265SmithWatt 75Neumann 55.YunusAbed , AI20s.com JHDHFL 20
KingCharlesLLM DeepLearning009 NormanMacrae.net EconomistDiary.com Abedmooc.com
AIVeryGood testimonies Feb 24: Nvidia CEO LLM World Gov UNG 17 AI Policy Condy Rice B16-9: World Bank Ajay Banga : Help AI World Series code & catalogue AI champions advancing humanity and matching opportunities of sustainability goals and millennials' world champions |
Onwards with King Charles AI World Series cf onwards world bank Banga's liveable Planet & Guterres UN2.0
@ Top of Millennials Intelllgence World
@ King Charles @ Hasabis uk-us leader of natural science AI;
@Fei-Fei Li leader code AI of 20000 everyday identities (Imagenet 2012 ends AI Winter)
@ Bengio from Canada nominated to diarise Ai world series as well as corresponding role Guterres UN AI Science panel
longer list of corporates ....
Tags:
Views: 306
400 Jensen Huang - some copilot flights in health with 402,403 Priscilla Chan & Mona Flores, Global Head of Medical AI, NVIDIA, 404 Renee Yao lifesciences ecosystem Business Development Healthcare and Life , NVIDIA
Renee leads ecosystem business development in healthcare life sciences, focusing on scaling partners (global system integrator, solution delivery partners, independent system integrators, cloud service providers, and startups) critical for expediting ecosystem go-to-market strategies and enhancing NVIDIA platform adoption. Managing a diverse portfolio, she also oversees more than 2,000 healthcare startups as independent software vendors in segments like digital health, medical instruments, medical imaging, genomics, and drug discovery. In prior roles as a senior product manager and product marketing manager for AI systems, Renee shaped bundle solutions and reference architectures for sectors spanning self-driving cars, telecom, and big data analytics. Beyond her corporate journey, she's founded six startups in domains including health insurance, fashion, AI toys, and more. A University of California, Berkeley Haas School of Business graduate with an economics and IT focus, Renee enjoys ballroom dancing, reading, and exploration during her leisure.
AI Sovereignty- Peoples Language (LLM), Data Herstory: Climate, Agri, Health, Ed-agency, Geonomics
People to check in with
Brynjohnnson ex Mit; Rob Johnson ex soros/friend brynjohnson; Cambridge in amerca east coat John Kase – official Uk west coast envoys tan white mbe; john white mbe – links hassabis london/cambridge king charles AI world serues Turing and Kings English LLM
Backed by both King Charles AI Coomonwealth World Series & Huang. UK Tech envoysin Valley Ms Tan White MBE & John White MBE – connect Hassabis London-Cambridge: Stanford, any twin aigood city.
stanford with Li & Rice Ai futute of every discipline
Case Barbados (extension cases – carribean, kenya)
Case partners of commonwealth AI
Nvidia Huang AI Sovereignty Don’t get drownede in AI Safety; Positive reasoning for NAIRRS , and why LLM is not the core focus without 2012 AI breakthroughs: Perception, Natures AI, Million times lowe cost for deep data generative computing. Huang shared his views that every country should have its own AI system. This will empower nation-states to serve their specific cultural and language needs and leverage their particular business strengths in the age of AI. Huang believes companies should own the AI intelligence and data they produce. “It codifies your culture, your society’s intelligence, your common sense, your history – you own your own data,” AI sovereignty refers to the strategic development and deployment of AI technology to protect national security, economic competitiveness, and societal well-being. This is in contrast to corporate-controlled AI |
Huang additional Specials
Co-pilot Digital Twins Taiwan, Weather Company www alert model
UAE – world gov keynote- why eg falcon as completely open LLM is genius
Piloting Trillion Doolar AIGood+Sectors -see 100 partners GTC2024
===============================
Boston Foci
Russ
Fady Saad MassRobotics – Robotics Climate AI
At the recent World Governments Summit in Dubai, Huang shared his views that every country should have its own AI system. This will empower nation-states to serve their specific cultural and language needs and leverage their particular business strengths in the age of AI. Huang believes companies should own the AI intelligence and data they produce.
“It codifies your culture, your society’s intelligence, your common sense, your history – you own your own data,” Huang said at the event attended by more than 4,000 delegates from 150 countries.
AI sovereignty refers to the strategic development and deployment of AI technology to protect national security, economic competitiveness, and societal well-being. This is in contrast to corporate-controlled AI, which is developed primarily for the best interests of a company, rather than the state.
The concept of a sovereign AI is not new, but now that this suggestion has come from Huang and other influential business leaders, the idea has gained significant attention in the industry. Earlier, IBM CEO Arvind Krishna also made a similar call to action by urging countries to have “some sovereign capability on artificial intelligence, including large language models for AI.” Krishan suggested that countries should set up national AI computing centers and common data sets for specific use cases.
Several countries have already started establishing a sovereign AI infrastructure, including the Netherlands. The Dutch government revealed its vision for GenAI, which includes further investment in the nation’s open large language model, GPT-NL. The European Union is also pursuing sovereign AI by investing in supercomputers to support AI startups in the region.
Taiwan is also investing in sovereign AI. It is building a government-funded LLM named Taide with a primary objective to counter the influence of AI tools from China such as Baidu’s Ernie bot. The Taiwanese government wants to restrict the use of Chinese AI tools as they often provide politically biased information.
While sovereign AI infrastructure has to be led by governments, the private sector plays a vital role in achieving this vision. The private tech industry must cooperate with governments to build a robust API infrastructure. This is where the support of major tech players, such as Nvidia and IBM, is critical to the successful development of sovereign AI.
The Dutch government suggests an “open strategic autonomy” structure where local companies have the freedom to work with foreign governments but have the ability to work independently as needed.
Speaking at the summit in UAE, Huang urged business leaders not to be “mystified” by AI as the capabilities offered by the technology offer great potential. An increasing number of AI events are happening in the UAE, which has become a center for AI innovation in the Middle East. PwC projects the AI market in the region to reach $320 billion by 2030.
==================================
COULD COMPUTING MACHINES BETTER SERVE HUMANS IF THEY UNDERSTOOOD 19999 ENTITIES HUMANS MOST WORK & PLAY WITH
At the start of the 21st C there may only have ever been 4 people who had dared asked this question. Three had left us in 1950s. This left one 25 year old female graduate to ask this question. For the next 11 years almost every American academic (except a few at Stanfird from 2009) gave her the thumbs down.Then at the 3rd annual summit she had arranged to give computers 20 million image databank of 19999 entities (plus humans) a maths algorithm confirmed this was the most valable question computing had ever been applied to. Or more accurately this summit prompted the biggest transformation in tech investment - by 2019 every tech investir was saying that coding computer vision was obvious.
Actually there are at least 3 investment races going on:
continuing to maximise what computers can do now they can be asked to sort out problems(eg deep data) around the 19999 entities humans develop life on earth with - yes i get that
playing with nature's 25 million proteins - yes this second neuroscience computation breakthrough certainly is the way to go if you do biotech or anything that innovates with matures nano-science
but the leap to asking computers to woirk with anything humans hsve ever written (the large language models) i personally wonder about that- if computers are training up on educational materials that I understand but if they are training up on anything ever written, I just hope we are not going to again get lost in the woods from the trees as we have so often since neumann-einsiein-turing parted.
#!$ Compare the brainstrust linking in Sandbox QA and UK's leading female tech envoy in Valley, Burmese-Brit Ms Tan White MBE
with final examining pilot UK AI panel
Country | Nomination |
---|---|
Australia | Professor Bronwyn Fox, Chief Scientist, The Commonwealth Scientific and Industrial Research Organisation (CSIRO) |
Brazil | André Carlos Ponce de Leon Ferreira de Carvalho, Professor, Institute of Mathematics and Computer Sciences, University of São Paulo |
Canada | Doctor Mona Nemer, Chief Science Advisor of Canada. |
Chile | Raquel Pezoa Rivera, Academic, Federico Santa María Technical University |
China | Doctor Yi Zeng, Professor, Institute of Automation, Chinese Academy of Sciences |
EU | Juha Heikkilä, Adviser for Artificial Intelligence, DG Connect |
France | Guillame Avrin, National Coordinator for AI, General Directorate of Enterprises |
Germany | Professor Antonio Krüger, CEO, German Research Center for Artificial Intelligence. |
India | Professor Balaraman Ravindran, Professor at the Department of Computer Science and Engineering, Indian Institute of Technology, Madras |
Indonesia | Professor Hammam Riza, President, KORIKA |
Ireland | Doctor. Ciarán Seoighe, Deputy Director General, Science Foundation Ireland |
Israel | Doctor Ziv Katzir, Head of the National Plan for Artificial Intelligence Infrastructure, Israel Innovation Authority |
Italy | Doctor Andrea Monti,Professor of Digital Law, University of Chieti-Pescara. |
Japan | Doctor Hiroaki Kitano, CTO, Sony Group Corporation |
Kenya | Awaiting nomination |
Mexico | Doctor José Ramón López Portillo, Chairman and Co-founder, Q Element |
Netherlands | Professor Haroon Sheikh, Senior Research Fellow, Netherlands’ Scientific Council for Government Policy |
New Zealand | Doctor Gill Jolly, Chief Science Advisor, Ministry of Business, Innovation and Employment |
Nigeria | Doctor Olubunmi Ajala, Technical Adviser to the Honourable Minister of Communications, Innovation and Digital Economy, |
Philippines | Awaiting nomination |
Republic of Korea | Professor Lee Kyoung Mu, Professor, Department of Electrical and Computer Engineering, Seoul National University |
Rwanda | Crystal Rugege, Managing Director, National Center for AI and Innovation Policy |
Kingdom of Saudi Arabia | Doctor Fahad Albalawi, Senior AI Advisor, Saudi Authority for Data and Artificial Intelligence |
Singapore | Denise Wong, Assistant Chief Executive, Data Innovation and Protection Group, Infocomm Media Development Authority (IMDA) |
Spain | Doctor Nuria Oliver, Director of ELLIS Alicante |
Switzerland | Doctor. Christian Busch, Deputy Head, Innovation, Federal Department of Economic Affairs, Education and Research |
Turkey | Ahmet Halit Hatip, Director General of European Union and Foreign Relations, Turkish Ministry of Industry and Technology |
UAE | Marwan Alserkal, Senior Research Analyst, Ministry of Cabinet Affairs, Prime Minister’s Office |
Ukraine | Oleksii Molchanovskyi, Chair, Expert Committee on the Development of Artificial intelligence in Ukraine |
USA | Saif M. Khan, Senior Advisor to the Secretary for Critical and Emerging Technologies, U.S. Department of Commerce |
United Kingdom | Dame Angela McLean, Government Chief Scientific Adviser |
United Nations | Amandeep Gill, UN Tech Envoy |
428
, Co-Founder and Chief Executive Officer, Crusoe Energy
=====expecting for example many fortune 500 companies to have larger ai budgets by 2027 than most nations - which is one reason why we primarily catalogue persons and their alumni who are innovation ai good- we welcome discussion if you think we are missing way to see whose intelligence worlds partnerships are designing ai to get back to the goals all 193 nations of UN promised to unite humans round in 2015 - as yet we see far more risk that nations are not going tp invest in in enough good ai than that too much ai will take over from humanity- we also remind non native english speakers - articificial applied to engines = man-made
MILLENNIALS CODE GUIDE WHO’s AI IS IT ANYWAY
N Neumann exponential expectations engine type 6 for brainwork , 7 for autonomous gov 2.0 |
E Einstein exp exp “ “ |
T Turing exp exp “ “ |
Wai |
Hai H1 ScienceAI eg alphafold2 H2 entity AI eg imagenet H3 every ed skills ai -blend H4 more |
Yai |
F Foundation |
I INTER – cooperation way above zero sum |
Gov2.0 |
SDG ER1 3 billion new livelihoods millennials generate ~G8 |
SDG ER2 G1-G5 community solutions- see women empowerment abedmooc.com |
SDG ER3 – Apply G6 water G7 solar to go green and to sanirise |
SDG ER4 – G9-12 Infrastructure 2.0 win-win trade www nb vast majority nations no critical minerals to play Industrial era) |
SDG ER5 POLC Goals 16 (peace)*14(Oceanlfe)=15(landlife)-13(Climate) |
SDG ER6 replace sdg17 by verygoodai & worldclass llm partnerships |
NewS 0-3 CoatalBelts Atlantic west & east, Pacific West & East |
NewS 4,5 rwo most conflicted landed NS in Americas |
NewS 6,9 four most conflicted land corridirs Eurasa & Below |
@ essential to ed3=personal learning agency world aware of intel trans this persons alumni c @ Demis Hasabis alumni of Alphafold2 - 250 million protein databank - an be the greatest heroines/heroes world has ever seen- i dont see climate crises or viral diseases being mitigated without them @ fei-fei li is education intelligences MVP- her 20000 entity databank imagenet provided breakthrough that machines can be trained to learn- this changes coding and if it hasnt yet changed any discipline studied at college, you might want to check in with stanford as vast majority of stanfird subjects are being transformed by HAI #Fazle Abed: It took 17 years (1984-2021) before either Steve Jobs or Bill Gates understood that personal networking greatest win-win is sharing life saving knowhow. Over a billion Poorest Asian village mothers provide the evidence thanks to Fazle Abed and UNICEF's James Grant from late 1970s. |
ER6 examples Jensen Huang suggest every language needs an llm as its sovereign ai; 50 small island nations suggested need to share llm as they never had critical resources of industrial age so doubly need livable planet ai (support from some rich islands eg Singapore & Ireland) |
|
MILLENNIALS CODE GUIDE WHO’s AI IS IT ANYWAY
N Neumann exponential expectations engine type 6 for brainwork , 7 for autonomous gov 2.0 |
E Einstein exp exp “ “ |
T Turing exp exp “ “ |
Wai |
Hai H1 ScienceAI eg alphafold2; H2 entity AI eg imagenet; H3 ed ai include no silos ; H4 more |
Yai |
F Foundation |
I INTER – cooperation way above zero sum |
Gov2.0 |
SDG ER1 3 billion new livelihoods millennials generate ~G8 |
SDG ER2 G1-G5 community solutions- see women empowerment abedmooc.com |
SDG ER3 – Apply G6 water G7 solar to go green and to sanirise |
SDG ER4 – G9-12 Infrastructure 2.0 win-win trade www nb vast majority nations no critical minerals to play Industrial era) |
SDG ER5 POLC Goals 16 (peace)*14(Oceanlfe)=15(landlife)-13(Climate) |
SDG ER6 replace sdg17 by verygoodai & worldclass llm partnerships |
NewS 0-3 CoatalBelts Atlantic west & east, Pacific West & East |
NewS 4,5 rwo most conflicted landed NS in Americas |
NewS 6,9 four most conflicted land corridirs Eurasa & Below |
@ essential to ed3=personal learning agency world aware of intel trans this persons alumni Z scales transformation Named Place = linkin that place (by stanford we mean whole valley-bay ) C=colored lives matter solutions |
ER6 examples Jensen Huang suggest every language needs an llm as its sovereign ai; 50 small island nations suggested need to share llm as they never had critical resources of industrial age so doubly need livable planet ai (support from some rich islands eg Singapore & Ireland) |
Examples
Fei-Feil Li @ notably Stanford HAI W Y POLC ER 2.3 without Li society would not have been valued as integral to AI as early as 2012 - connections HAI2 imagenet multiplied include NET & from 09 Hasabis Koller Ng Doudna Yang Rice Tsai from 2012 Huang Melinda Gates; 3 Alogithm professors; - AI4all; googlecloud UN , National Ai POLC Every discipline AI version
Demis Hasabis @ notably HAI HA1 Science AI may be only way humans have to be in time to prevent extinction given hassabis open sourced 250 million ptotein codes of nature- he leads Game logic designs way beyond others -out of London & Cambridge Unites Kings Charles AI & Turing
Jensen Huang -@ Stanford, Taiwan Oregon State multiplied Fei-Fei's vision breakthrough by designing million times more computational GPU; many orders of magnitude beyond typical moores law decades ; is leader of every locality needs its own LLM now to own sovereignty of its peoples data, culture and geo-diversity
Jerry Yang @ without Taiwanese American Jerry Yang and his Japanese American wife - I do not see how stanford 21st C partnership ecosystem would have stayed ahead of every pro-millennial connection grounded on both connections and wealth transferred from Yahoo ecosystem 2004 onwards. Like many Asians the Yang family are relatively humble but as surviving Diaspora Scot archivist of Economist and NET diaries my assessment criss crosses over 50 countries. See also NY Asia Society Laureates gala 2023 chris.macrae@yahoo.co.uk
, Vice President, Applied Deep Learning Research, NVIDIA
, Chief Executive Officer and Co-Founder, Imbue
In Search of General Human Intelligence before AGI
Fazle Abed @ remarkable life uniting 8 billion humans intel www.abedmooc.com in deepest knowhow f 21st c `- like Gandhi he trekked as teen to go learn from Empitre's colleges. But in Abed's case his homeland Bay of Bengal of 1950s had been recolonised by Pakistan so he wanted to learn engineering for shipping trade from glasgow university and chartered accounting. Succeeeding this he had just become regional ceo for Royal Durch Shell when half a million of his compatriots wrere killed by an intense local cyclone- with the shell campus last infrastructure left dozens of medics and others joined abed in recovimmediate recovry work (eg body bagging and preventing colera). After a few months, Shell almost got Abed assinnated. They ordered him to join Pakistan army in nextt phase of recovery. Abed escaped to london; Bangladesh's war of indepence occurred; he sold his flat in putney and returned to build 15000 vilagers homes. Basically one room huts but better than the refugee camp the war had turned his homeland into. Abed soon found he was responsible for 100000 people communities not starving nor dying of basic illnesses. He designed small village franchuses (but with positive cash flow) around rice farming, distributung basic meds etc. The number 1 aim at that stage of village mothers was not raise earnings above a dollar but raise life expectancy from low 40s to 60s. Fortunatlely abed's team invented oral rehydration saving one in infants from death by diarrhea. Abed submitted this to unicef year of child competion 1979 and won. James Grant arranged for the proze to be Bangladesh Rorual Advancement Cooperation training every rural mother in ORD. That took BRAC nationwide. Abed's business designs can be said over 50 years to involve entrepreurial games of 2 hallves with an 5 year transition. For 25 years up to 1996, every word of mouth- rural meant no electricity grids and no phones. Then from 1996 a silicon vallef prner offered abed chance to experiment with mobile and solar. Steve Jobs and Bill Gates who had invented the west's personal computer networking in 1984 admitted they hadnt understood what pooresst rural women needed. So they and silicon valley saged abed's 65th birthday wish party in 2001. Silicon valley started connecting with billion poorest gilrls intelligence needs and stanfird became the pro-millennila university with abed' foiunding poverty's ttwin university in ganglades. That's how between 2001-2012 stanfor linked in Womens Intel, Millennials Youth Intel and from 2009 HAI (with Fei-Fei Li Daphne Koller Demis Hassabis Andrew Ng supported by the Yang family and others who have made staford potentially the leading intelligence si
Deep learning africa with Hasabis & Co
G= Aigames verified VeryGood ranking - rsvp chris.macrae@yahoo.co.uk to discuss inclusions/exclusions - our criteria since 1951 aligned to NE- celbrate millennials as first renewable generation
Footnote qs to Gemini
Demis Hassabis and Safety:
Shane Legg and Safety:
Mathematics in Safety:
Example of Safety in Practice:
Imagine DeepMind is developing an AI for drug discovery. Here's how safety might play out for Hassabis and Legg:
Overall:
While both Hassabis and Legg share a concern for safety, their expertise and approaches differ. Hassabis takes a more practical, systemic view, while Legg brings a theoretical and formal logic perspective. Mathematics plays a vital role, particularly in Legg's work on formal verification. Their combined efforts help ensure DeepMind's AI advancements are developed and used responsibly
2023
https://www.regulations.gov/search/docket?filter=%22artificial%20in... lots of gov discussions ai - quite hard to sort out dates etc
latest ntia request info operational march 24 - how weights change foundation models openess and closure https://www.ntia.gov/federal-register-notice/2024/dual-use-foundati...
Stanford foundation models team july 2023 issues key response to ntia request for info https://hai.stanford.edu/sites/default/files/2023-06/Response-to-Re...
Rishi Bommasani
Researcher & Society Lead, Stanford Center for Research on Foundation Models
Ph.D. Candidate, Stanford University
Sayash Kapoor
Researcher, Princeton Center for Information Technology Policy
Ph.D. Candidate, Princeton University
Daniel Zhang
Senior Manager for Policy Initiatives, Stanford Institute for Human-Centered Artificial
Intelligence
Dr. Arvind Narayanan
Incoming Director, Princeton Center for Information Technology Policy
Professor of Computer Science, Princeton University
Dr. Percy Liang
Director, Stanford Center for Research on Foundation Models
Associate Professor of Computer Science and (By Courtesy) of Statistics, Stanford University
Given the significance of foundation models, we argue that pervasive opacity compromises
accountability for foundation models. Foundation models and the surrounding ecosystem are
insufficiently transparent, with recent evidence showing this transparency is deteriorating
further.
3 Without sufficient transparency, the federal government and industry cannot implement
meaningful accountability mechanisms as we cannot govern what we cannot see. The history of
regulating online platforms and social media foretells the story for foundation models: If we fail
to act now to ensure foundation models are sufficiently transparent, we are destined to repeat the
avoidable errors of the past.
Our submission recommends the following in response to questions posed in the RFC:
● Invest in digital supply chain monitoring for foundation models (Section 2; Questions
5, 11, 15, 20).
● Invest in public evaluations of foundation models (Section 3; Questions 3, 21, 23, 29,
30b).
● Incentivize research on guardrails for open-source models (Section 4; Question 7,
32
chris macrae said:
G= Aigames verified VeryGood ranking - rsvp chris.macrae@yahoo.co.uk to discuss inclusions/exclusions - our criteria since 1951 aligned to NE- celbrate millennials as first renewable generation
LEADERS
- Sam Altman
- Demis Hassabis VG
- Robin Li (VG)
- Clément Delangue
- Lila Ibrahim VG
- Elon Musk (VG)
- Raquel Urtasun
- Alex Karp
- Reid Hoffman
- Greg Brockman
- Marc Andreessen (VG)
- Sandra Rivera
- Aidan Gomez
- Daniel Gross
- Kai-Fu Lee (VG)
- Jaime Teevan
- Andrew Ng (VG)
- Kevin Scott
- Jensen Huang (VG)
- Clara Shih (VG)
- Alexandr Wang
- Mustafa Suleyman
- Marc Raibert
INNOVATORS
- Charlie Brooker
- Holly Herndon
- Pelonomi Moiloa
- Grimes
- Neal Khosla
- Stephanie Dinkins
- Sougwen Chung
- Cristóbal Valenzuela
- Lilly Wachowski
- Manu Chopra
- Kate Kallot
- Ziad Obermeyer
- Noam Shazeer
- Alison Darcy
- Nathaniel Manning
- Tushita Gupta
- Andrew Hopkins
- Linda Dounia Rebeiz
- Richard Socher
- Keith Dreyer
- Nancy Xu
- Rootport
SHAPERS
- Ian Hogarth
- Audrey Tang (VG)
- Meredith Whittaker
- James Manyika
- Jack Clark
- Anna Makanju
- Omar Al Olama (VG)
- Kelly McKernan
- Eric Schmidt
- Margrethe Vestager
- Anna Eshoo
- Richard Mathenge
- Sneha Revanur
- Tristan Harris
- Joy Buolamwini
- Eliezer Yudkowsky
- Verity Harding
- Ted Lieu
- Sarah Chander
- Nina Jankowicz
- Romesh and Sunil Wadhwani
- Elham Tabassi
- Dan Hendrycks
- Jess Whittlestone
- John Honovich
THINKERS
- Fei-Fei Li (VG - much more than thinker)
- Abeba Birhane
- Shane Legg (VG see footnote 1)
- Rumman Chowdhury
- Yi Zeng
- Timnit Gebru
- Kate Crawford
- Pushmeet Kohli
- Ilya Sutskever
- Yejin Choi
- Yann LeCun (VG)
- Inioluwa Deborah Raji
- Max Tegmark
- Yoshua Bengio (VG)
- Emily M. Bender
- Margaret Mitchell
- Paul Scharre
- Jan Leike
- Paul Christiano
- Kalika Bali
- Stuart Russell
- Arvind Narayanan & Sayash Kapoor
- Shakir Mohamed
- =============
Footnote qs to Gemini
i feel that Hassabis and Legg are both concerned with safety - what would be an example of safety in practice that hassabis would probably expect legg to lead? For example are they experts in different types of maths?
Show drafts
You're right, both Hassabis and Legg are concerned with safety in AI, but their approaches might differ. Here's a breakdown of their potential areas of focus and the role of mathematics:Demis Hassabis and Safety:
- Focus: Hassabis likely views safety from a more systemic and practical perspective. He might be concerned with:
- Alignment with Human Values: Ensuring DeepMind's AI systems are designed and used in ways that align with human values and societal goals.
- Transparency and Explainability: Developing AI systems that are transparent in their decision-making processes, allowing humans to understand how they arrive at conclusions.
- Mitigating Unforeseen Risks: Identifying and mitigating potential risks that could arise from unforeseen consequences of AI development.
Shane Legg and Safety:
- Focus: Legg likely approaches safety from a more theoretical and formal logic perspective. He might be concerned with:
- Formal Verification: Applying mathematical techniques and logic to formally prove the safety and correctness of AI algorithms. This involves ensuring the AI cannot perform unintended actions or cause harm.
- Control Mechanisms: Designing mechanisms to control and oversee AI systems, preventing them from exceeding their intended purpose or becoming uncontrollable.
- Long-Term AI Risks: Considering the long-term philosophical and existential risks posed by highly advanced AI and exploring ways to mitigate them.
Mathematics in Safety:
- Formal Logic: This branch of mathematics is crucial for Legg's work in formal verification. It allows for rigorous reasoning about the behavior of AI systems.
- Game Theory: Concepts from game theory can be applied to design AI systems that cooperate with humans and achieve mutually beneficial outcomes.
- Probability and Statistics: These fields are important for Hassabis' focus on risk assessment and identifying potential negative consequences of AI development.
Example of Safety in Practice:
Imagine DeepMind is developing an AI for drug discovery. Here's how safety might play out for Hassabis and Legg:
- Hassabis: Concerned that the AI prioritizes effective treatments while considering potential side effects and ethical considerations in drug development.
- Legg: Focuses on formally verifying the AI's decision-making process to ensure it cannot propose harmful or unintended drug combinations.
Overall:
While both Hassabis and Legg share a concern for safety, their expertise and approaches differ. Hassabis takes a more practical, systemic view, while Legg brings a theoretical and formal logic perspective. Mathematics plays a vital role, particularly in Legg's work on formal verification. Their combined efforts help ensure DeepMind's AI advancements are developed and used responsibly
2023
Bryan Catanzaro , Vice President, Applied Deep Learning Research, NVIDIA
,David Luan Founder and Chief Executive Officer, Adept AI
, Marc Raibert, Executive Director, The AI Institute
,Dieter Fox, Senior Director of Robotics Research, NVIDIA
Iain Cunningham, Vice President & Deputy General Counsel, NVIDIA
Kathi Vidal , Under Secretary of Commerce for Intellectual Property and Director, United States Patent & Trademark Office (USPTO)
Graham Brookie, Vice President, Atlantic Council
,Iain Cunningham Vice President & Deputy General Counsel, NVIDIA
Azita Martin,, Vice President and General Manager Artificial Intelligence for Retail and CPG, NVIDIA
Seemantini Godboie, Executive Vice President, Chief Digital and Information Officer, Lowe's
Brad Lightcap, Chief Operating Officer, OpenAI
Manuvir Das, Vice President of Enterprise Computing, NVIDIA
Jim Fan, Research Scientist, NVIDIA
Percy Liang, Associate Professor and Director of CRFM, Stanford University, Co-Founder, Together AI
Priscilla Chan, Co-Founder and Co-CEO, Chan Zuckerberg Initiative
Mona Flores, Global Head of Medical AI, NVIDIA
Chetan Sharma, Chief Executive Officer, Chetan Sharma Consulting
Chris Penrose, Global Head of Business Development – Telco, NVIDIA
Chris Penrose, Global Head of Business Development – Telco, NVIDIA
Soonmin Bae, Senior Vice President, KT
Advancing the Energy Transition With AI-Powered Innovation [S63419]
Nefeli Moridis, Developer Relationship Manager, Subsurface, Global Energy Team, NVIDIA
Marc Spieler, Senior Managing Director Energy, NVIDIA
Detief Hohl, Chief Scientist Computation and Data Science, Shell
,Alexandra Mousavizadeh CEO, Evident
Chintan Mehta, Chief Information Officer and head of Digital Technology and Innovation, Wells Fargo
Azita Martin, Vice President and General Manager Artificial Intelligence for Retail and CPG, NVIDIA
,Arsen Avaklan Chief Executive Officer and Founder, Cooler Screens
Ryuji Akakawa, Vice President, Research Institute of Advanced Technology, Softbank
Soma Velayutham, General Manager, AI and 5G, NVIDIA
Lilach Ilan, Global Head of Business Development - Telco Operations, NVIDIA
Dohit Batra, General Manager and VP, Telecom, Media & Technology Industry, ServiceNow
,Renee Yao Ecosystem Business Development, Healthcare and Life Sciences, NVIDIA
Eliot Hershberg, Biotech Partner, Not Boring Capital
Andrew Gostine, Artisight
Alex Luthwaite, Senior Vice President, Show Systems Technology, Sphere Entertainment Co.
Sepi Metamedi, Sr. Product Marketing Manager, Live Media Solutions, NVIDIA
Paul Breen, Vice President, Playback, Sphere Entertainment Co.
Joshua Grow, Senior Vice President, Studio Core Technology, Sphere Entertainment Co.
Andrew Johnson, Principal Systems Engineer, 7thSense
Chase Lochmiller, Co-Founder and Chief Executive Officer, Crusoe Energy
Korea summit needs heck of lot of work to live up to king charles
day 1 virtual national leaders with few corporates
day 2 real in seoul with donellan attending from uk
https://www.gov.uk/government/news/uk-and-republic-of-korea-to-buil...
all to play for around safety report edited by bengio- this will show which of the 3 oroginal algorithm professor still able to keep up with rapidly innovating maths
lecun seems to be positive player out of new york and only one with a contract from leading digital company metaverse
bengio and lecun share summer retreat in canada students - hopefully this will keep bengio interested in ai saving the world by being connected to best human intelligences see www.friends20.com
hinton retired to london would seem to be deeply exposed compared with world leading contributions of hassabis to climate and life sciences praised by leaders in these sectors and making the crown estate scence park in cambrdge together with london one if the west's few world epicenters that can keep up with the valley and asian american ai immigrants now desperately trying to keep millennials ai world leaping forwatd round renewable intergenerational investments
UK and Republic of Korea forging ahead with plans for the AI Seoul Summit on 21 and 22 May.
The UK and the Republic of Korea are forging ahead with plans for the next wave of global discussions on the safe development of Artificial Intelligence, with the AI Seoul Summit set for 21 and 22 May.
The summit will spearhead discussions on AI safety, addressing the potential capabilities of the most advanced AI models, building on the Bletchley Declaration and wider agreements which were reached at the AI Safety Summit in the UK last November, which included commitments from developers on AI safety.
Countries will also gather for talks on how the technology can be made more inclusive, ensuring the benefits and opportunities of AI are shared equally – and how attendees can further advance innovation. AI innovations have already helped to realise important breakthroughs in areas such as healthcare and drug discovery, and is being used to increasing effect in other settings such as education and tackling climate change.
Day one of the AI Seoul Summit will see a virtual leaders’ session co-chaired by Prime Minister Rishi Sunak and Republic of Korea President Yoon Suk Yeol. A select number of global industry leaders will also be invited, to update on how they are fulfilling the commitments made at Bletchley Park to ensure the safety of their models. This comes ahead of an in-person meeting of Digital Ministers on the second day, which is co-hosted by UK Technology Secretary Michelle Donelan, and Korean Minister of Science and ICT Lee Jong-Ho.
Next month’s summit continues the legacy of the Bletchley Park discussions, capitalising on its momentum to once again bring international governments, AI companies, academia, and civil society together to advance the global AI safety agenda. This next round of talks comes at a critical time for the technology, with increasingly capable and advanced AI models expected to be released over the course of 2024.
UK Science, Innovation, and Technology Secretary, Michelle Donelan said:
The summit we held at Bletchley Park in November was a generational moment. We agreed the historic Bletchley Declaration and have ensured discussions around AI safely are firmly on the international agenda.
If we continue to bring international governments and a broad range of voices together, I have every confidence that we can continue to develop a global approach which will allow us to realise the transformative potential of this generation-defining technology safely and responsibly.
I am looking forward to building on the ‘Bletchley effect’ with this next round of talks in the Republic of Korea, who are perfectly placed with their rich history of technological innovation to advance the global conversation on AI safety.
Minister Lee Jong-Ho of the Ministry of Science and ICT of the Republic of Korea said:
The AI Safety Summit held in Bletchley, UK last year marked a milestone in which the government, industry and academia coming together to address the potential risks of AI, and I am pleased that the Republic of Korea takes the baton from the UK.
AI is advancing at an unprecedented pace that exceeds our expectations, and it is crucial to establish global norms and governance to harness such technological innovations to enhance the welfare of humanity.
We hope that the AI Seoul Summit will serve as an opportunity to strengthen global cooperation on not only AI safety but also AI innovation and inclusion, and promote sustainable AI development.
Innovation is a particular focus for the UK’s overall approach to AI, with projects such as the Manchester Prize marking a decade-long commitment of £1 million every year by the government to tap into the technology and advance solutions to pressing challenges such as climate change and energy efficiency.
The UK continues to drive forward international collaboration on AI safety through the AI Safety Institute – the world’s first state-backed body dedicated to AI safety. The Institute has already published a detailed approach to model safety evaluations, rapidly expanded its researcher ranks, and earlier this month put pen to paper on an historic agreement with the United States on AI safety.
The AI Seoul Summit will be accompanied by the release of the first iteration of the International Scientific Report on Advanced AI Safety – a key commitment from the Bletchley Park Summit which is being independently led by Turing Prize winner Yoshua Bengio and brings together the best existing scientific research on AI safety from across the globe. The international expert review panel for the report includes representatives from the UK, the Republic of Korea, and other leading AI nations.
The UK will continue to work closely with international governments, AI companies and civil society, to ensure people across the globe can safely realise the transformative benefits of AI to unlock new opportunities, transform productivity and public services, and power economic growth.
Further details on summit attendees will be announced in due course.
The virtual Leaders’ session on day one ‘Building upon the AI Safety Summit: towards an Innovative and Inclusive Future’ will deepen the consensus on AI safety while also focusing on broader aspects of global AI governance around innovation and inclusivity.
Talks on day two will be held in Seoul, and ministers will discuss ways to ensure AI safety and explore ways to foster the sustainable development of AI.
The AI Seoul Summit is the latest international summit on AI safety, kickstarted at Bletchley Park last November and continuing with a further planned summit in France over the next 12 months.
Ahead of the AI Seoul Summit the UK has appointed Imran Shafi, Director of AI Policy at the Department for Science, Innovation, and Technology, and Henry De Zoete, the Prime Minister’s adviser on Artificial Intelligence, to spearhead preparations. Approaches to AI should complement a country’s existing strengths, which is why the UK has cemented its regulatory approach in the wake of the discussions at Bletchley Park. In February, the government published its response to the AI Regulation White Paper consultation.
The following links open in a new tab
2025REPORT-ER: Entrepreneurial Revolution est 1976; Neumann Intelligence Unit at The Economist since 1951. Norman Macrae's & friends 75 year mediation of engineers of computing & autonomous machines has reached overtime: Big Brother vs Little Sister !?
Overtime help ed weekly quizzes on Gemini of Musk & Top 10 AI brains until us election nov 2028
unaiwho.docx version 6/6/22 hunt for 100 helping guterres most with UN2.0
RSVP chris.macrae@yahoo.co.uk
Prep for UNSUMMITFUTURE.com
JOIN SEARCH FOR UNDER 30s MOST MASSIVE COLLABS FOR HUMAN SUSTAINABILITY
1 Jensen Huang 2 Demis Hassabis 3 Dei-Fei Li 4 King Charles
5 Bezos Earth (10 bn) 6 Bloomberg JohnsHopkins cbestAI.docx 7 Banga
8 Maurice Chang 9 Mr & Mrs Jerry Yang 10 Mr & Mrs Joseph Tsai 11 Musk
12 Fazle Abed 13 Ms & Mr Steve Jobs 14 Melinda Gates 15 BJ King 16 Benioff
17 Naomi Osaka 18 Jap Emperor Family 19 Akio Morita 20 Mayor Koike
The Economist 1982 why not Silicon AI Valley Everywhere 21 Founder Sequoia 22 Mr/Mrs Anne Doerr 23 Condi Rice
23 MS & Mr Filo 24 Horvitz 25 Michael Littman NSF 26 Romano Prodi 27 Andrew Ng 29 Lila Ibrahim 28 Daphne Koller
30 Mayo Son 31 Li Ka Shing 32 Lee Kuan Yew 33 Lisa Su 34 ARM 36 Priscilla Chan
38 Agnelli Family 35 Ms Tan & Mr Joe White
37 Yann Lecun 39 Dutch Royal family 40 Romano Prodi
41 Kramer 42 Tirole 43 Rachel Glennerster 44 Tata 45 Manmohan Singh 46 Nilekani 47 James Grant 48 JimKim, 49 Guterres
50 attenborough 51 Gandhi 52 Freud 53 St Theresa 54 Montessori 55 Sunita Gandhu,56 paulo freire 57 Marshall Mcluhan58 Andrew Sreer 59 Lauren Sanchez, 60 David Zapolski
61 Harris 62 Chips Act Raimundo 63 oiv Newsom. 64 Arati Prab hakarm,65 Jennifer Doudna CrispR, 66 Oren Etsioni,67 Robert Reisch,68 Jim Srreyer 69 Sheika Moza
- 3/21/22 HAPPY 50th Birthday TO WORLD'S MOST SUSTAINABLE ECONOMY- ASIAN WOMEN SUPERVILLAGE
Since gaining my MA statistics Cambridge DAMTP 1973 (Corpus Christi College) my special sibject has been community building networks- these are the 6 most exciting collaboration opportunities my life has been privileged to map - the first two evolved as grassroots person to person networks before 1996 in tropical Asian places where village women had no access to electricity grids nor phones- then came mobile and solar entrepreneurial revolutions!!
COLLAB platforms of livesmatter communities to mediate public and private -poorest village mothers empowering end of poverty 5.1 5.2 5.3 5.4 5.5 5.6
4 livelihood edu for all
3 last mile health services 3.1 3,2 3.3 3.4 3.5 3.6
last mile nutrition 2.1 2.2 2.3 2.4 2.5 2,6
banking for all workers 1.1 1.2 1.3 1.4 1.5 1.6
NEWS FROM LIBRARY NORMAN MACRAE -latest publication 2021 translation into japanese biography of von neumann:
Below: neat German catalogue (about half of dad's signed works) but expensive -interesting to see how Germans selected the parts they like over time: eg omitted 1962 Consider Japan The Economist
feel free to ask if free versions are available
0 The coming entrepreneurial revolution : a survey Macrae, Norman - In: The economist 261 (1976), pp. 41-65 cited 105
. we scots are less than 4/1000 of the worlds and 3/4 are Diaspora - immigrants in others countries. Since 2008 I have been celebrating Bangladesh Women Empowerment solutions wth NY graduates. Now I want to host love each others events in new york starting this week with hong kong-contact me if we can celebrate anoither countries winm-wins with new yorkers
mapping OTHER ECONOMIES:
50 SMALLEST ISLAND NATIONS
TWO Macroeconomies FROM SIXTH OF PEOPLE WHO ARE WHITE & war-prone
ADemocratic
Russian
=============
From 60%+ people =Asian Supercity (60TH YEAR OF ECONOMIST REPORTING - SEE CONSIDER JAPAN1962)
Far South - eg African, Latin Am, Australasia
Earth's other economies : Arctic, Antarctic, Dessert, Rainforest
===========
In addition to how the 5 primary sdgs1-5 are gravitated we see 6 transformation factors as most critical to sustainability of 2020-2025-2030
Xfactors to 2030 Xclimate XAI Xinfra Xyouth Wwomen Xpoor chris.macrae@yahoo.co.uk (scot currently in washington DC)- in 1984 i co-authored 2025 report with dad norman.
Asia Rising Surveys
Entrepreneurial Revolution -would endgame of one 40-year generations of applying Industrial Revolution 3,4 lead to sustainability of extinction 1972's Next 40 Years ;1976's Coming Entrepreneurial Revolution; 12 week leaders debate 1982's We're All Intrapreneurial Now
|
The Economist had been founded in 1843" marking one of 6 exponential timeframes "Future Histores"
IN ASSOCIATION WITH ADAMSMITH.app :
we offer worldwide mapping view points from
and these viewpoints:
40 years ago -early 1980s when we first framed 2025 report;
from 1960s when 100 times more tech per decade was due to compound industrial revolutions 3,4
1945 birth of UN
1843 when the economist was founded
1760s - adam smithian 2 views : last of pre-engineering era; first 16 years of engineering ra including america's declaration of independence- in essence this meant that to 1914 continental scaling of engineeriing would be separate new world <.old world
IF we 8 billion earthlings of the 2020s are to celebrate collaboration escapes from extinction, the knowhow of the billion asian poorest women networks will be invaluable -
in mathematically connected ways so will the stories of diaspora scots and the greatest mathematicians ever home schooled -central european jewish teens who emigrated eg Neumann , Einstein ... to USA 2nd quarter of the 20th century; it is on such diversity that entrepreneurial revolution diaries have been shaped
EconomistPOOR.com : Dad was born in the USSR in 1923 - his dad served in British Embassies. Dad's curiosity enjoyed the opposite of a standard examined education. From 11+ Norman observed results of domination of humans by mad white men - Stalin from being in British Embassy in Moscow to 1936; Hitler in Embassy of last Adriatic port used by Jews to escape Hitler. Then dad spent his last days as a teen in allied bomber command navigating airplanes stationed at modernday Myanmar. Surviving thanks to the Americas dad was in Keynes last class where he was taught that only a handful of system designers control what futures are possible. EconomistScotland.com AbedMooc.com
To help mediate such, question every world eventwith optimistic rationalism, my father's 2000 articles at The Economist interpret all sorts of future spins. After his 15th year he was permitted one signed survey a year. In the mid 1950s he had met John Von Neumann whom he become biographer to , and was the only journalist at Messina's's birth of EU. == If you only have time for one download this one page tour of COLLABorations composed by Fazle Abed and networked by billion poorest village women offers clues to sustainability from the ground up like no white ruler has ever felt or morally audited. by London Scot James Wilson. Could Queen Victoria change empire fro slavemaking to commonwealth? Some say Victoria liked the challenge James set her, others that she gave him a poison pill assignment. Thus James arrived in Calcutta 1860 with the Queens permission to charter a bank by and for Indian people. Within 9 months he died of diarrhea. 75 years later Calcutta was where the Young Fazle Abed grew up - his family accounted for some of the biggest traders. Only to be partitioned back at age 11 to his family's home region in the far north east of what had been British Raj India but was now to be ruled by Pakistan for 25 years. Age 18 Abed made the trek to Glasgow University to study naval engineering.
1943 marked centenary autobio of The Economist and my teenage dad Norman prepping to be navigator allied bomber command Burma Campaign -thanks to US dad survived, finished in last class of Keynes. before starting 5 decades at The Economist; after 15 years he was allowed to sign one survey a year starting in 1962 with the scoop that Japan (Korea S, Taiwan soon hk singapore) had found development mp0de;s for all Asian to rise. Rural Keynes could end village poverty & starvation; supercity win-win trades could celebrate Neumanns gift of 100 times more tech per decade (see macrae bio of von neumann)
Since 1960 the legacy of von neumann means ever decade multiplies 100 times more micro-technology- an unprecedented time for better or worse of all earthdwellers; 2025 timelined and mapped innovation exponentials - education, health, go green etc - (opportunities threats) to celebrating sustainability generation by 2025; dad parted from earth 2010; since then 2 journals by adam smith scholars out of Glasgow where engines began in 1760- Social Business; New Economics have invited academic worlds and young graduates to question where the human race is going - after 30 business trips to wealthier parts of Asia, through 2010s I have mainly sherpa's young journalist to Bangladesh - we are filing 50 years of cases on women empowerment at these web sites AbedMOOC.com FazleAbed.com EconomistPoor.com EconomistUN.com WorldRecordjobs.com Economistwomen.com Economistyouth.com EconomistDiary.com UNsummitfuture.com - in my view how a billion asian women linked together to end extreme poverty across continental asia is the greatest and happiest miracle anyone can take notes on - please note the rest of this column does not reflect my current maps of how or where the younger half of the world need to linkin to be the first sdg generation......its more like an old scrap book
how do humans design futures?-in the 2020s decade of the sdgs – this question has never had more urgency. to be or not to be/ – ref to lessons of deming or keynes, or glasgow university alumni smith and 200 years of hi-trust economics mapmaking later fazle abed - we now know how-a man made system is defined by one goal uniting generations- a system multiplies connected peoples work and demands either accelerating progress to its goal or collapsing - sir fazle abed died dec 2020 - so who are his most active scholars climate adaptability where cop26 november will be a great chance to renuite with 260 years of adam smith and james watts purposes t end poverty-specifically we interpret sdg 1 as meaning next girl or boy born has fair chance at free happy an productive life as we seek to make any community a child is born into a thriving space to grow up between discover of new worlds in 1500 and 1945 systems got worse and worse on the goal eg processes like slavery emerged- and ultimately the world was designed around a handful of big empires and often only the most powerful men in those empires. 4 amazing human-tech systems were invented to start massive use by 1960 borlaug agriculture and related solutions every poorest village (2/3people still had no access to electricity) could action learn person to person- deming engineering whose goal was zero defects by helping workers humanize machines- this could even allowed thousands of small suppliers to be best at one part in machines assembled from all those parts) – although americans invented these solution asia most needed them and joyfully became world class at them- up to 2 billion people were helped to end poverty through sharing this knowhow- unlike consuming up things actionable knowhow multiplies value in use when it links through every community that needs it the other two technologies space and media and satellite telecoms, and digital analytic power looked promising- by 1965 alumni of moore promised to multiply 100 fold efficiency of these core tech each decade to 2030- that would be a trillion tmes moore than was needed to land on the moon in 1960s. you might think this tech could improve race to end poverty- and initially it did but by 1990 it was designed around the long term goal of making 10 men richer than 40% poorest- these men also got involved in complex vested interests so that the vast majority of politicians in brussels and dc backed the big get bigger - often they used fake media to hide what they were doing to climate and other stuff that a world trebling in population size d\ - we the 3 generations children parents grandparents have until 2030 to design new system orbits gravitated around goal 1 and navigating the un's other 17 goals do you want to help/ 8 cities we spend most time helping students exchange sustainability solutions 2018-2019 BR0 Beijing Hangzhou:
Girls world maps begin at B01 good news reporting with fazleabed.com valuetrue.com and womenuni.com
.==========
online library of norman macrae--
==========
Ma 2 Ali Financial
health catalogue; energy catalogue
Keynes: 2025now - jobs Creating Gen
how poorest women in world build
A01 BRAC health system,
A02 BRAC education system,
A03 BRAC banking system
K01 Twin Health System - Haiti& Boston
Past events EconomistDiary.com
include 15th annual spring collaboration cafe new york - 2022 was withsister city hong kong designers of metaverse for beeings.app
© 2024 Created by chris macrae. Powered by