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.

Sunday, April 30, 2023

Is DeepMind the most humanly valuable AI yet?

@Stanford, 2019: The emergence of a new kind of Artificial Intelligence has the potential to radically alter how we live our lives. This new era can bring us closer to our shared dream of creating a better future for all of humanity. It will also bring opportunities and challenges that we can’t yet foresee, requiring a true diversity of thought. Stanford HAI aims to become a global, inter-disciplinary hub for discussion and development of AI.

The search for Intel begins in different times, places, gens. 73 years ago, my dad was sent from London's Economist to spend a year meeting Von Neumann in Princeton as well as a few other New Yorkers: in a small but intentionally optimistic way journalism out of King Charles village in London seeks to do- we've  been hunting out good AI stories ever since. 

Try this current AI Breaking News story to decide whether Human-centric AI's dance through life is for you.
Hai Stanford (Human Centric AI) was started in 2019 with support of Stanford President ndleladership of Fei-Fe Li and   John Etchemendy, professor of philosophy and former Stanford University provost
Stanford Video

HAI Founding Distinguished Fellows

The inaugural group of Distinguished Fellows will include: Yoshua Bengio, University of Montreal; Rodney Brooks, MIT; Erik Brynjolfsson, MIT; Jeff Dean, Google; Daniel Dennett, Tufts University; Susan Dumais, Microsoft Research; Edward Feigenbaum, Stanford University; Barbara Grosz, Harvard; Demis Hassabis, DeepMind; Geoff Hinton, University of Toronto; Eric Horvitz, Microsoft Research; James Manyika, McKinsey & Company; John Markoff, Center for Advanced Study in the Behavioral Sciences; Helen Nissenbaum, Cornell Tech; Judea Pearl, UCLA; Stuart Russell, UC Berkeley; Mustafa Suleyman, DeepMind; Terry Winograd, Stanford University; and Hal Varian, Google.

tSanford President Marc Tessier-Lavigne said artificial intelligence has the potential to radically change how we live our lives. “Now is our opportunity to shape that future by putting humanists and social scientists alongside people who are developing artificial intelligence,” he said. “This approach aligns with Stanford’s founding purpose to produce knowledge for the betterment of humanity. I am deeply thankful to our supporters who are providing foundational funding for the institute, which is a critical element for our vision for the future of Stanford University.”

Stanford HAI formally launches at a symposium on Monday, March 18 featuring speakers such as Microsoft founder and philanthropist Bill Gates and California Governor Gavin Newsom, as well as leading experts Kate Crawford of NYU, Jeff Dean of Google, Demis Hassabis of DeepMind, Alison Gopnik of UC Berkeley, Reid Hoffman of Greylock Partners and Eric Horvitz of Microsoft Research. (Watch the livestream here.)

Recursion 1 - from long video above

2023- Hai Stanford is celebrating leaps forward from covid era with extraordinary talks like this

co-blog note: We humans. slow as we may bem are reducing this 90 minute youtube and Transcript to key cases and methods mentioned by fei-fei li and demis hassibis -of course you are referred to the 90 minute version at youtube

I am Fei-Fe Li   HAI stanford ie lab Human-centered AI

Welcome Demis Hassibis founder DeepMind born 2010- now an alphabet/google company

Demis mental superpowers began in games, and doctorate in cognitive neuroscience -brain architecture - at MIT (check him out as alumni of Uni College London, MIT and Harvard so this is how he came to machine intel – 

DEEPMIND 2010 is truly one of first new wave AI companies acquired google 2014 but retaining its sphere of influence out of London. (indeed this may be Demis first san francisco region visit since covid even though he was on HAI stanford founding council 2019

deepmind commercial breakthroughs include data centre energy, and mapping the world’s proteins through the very impressive AlphaFold 

 a world leader in realms of deep learning and reinforcement learning and this reflects gaming roots -eg AlphaGo world champion

there are hopes that DL will become climate AI leader –I invite student Q&A on that at end indeed Demis is in midst of pioneering Artificial General Intelligence as potentially Epoch Changing Tech changing the very fabric of human lives

AI is having a Public Awakening moment and it's no longer just a niche field that

nerds like us play around ; it's impacting human life society and our future and

Hai Stanford has been missioned to be one of the forums that will host this kind of

intellectual discourse about Ai  - I cant think of more timely speaker than Demis

========================as at 5/3 rest undrr construction


Demis – thanks so much Fei-Fei – yes now covid’s hoefully passing I hope to be in bay area more often and share  real passion of mine which is to use AI to accelerate


scientific discovery with generative Ai and and large language models and and the work we're doing

deepmind was founded way back in 2010 that was almost like medieval times


in 2010 it was very difficult to o raise our seed round of you know a few hundred thousand dollars compared with today’s billion dollar rounds  - in 2010 few were  talking about AI Shae Legg DM’s chief scientst annd I felt very isdolated – people seemed to have forgotten AI  as field to build a human-like intelligence so it's been astounding what the last few months have brought as wwe see comvergence of a lot of different

DM has always been big proponent of reinforcement learning and understanding

7 the human brain - my PhD I worked on the hippocampus and memory systems and Imagination made some interesting discoveries in in that domain that I thought would also potentially carry over into ideas for AI systems architects together with QC Advent of lot of compute power and specifically GPUs (Graphic Processing Units) which ironically of course were invented for games so everything for me as you'll see comes back to games one way or another um

We began DM as king of Apollo Program of Games

First we revited earliest game systems Atari space invaders and 50 games from the 1970s  -we uh and maximized the score jaround n the raw pixels on the screen so it was very much um probably the first example of a kind of end-to-end learning system on something that working on something really challenging perceptually


challenging lan Atari game swas a incredible moment for us and I remember when back in 2011 when we were struggling to even win a single point at a game like pong and we was jwondering well maybe we're just 20 years too early with these ideas of of learning systems and then suddenly it won a point then it won a game and then it didn't lose any points; by 2013 it was playing all the Atari games of course we then took that much further and and

However our big opportunity came with Alphago  - world champion of game like GO

the super complex game that's played in Asia

obviously famously in 2016 we had this massive million dollar challenge match in Seoul 200 million people watched thematch around the world an alphago famously won that match for one but more important than it winning move 37 which blew away all past human players startegies

Today we can design game winners one thing that's holding us back is that we don't really know how to ask aplha to design a great game not in a way that it could understand

 As yet we havent found way to ask alpha to invent a game that only takes five minutes to learn but many lifetimes to master is aesthetically beautiful can be completed in in 10 hours of you know play so it fits into a human day


Thesek are inds of things is what I would kind of give as instructions and then I'd hoped it would come up with something like go but there's no real way to do tgis yet

so how does the self-play system work and I'm just going to combine together um actually a range of systems together

Back to what we can do16:10

Face-Off match a hundred game match of old play -version V1 versus new veriosn V2 and threshold in our case we set a 55 win rate threshold where if V2 beats V1 by

above that threshold you assume that it is significantly uh better and then you

replace the Master System that the generator system with that new V2 system now and you go around of course


iterating this round so now you could play another 100 000 games with V2 so it's slightly stronger so that means the


generated data is slightly better quality -continue to generate more data another hundred thousand games with V2 so then now you have 200 000 games uh to train a


general way of thinking about  Ai and the and the um the idea of coming up with a solution to a problem


se've been very fortunate over the last decade we've been part of um kind of creating many big breakthroughs um inall sorts of different games all of them kind of landmark uh results at the Atari one the alphago one I mentioned Alpha


zero I just talked about generalizing that to every two-player game and then finally Alpha star which was our program


to uh beat Grand Masters players at Starcraft 2 which is the most complex


real-time strategy game computer game and it has extra challenges over board games of being partially observable uh


it needs things like long-term planning so it's complex in in in in more challenging ways than a board game and


so this was all of our work in in games now of course although I love games always have done playing them designing


them using them for training for AI I've sort of used games in every way possible but they've always although it's been


very fun to do that um it's always been a kind of means to an end not an end in itself right the end was never to just win it go or Win


It win at Starcraft it was to build it was to use games as a convenient proxy


to test out our algorithmic ideas so that we could apply them to important real world problems

No comments:

Post a Comment