises- eg where UN leader guterres made 21-22 year of SDgoal 4 crisis – education no longer fit for purpose ............we asked CGPT top 10 goods it expects Ai to help humans with in 2020s--.. Healthcare - improve diagnosis, treatment, and personalized medicine..Environment - monitor and manage natural resources, predict and mitigate natural disasters, reduce carbon emissions...Education - personalize learning, new ed opportunities, and improve accessibility for learners with disabilities..Aid and development - improve disaster response, humanitarian and economic development... Agriculture - optimize farming practices, increase yields, reduce environmental impact..Transportation - improve efficiency, safety, and reduce emissions..Energy - optimize energy consumption and distribution, accelerate the transition to renewable energy..Cybersecurity - detect and prevent cyber attacks, protect personal data, and secure critical infrastructure..Manufacturing - improve efficiency, reduce waste, and increase productivity in manufacturing..Space exploration - analyze large amounts of data and enable more efficient space exploration missions..

 Epoch changing Guides

1 AI Training AI Training.docx

  2 Exploring cultural weakness of encounters with greatest brain tool.docx

 Alphafold new Protein maps can be used to design enzymes to fight plastic pollution; potentially fight cancer with molecular syringe;   to circumvent antibiotic resistance ; to combat neglected diseases like African sleeping sickness'Chagas disease;Cysticercosis; Leprosy ]Lymphatic filariasis [Onchocerciasis ;Schistosomiasis; Soil-transmitted helminthiasis ;Trachoma ;Tuberculosis; Buruli ulcer; it may help accelerate vavvines for malaria;

You shared me that the famous Alpha models of DeepLearning ( see broadcast of 60 minutes april 2023) which has mapped every human protein saving millions of human hours of work ( biggest ever change in biotech) don’t really use C G P T- so what does deep learning ai architecture use RSDE?

What is Reinforcement Learning?

What is Specific Task instead of General Purpose?

What are Deep Neural Networks?


What are Evolutionary Algorithms?

AdamSmith.app Moral Sentiments SDGs.games mapping with Guterres AIforGood decade became sustainability's gen's last chance of south-north and east-west- or the death of United Nations' world trade transparency

Here is Chatgpt May 2023 answer to comparing itself with biotech greatest ever leap alphafold
Sure, here's an analogy that may help: Imagine that CGPT-4 is like a language teacher who has read and understood a huge number of books in various languages. It has learned to understand the patterns and nuances of language, and can generate its own sentences and paragraphs based on what it has learned. When it encounters a new piece of text, it can use its understanding of language to make predictions about what will come next, and generate a response that makes sense in context.
On the other hand, Alphafold is like a puzzle solver who has been trained on a vast number of jigsaw puzzles. It has learned to recognize the patterns and shapes of puzzle pieces, and can predict how they fit together to form a complete picture. When it encounters a new puzzle, it can use its understanding of these patterns to make predictions about where each piece should go, and assemble the puzzle quickly and accurately : to question -...................................................................................
More questions: Q: Could you extend to include wizardry of Fei-Fei Li with comparison above a teacher of 12 year olds may use to vision similar and different work on architectures of CGPT4 and Alpha Deep Learning by Demis Hassibis

You mentioned major tech companies offer catalogues – 5 minute lesson plans on different wizard components. How do you find these?

60 seconds exercise: suppose for teen earthlings: 2020s is more exciting than 1960s moonrace decade of my teens; You mentioned searching ai for beginners but what if a teacher wants to help kids imagineer back from future of 2020s possibilities or just next 3 years of AI is epoch-changing


Q: please tell me how could a 5th grade teacher explain why Stanford HAI is proud of being one of the world's leading GAN (Generative Adversarial Network?)
Chatgpt reply23/5 -: A GAN, or Generative Adversarial Network, is a type of computer program that can create new things that look like they were made by humans. It works by having two players eg two artists who are trying to compete with each other. One player, called the generator, tries to create something new, like a picture of a dog. The other player, called the discriminator, tries to figure out if the picture was made by a human or by the generator. The generator keeps trying to make better pictures until the discriminator can't tell the difference between a picture made by a human and one made by the generator.
In simpler terms, a GAN is like having a computer artist that can create new pictures that look like they were made by a person, and it gets better the more it practices.
33 years ago we started practicing core brand transformation inspired by new systems modeling -eg of CK Prahalad & Gary Hamel- typically when needing to transform as large brand entity as the UN we'd propose better start again and then reverse takeover-; we realise that's not an option UN2.0 so urgent to address what's the 9 piece combo of UN2.0 Tech Envoy Team at Guterres HQ- how contextually value roadmaps for anyone SDG partnering Guterres: Global Connectivity since 1865 (ITU); AIforgoodreborn ITU 2018 stems from Neumann peers 100 times more tech per decade since 1935 -see dad's bio of vn
Digital Cooperation launched by Guterres 2018 but seen by those valuing youth generation as antidote to failure of millennium goals to value education more that primary school; Digital Capacity Building: sustainable gov tech requires UN2 to be skills benchmark wherever gov designed to empower; this leaves 4 traditional connections of UN to digitalise inclusion commons human rights so that trust/safety is brand's reality; 9th piece CODES environmental sustainability - this seems to have emerged as it became clear that cops may lead on adaptation but adaptation needs to be borderless community replication of deep solutions
379 UN Antonio Guterres :: Family & Smithian Diary: why 1984's 2025 report published to ask Economist Readers to co-search 3 billion new jobs 2025=1985 following on prt 1 teachforsdgs.com
Learning's Unconventional Worldwide Premieres
300 vriti world premier ed3 tour ^^^ NFT V 0 1 2 3

2025Report- download monthly update 100 learning networks millennials girls love most
(Economist Surveys inspired by Von Neumann 1984-1951; why 1936 dad & von neumann started 100 year race to prevent extinction; why dad's last year nominated Fazle Abed Entrepreneurial Revolution GOAT - who do you vote for SDGoats.com

00Fazle Abed: Which educational and economic partnerships most empower a billion women to end extreme poverty, and value their children’s sustainability? Fortunately for SDGS.games 2020s, start deep village maps around partners/alumni of 50 years of servant leadership by fazle abed 1970-2019

IN 1970, life expectancy tropical villages up to 25 years below world average _skills trainers priority last mile health world’s most trusted eds needed eg epidemiologists UNICEF Grant, Brilliant, later Jim KIm –& to end starvation food's borlaug

3) last mile health
2) agriculture for village food security

4)non-linear livelihood education
5) timing what platforms partners could facilitate entrepreneurial revolution not not just inclusive community but cooperation in full and meaningful entrepreneurial employment

financial entrepreneurial revolution for nation's people history excluded from machine age
billion women's Sustainability COLLABS 

 Intergenerational collaboration entrepreneur platforms 5.1  metavillage sustainable community building - women empowered:15000 families at a time;5.2   billion asian women,5.3  brac net; 5.4   asian universities share sdg graduates 5.5  climate smart village exchanges,5.6 meta and zoom-me up scotty

BANK FOR ALL 1.1  1.2  1.3   1.4   1.5   1.6 celebrate 30 most human collaborations from developing world of last half-century - inspiring  anyone valuing UN and youth as first sustainability generation
EDUCATION  adult village entrepreneurs 4.1; primary 4.2  ; teen 4.3; university4.4 ; pre-school4.5;tech multidisciplinary luminaries 4.6 
HEALTH oral rehydration 3.1 ;para health "doordash" basic meds 3,2; scale vaccination3.3 ;tuberculosis & 3.4  Frugal processes eg wash sanitation, maternity3.5  ; James Grant School of public health 3.6
FOOD/land security 2.1  rice; 2.2 veggie  2.3    cash crops & village fair; 2.4  poultry;2.5  dairy, 2,6  14 nation leading supply chains financial opportunities to end poverty ;
....................................please tell me how could a 5th grade teacher explain why Stanford HAI is proud of being one of the world's leading GAN (Generative Adversarial Network?)
Chatgpt reply23/5 -: A GAN, or Generative Adversarial Network, is a type of computer program that can create new things that look like they were made by humans. It works by having two players eg two artists who are trying to compete with each other. One player, called the generator, tries to create something new, like a picture of a dog. The other player, called the discriminator, tries to figure out if the picture was made by a human or by the generator. The generator keeps trying to make better pictures until the discriminator can't tell the difference between a picture made by a human and one made by the generator.
In simpler terms, a GAN is like having a computer artist that can create new pictures that look like they were made by a person, and it gets better the more it practices.

Tuesday, May 30, 2023

 Hello Family & friends  have a search problem - main subject of this post below 

first some updates on AI Architect Intelligence (solutions to sustainability most coooerative crises?) from 73 years of chatter which began with Von Neumann 1951 and his peer NET - Neumann Einstein Turing diarised in a thousand interviews (and about 30 surveys each based on a month of worldwide interviews and reporting - eg Entrepreneurial Revolution 1976; Consider Japan 1962;  Silicon Valley 1982 (1 week nictoreport) in The Economist 1951-1989 which since dad's death and with 16 mentoring sessions by fazle abed and japanese and 1billiongirls.coms/girlsworldbank.com- bard.solar Neumann,ning friends and I now try to update at eg http://povertymuseums.blogspot.com Economistdiary.com linkedin unwomens these twitter subscription lists

here's the problem - i wanted to give bard every chance of a detailed answer in spite of my ignorance - if you find a shorter question please tell me chris.macrae@yahoo.co.uk

i have a search problem - i believe i know where to start with ai for eg science breakthrough- billion hours saved of phd times by Hassabis; protein dayabase - all biotech and human consequences chnaged by alphafold2;  generally where deep ai changed from 2006 with fei-fei li (now hundreds of people around her at Stanford HAI) training recognition and even training whotehouse on future of education  https://www2.ed.gov/documents/ai-report/ai-report.pdf  ; I also understand a little about where people are putting  youth's most exciting sdg stories on metaverse but I really dont understand who changed bots from selling to the gpt or llm - so i hope you may find this q&A with bard relevant - more at www.economistlearning.com - if you have time for a ny coffee before october please chose one  Q to Bard  if i want to understand who imagenet began witg I see that talking to someone whos tracked fei fei li helps; if I wanted to understand deep learning i see that talking to an alumni of hassabis helps; what I dont understand is if I want to undestand roughly how llm or gpt evolved who are the first team members (or the first articles they wrote in non jargon but for mass human readers) that I should try and track? I ask because I undestand how bots were designed to sell people stuff- but is design of bots to help humans choose what they need to learn a very different design challenge even if the bot tech is common; if there was a better question to ask to understand where llm or gpt first became educational please feel free to answer that

View other drafts

Sure, here are a few people you could talk to to understand the evolution of LLMs and GPTs:

Ilya Sutskever: Sutskever is a co-founder of OpenAI and one of the leading researchers in the field of deep learning. He is the author of several papers on LLMs and GPTs, including the paper that introduced the GPT-2 model.

Oriol Vinyals: Vinyals is a research scientist at Google AI. He is the author of several papers on LLMs and GPTs, including the paper that introduced the GPT-3 model.

Quoc Le: Le is a research scientist at Google AI. He is the author of several papers on LLMs and GPTs, including the paper that introduced the GPT-4 model.

You could also read the following articles to learn more about the evolution of LLMs and GPTs:

A Neural Conversational Model by Ilya Sutskever, Oriol Vinyals, and Quoc Le (2015)

Attention Is All You Need by Vaswani et al. (2017)

GPT-3: OpenAI's Generative Pre-trained Transformer by Brown et al. (2020)

GPT-4: Language Models are Few-Shot Learners by Brown et al. (2022)

As for your question about whether the design of bots to help humans choose what they need to learn is a very different design challenge, I would say that it is. Bots that are designed to sell people stuff are typically designed to be persuasive and to make people feel good about buying the product. Bots that are designed to help humans choose what they need to learn, on the other hand, are typically designed to be informative and to help people learn in a way that is efficient and effective.

The design of bots to help humans choose what they need to learn is a relatively new field, and there is still a lot of research that needs to be done. However, I believe that this is a very important field, and I am excited to see how it develops in the years to come.

Monday, May 22, 2023

ed3 web3 language 3 - last call to unite 8 billion humans with language

 first we coded personal computer networks -sadly this drowned in commerce/spam - all we needed was to identify open learning webs from every pscyho abuse used to seel things and lie about peoples who more dic=verse than your core group

then we coded mobile devices eg telephone and camera with computer brains inside- problem here was that behavior of humans and mother earth at every gps was now a commercial secret not a social commons

BARD.SOLAR bids thee welcome --- now we have the war between the languages ai uses- pick one and be sure you know which side to =ou are mediating - 

i welcome Q&A on this document - eg whats app chris macrae +1 240 316 8157 or linkedin UNwomens
Year 73 of merging maps &  maths of economics and Neumann AI

do you want to join older half of the world pied pipering to extinction or is there yet a species liberating way at every gps to do far smarter work with human centred ai and billions of hours of new doctoral research alphafold has gifted us on 200000 proteins the keys to how nature plays out chaotic maths at levels previously unseen to man's top down science

additional bard.solar library may 2023
ClaretoFrancis Dialogues may z
Library of ai saves world
June's library expected to start new library now that london and san francisco have twinned google deep brains

Metaverse for good also leapt forward in May for 30 minutes at the UN 

please look at this please look at this ,,I want to see this come to a few schools in Bronx/Brooklyn/Quuens so that they can also invite un visitors to see metaverse for good. Any ideas or questions?

Thursday, May 18, 2023

At EconomistJapan.com we have started to ask BARD and others how to maxi,ise ai demos at Osaka Expo - this is an ideal time to search ahead, connect Japan's UN investments in AI, and identiy ,ong-run leverage eg from bringong data science to the world stage of 2019 G7- Agenda Osaka Track. There are many "broken syste" challenges to millennials life and times  eg climate where its absolutely essential youth can bridge asian and western transformational creativity - please say if you have ideas on celebrating this . 


Also fresh off press our 73rd annual review of what von neumann might expect Good Ai worldwide to be advancing now - particularly the view that Human AI maps how well places are spending peoples time in ways unseeable before but which may now explain whether ai good leaps way ahead of harmful ai.

help catalogue where ai did good in mitagating covid rsvp chris.macrae@yahoo.co.uk

-eg was thailand's singlestore and true digital one benchmark

was valencia's xprize (itu) winner aworld class mapping model  https://ellisalicante.org/xprize_valencia

Tuesday, May 16, 2023

AI Serial Giant Leapers

Stanford President Tessier + 2 Directors appointed to lead Stanford HAI Fei-Fei Li and John Etchemendy

Reid Hoffman panel moderator of Demis Hassibis Jeff Dean Chris Manning Alison Gopnik

Michael Frank Percy Liang   Serya Ganguli

Bill Gates with Amy Jin and Stephani Tena-Meza - full speakers  -full planning committee


 Lead Peers of Von Neumann had all gone by his death in  1957 but they had left behind at least 3 innovations streams in one: hardware, coiding or software, how would human brains behaviors change the more time spent in digital world-one reminder of slow slow quick quick slow is schools- i was in last gen to use slide rulers; when i git to high school my pride & joy a pocket calculator; whilst i saw people pumnching cards to program mainframes at university in europe at least online terminals linking mini computer arrived circa 1971; and for much longer than that those who did ai were programing in heuristics from experts; this isn't what breakthrough AI has done since 2006 when eg fei-fei li started training a computer's vision analogously to a baby's brain- it took one heck of a lot of computing power to do this; and although the mobile web2 era eclipsted invenet in deep ai fir 7 or more yeras its HAI at Stanford 2019 that I'd suggest as dual benchmark for magic leaps beyond human brainpower alone and desire to maintain AI as tool to augment what humans do best

upd  NAIRR OCT 2021

This month, researchers affiliated with the Stanford Institute for Human-Centered Artificial Intelligence released a blueprint for how to build a National AI Research Resource (NAIRR), a system that would allow the broader AI academic research community to access the expensive computing and data resources to conduct fundamental and non-commercial AI research. The report, a culmination of a multidisciplinary two-quarter practicum offered at Stanford Law School and based on dozens of interviews with leading computer scientists, government officials, and policy experts, outlines the necessary steps to create this resource

Monday, May 8, 2023

Timeline of Intel and Economics

 This is what our diaries have recorded - we welcome additional diary inputs

ED: 1951 was when Economist Journalists first met Von Neumann in Princeton and decided that  the intended mediation futures of The Economist founded 1843 (to assist Queen Victoria in redesigning Empire maps towards Commonwealth goals of ending poverty and ending hunger through designing above zero-sum trade) and alumni of Princeton's maths TEN (Turing Einstein Neumann) were humanly, as well as logically, convergent.

 Von Neumann et al used the term artificial machines (probably coined historically by Babbage!)- Neumann's last work  (written during his last 18 months ) is book "The Computer and the Brain". This is fundamental to deep discussion of Human and Inhuman Artificial Intel!. Recent media frenzy demanding 6 months halt to AI seems to be as unreasonable as demanding a halt to economics  -at least from perspective of 73 year learning curve

Titles of last parts of Neumann book on Computer & Brain are: Digital and Analogue parts in the Nervous System; Role of Genetic mechanism

Codes & Their Role in the functioning of a machine: complete code, short code

Full contents

As early as 1945 Von Neumann had told his wife - my supermaths generation's work on energy is going to make scientists both the most hated and wanted of people; one day the exponential consequences of artificial machines will be even more climactic to our species future. We hypothesise the exponential systems mapping intel around Ten alumni is where to find foundations of today's crisis of opportunity and threat in HAI "double loop". Von Neumann asked Economist journalists to continuously interview (brand charter) leaders- what goods will peoples unite wherever they are privileged to first access at least 100 tines more tech per decade? The first of  The Economist's decade-long learning curves concluded 1961 (see right) 1961 reveals  5 geonomic place labs exploring 100 times mo(o)re tech from now until computer memories exceed humans capacity: Swiss corridors where coms worldwide sectors began at ITU 1865 and since 1945 UN's digital tech twin; the two UNDPrincetion corridors N to Boston via eg IBM and Yale; South by S.West via DC to Houston soecialising in energy/nuclear and space. West Coast :Francis-Clare corridor with Stanford as its epicentre. Japan south coastal belt which by 1961 had linkedin Korea S and emerging Taiwan (as Chinese minds first lab in entrepreneurial freedom) since Brit's 1860 opium wars had closed down China's trading relationships. President Kennedy approved this 5-intel-space map 1962. 

Please note the actual twinning of AI Labs (MIT and Stanford) was advanced by McCarthy 1960 on. Chatgpt credits Macarthy with coining the term AI but adds this :   John McCarthy, who was one of the pioneers of artificial intelligence (AI), did refer to John von Neumann's book "The Computer and the Brain" in his own work.

In fact, McCarthy cited von Neumann's book as a key influence on his own thinking about AI and the relationship between computers and the human brain. In particular, McCarthy was interested in von Neumann's ideas about the similarities between the processing capabilities of the brain and those of a digital computer.

McCarthy also drew on von Neumann's work in his development of the programming language LISP, which is still widely used in AI research and programming today. LISP was designed to be a flexible and powerful language that could support the creation of complex algorithms and simulations, and it remains an important tool for researchers working in fields such as natural language processing and robotics.

Sunday, May 7, 2023

Human Intel' greatest twin leapmakers? youtube case 1 Stanford HAI FFL and DL Demis Hassibis

 Youtube latest of HAI's Fei-Fei Li & DL's Demis Hassibis (some datings are approx)

4/23 Fei-Fei Li & Demis Hassabis: Using AI to Accelerate Scientific Discovery
3/23 HAI Transforming safety FFL * Hoffman

-/17 Collection - Neural Networks Visual Recognition 2mn views
-/15 How we teach computers to understand pictures |

3/23 AI vs. Human: "Everything the brain does is computable" — DeepMind CEO
10/22 DeepMind's Demis Hassabis on the future of AI | The TED Interview
6/22Demis Hassabis: DeepMind - AI, Superintelligence & the Future of Humanity | Lex Fridman Podcast #299
There’s Only Two Subjects Worth Studying | Demis Hassabis | Google Zeitgeist

Other vision spaces - coming soon:

Saturday, May 6, 2023

 FEC (Female Economics Community ) mapping is my favorite maths, According to the  world bank nearly 1.2 bn people ended extreme poverty (defined as living on less than $1.9 per day) between 1990 and 2015 . This intel integrates - dare we smithian say - the greatest human (development) economics miracle ever. Yet learning about this has been made complex. Although data shows that over 60% happened  in China, for reasons most western media obfuscates - learning how this happened has got ever more difficult since the SDGs were launched. It turns out there is a second way to understand most of the solutions which Steve Jobs and Fazle Abed discussed in 2001 brainstorming dinner. We call this FEC-  Feminine Economic Communities - as after 16 trips to Bangladesh Abed approved our goal of cataloguing top 30  women empowerment solutions as lond as we clarified that wherever we use term MOOC - C= cooperation http://abedmooc.com You can search who else celebrates understanding these women empowerment knowhow solutions- when Abed died 2019 there is no secret this included Guterres Jim Kin Abdut Latif Jpal network, the quadir family, reeta roy and mastercard foundation, Sheika Moza, Charles Yidan. Melinda Gates, various Japan networks, Jack Ma, George Soros, Schwab leader of WEF - probably many more -if you have bookmark refs : please tell us -chris.macrae@yahoo.co.uk EconomistDiary.com