>3/18 24: Similarities between Electronic Computers and the Human Brain: Thank you Jensen Huang for best week of Learning since John Von Neumann shared with The Economist 1956 notes Computer & The Brain
HAPPY 2024: in this 74th year since The Economist started mediating futures of brainworking machines clued by the 3 maths greats NET (Neumann, Einstein, Turing) people seem to be chatting about 5 wholly different sorts of AI. 1BAD: The worst tech system designers don't deserve inclusion in human intel at all, and as Hoover's Condoleezza Rice . 2 reports their work is result of 10 compound techs of which Ai is but one. Those worst for world system designs may use media to lie or multiply hate or hack, and to perpetuate tribal wars and increase trade in arms. Sadly bad versions of tv media began in USA early 1960s when it turned out what had been the nation's first major export crop, tobacco, was a killer. Please note for a long time farmers did not know bac was bad: western HIStory is full of ignorances which lawyer-dominated societies then cover up once inconvenient system truths are seen. A second AI ecommerce type (now 25 years exponential development strong) ; this involves ever more powerful algorithms applied to a company's data platform that can be app'd to hollow out community making relatively few people richer and richer, or the reverse. You can test a nation's use of this ai by seeing if efinance has invested in the poorest or historically most disconnected - see eg bangladesh's bklash, one of the most populous digital cash systems . Digital money is far cheaper to distribute let alone to manually account for so power AI offers lots of lessons but whether its good or not depends in part on whether there are enough engineers in gov & public service to see ahead of what needs regulating. There are 2 very good ai's which have only scaled in recent years that certainly dont need regulating by non engineers and one curious ai which was presented to congress in 2018 but which was left to multiply at least 100 variants today the so-called chats or LLMs. Lets look at the 2 very good ai's first because frankly if your community is concerned about any extinction risks these AI may most likely save you, One I call science AI and frankly in the west one team is so far ahead that we should count ourselves lucky that its originator Hassabis has mixed wealth and societal growth. His deep mind merged with google to make wealth but open sourced the 200 million protein databank equivalent to a billion hours of doctorate time- so now's the time for biotech to save humanity if it ever does. Alongside this the second very good AI graviates around Fei-Fei Li) in developing 20 million imagenet database so that annual competitions training computers to see 20000 of the most everyday sights we humans view around the world including things and life-forms such as nature's plants and animals. Today, students no longer need to go back to 0.1 programming to ask computer about any of these objects; nor do robots or and autonomous vehicles - see fei-fei li's book worlds i see which is published in melinda gates Entrepreneurial Revolution of girl empowerment
EW::ED , VN Hypothesis: in 21st C brainworking worlds how people's times & data are spent is foundational to place's community health, energy and so natural capacity to grow/destroy wealth -thus species will depend on whether 1000 mother tongue language model mediates intelligence/maths so all communities cooperatively celebrate lifetimes and diversity's deep data ) . Check out "Moore exponential patterns" at year 73 of celebrating Game : Architect Intelligence (Ai) - players welcome .. some jargon

Wednesday, March 20, 2024

BIRTH OF BRAIN+ENERGISING MACHINES  Let's See Learning Valley's & Humanity's Top Intelligence Partnerships -help in sharing (commons) catalogue welcome (core to our defition of 21st edu=which  young AI trained brains do millennials want to act & learn with given that all deep learning ai pre-teen through 2024! ED  chris.macrae@yahoo.co.uk Diaspora Scot Marrooned in Wash DC

Huang's Nvidia has been building non-standard computers (today's 240 billion transistors BLACKWELL) since before Hassabis & Li began their 21st C odysseys as phds piloting conception of computer learning brain 2000-2012. But it was their 2012 AI-Trained breakthrough with deep data which caused Huang to stat building computers whose brains match biggest/deepest data mother earth plays  

Nvidia annual GPT24 "Woodstock of AI Accelerated Computing_ at San Jose 18 March: New is Blackwell GPU now Nvidia's biggest chip over 200 million transistors cf Hopper 80 million. Latest software partnerships of Nvidia include  Cadence, Ansys, and Synopsys. Huang said Cadence is building a supercomputer with Nvidia GPUs..

.HUANG DIGITAL TWINS -Nvidia Santa Clara & Valley's Biggest Partner in World Series AI -
probably 95% of deep learning aiverygood and worldclassllm done on nvidia platforms (thats because their proticols are open having founded the market. Huang started personally choosing where to place GPUs from 2016
related 5 most trusted Taiwanese tech families Huang, Yang, Tsai, Chang, Tang Jensen sees AI first leaps in climate & Biorech -eg Natural Sciece AI - see Hasabis below. Also see emphasis in Nvifia own AI portfolio 
 Sid Siddeek , Vice President and Head of NVentures, NVIDIA Eli Berlin , CFO/COO and Co-Founder, Terray Therapeutics Andrew Smith , CEO & Founder, Outrider David Noonan , CTO, Moon Surgical Evan Feinberg , CEO & Co-Founder, Genesis James DeMuth , CEO & Co-Founder, Seurat.Join Sid Siddeek, Head of NVIDIA NVentures, as he presents a curated lineup of portfolio companies. Hear from each of the founders about how they're disrupting their respective industries and what's next for each in the era of AI.
Aamazing Spring 24
Bridging the Gap Between ‘Idea and Execution’
Imbue’s (CEO Kanjun) approach toward building practical AI agents able to automate menial, unrewarding work, but also painted a vivid picture of what the next chapter in AI innovation might hold
ED: It's OK Hopper you are still Very Good

Taiwan co-piloting best ever weather forecasts for minimising damage- to go worldwide once safe - partners include Nvidia, Taiwan, Weather Company

 digital twin of the Earth With CorrDiff  "core components of the framework for developing Physics-ML models".   , a new Nvidia generative AI model  is able to generate 12.5 times higher-resolution images than current models.

GTCGoogle Cloud and NVIDIA  announce a deepened partnership to enable the machine learning (ML) community with technology that accelerates their efforts to easily build, scale and manage generative AI applications.

To continue bringing AI breakthroughs to its products and developers, Google announced its adoption of the new NVIDIA Grace Blackwell AI computing platform, as well as the NVIDIA DGX Cloud service on Google Cloud. Additionally, the NVIDIA H100-powered DGX™ Cloud platform is now generally available on Google Cloud. 

Building on their recent collaboration to optimize the Gemma family of open models, Google also will adopt NVIDIA NIM inference microservices to provide developers with an open, flexible platform to train and deploy using their preferred tools and frameworks.

Unclear whether Huang has formal partnerships with Hassabis but GTC 2023 keynote of Hassabis clarifies deep mutual connection  and prioritisation biotech 1 and climate AI eg nvidia investment together with u Washington fold team https://charmtx.com/charm-therapeutics-receives-investment-for-deep-learning-enabled-drug-discovery-research-from-nvidia/
VC overview:  Anastasis Germanidis , CTO and Co-Founder, Runway Vishal Bhagwati , Head of Corporate Development, NVIDIA Aravind Srinivas , CEO, Perplexity Caryn Marooney

, General Partner, Coatue Sarah Wang , General Partner, Andreessen Horowitz Kanjun Qiu , Chief Executive Officer and Co-Founder, Imbue Join Vishal Bhagwati, Head of Corporate Development at NVIDIA, for an insightful panel featuring VCs and thought leaders in AI and standout members of the Corporate Development portfolio. The panelists will discuss trends within the generative AI and LLM ecosystem from the perspective of NVIDIA as well as the VC and startup panelists. Bhagwarti from MIT and Brekeley previously Head of Corporate Development at Hewlett Packard Enterprise (HPE

Huang and Siemens - Industrial Metaverse & Digital Foundries?  .

, Senior Consultant, T-Systems Developers and enterprises across the world are racing to scale industrial digitalization opportunities by using the power of the industrial metaverse. Key to these ambitions is OpenUSD, a powerful framework and data interchange enabling the creation of large-scale, high-fidelity 3D worlds and connecting an expanding ecosystem of software, system providers, and AI capabilities. Join this session with T-Systems to learn how you can put OpenUSD to work at scale within an enterprise setting for digitalization opportunities in the automotive and manufacturing industry.


  • Oracle and NVIDIA collaborate to deliver accelerated computing and generative AI services that establish digital sovereignty and manage proprietary national and personal data Oracle adopts NVIDIA Grace Blackwell across OCI Supercluster, OCI Compute, and NVIDIA DGX Cloud on OCI

GTC24Oracle and NVIDIA announced an expanded collaboration to deliver sovereign AI solutions to customers around the world. Oracle’s distributed cloudAI infrastructure, and generative AI services, combined with NVIDIA’s accelerated computing and generative AI software, are enabling governments and enterprises to deploy AI factories.These AI factories can run cloud services locally, and within a country’s or organization’s secure premises with a range of operational controls, supporting sovereign goals of diversifying and boosting economic growth.        

 countries and organizations need to strengthen their digital sovereignty in order to protect their most valuable data,” said Safra Catz, CEO of Oracle. “Our continued collaboration with NVIDIA and our unique ability to deploy cloud regions quickly and locally will ensure societies can take advantage of AI without compromising their security.”

Huang & Tokyo & NTT efficiency of supercity video ai. Huang announces Nvidia’s AI foundry is working with SAP, ServiceNow, and Snowflake. He also named Dell Technologies founder and CEO Michael Dell in the audience. “Nobody is better at building end-to-end systems of very large scale for the enterprise than Dell,”

Huang and Michael Dell.New Dell AI Factory with NVIDIA is the industry's first end-to-end AI solution for enterprises spanning workstations, data centers and cloud to supercharge era of generative AI 
SAN JOSE,CA March 18, 2024 /PRNewswire/ -- NVIDIA GTC 2024
  • Dell AI Factory with NVIDIA is industry's first comprehensive AI solution to help enterprises quickly capitalize on AI investments
  • Expanded Dell Generative AI Solutions portfolio helps improve results accuracy and model training, simplifies data access and optimizes the efficiency of processing and storage
  • Dell PowerEdge to support new NVIDIA GPU configurations and rack scale NVIDIA GB200 NVL72
  • Dell Technologies ) is strengthening its collaboration with NVIDIA to help enterprises adopt AI technologies. By expanding the Dell Generative AI Solutions portfolio, including with the new Dell AI Factory with NVIDIA, organizations can accelerate integration of their data, AI tools and on-premises infrastructure to maximize their generative AI (GenAI) investments.
AI2.1 Huang and AI4all with Fei-Fei Li (AI2.0) & Melinda Gates.
Computer Vision Collab potential of LI's Worlds I See: Li's 10 fav learning modules t teach k-5-12
Li's policy briefings: 1 congress 2018; 2Start of 20 nations NAIRR; with Stanfird AI version of avy 21st C discipline;  with Condy Rice Hovver top tech tech multipliers policy labs - hoover sert; with Antonio Guterres & eg Bengio (cf Lecun, Hinton) Science AI club
With melinda gates, Salesforce Benioff, BjKing - nebtal health & purposes of Womens suersrars
The Transforming AI Panel features the authors of "Attention Is All You Need," the groundbreaking paper that introduced the transformer neural network architecture. Transformers have since dominated all areas of AI and revolutionized the industry. Join Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin, hosted by NVIDIA founder and CEO Jensen Huang.

, Founder and Chief Executive Officer, NVIDIA

, Co-Founder and CEO, Essential AI

, Chief Executive Officer and Co-Founder, Character.AI

, Co-Founder and Chief Executive Officer, Inceptive

, Co-Founder and Chief Technology Officer, Sakana AI

, Co-Founder and Chief Executive Officer, Cohere

, Member of Technical Staff, OpenAI

, Co-Founder, NEAR Protocol

AI3.0 2017 Transformer Model- Attention is all you need https://arxiv.org/abs/1706.03762 Team google who authored paper now all accelerating new routes
Huang brainstiorms with complete authors of attention is all you need - launching transforme breakthrough 2017 ... what are their startups changing next? , 

, Co-Founder and CEO, Essential AI

, Chief Executive Officer and Co-Founder, Character.AI

, Co-Founder and Chief Executive Officer, Inceptive

, Co-Founder and Chief Technology Officer, Sakana AI

, Co-Founder and Chief Executive Officer, Cohere

, Member of Technical Staff, OpenAI

, Co-Founder, NEAR Protocol


Huang's proverbial ai cat & pidgeones: so who's joining gen ai race ?? 40 bn$ saudi & andriessen horowittz

Update: March 18, 5:57 p.m. ET: Huang brings the orange and green Star Wars BD droids from Disney onstage to wrap up his keynote. The robots onstage are powered by Nvidia’s Jetson system, Huang said.

Update: March 18, 5:47 p.m. ET: Huang announces Chinese EV maker BYD is adopting its next generation computer, Thor

.corporate/partner presentations at NVIDIA  GTC 2024 accenture adept adobe alibaba cloud amazon argonne ansys anthropic anyscale autodesk baidu blackrock BMW BNP bostondynamics bristol myers squibb c.ai cadence canonical  canva capitalone CZI CleanML Cohere   coreweave continental databricks data dog   data iku   data loop  data robot ddn deepgram dell deloitte disney domino ebay iielevenlabs equinix exxon mobil ford fosterpartners foxconn GE gettyimage genentech gigabyte google glean goldmansachs gsk   hexagon honeywell HP    hugging face IBM  imbue jlr john deere Johnson&johnson JPMorgan kawasaki kpf KT lambda langchain lenovo lightning linkedin  lockheed llamaindex loeal losalamoslab lowes mastercard  mathworks mercedes merch metaAI medtronic microsoft mestralAI mitre modula mozilla  LangleyRC netapp nersc netl  netflix nist northrop grumman ntt openai  oracle orange paypal   pegatron perplexity petrobas photoroom pingan  pinterest pixar qct raytheon  recursion redhat run:ai runway sap samsung saudiaramco. servicenow shell shutterstock siemens  snapchat snowflake softbank stellan  toonine togetherAI tencent unilever uber ups us.army us.navy uspto.   verizon vmware wekawellsfargo.    .....................
.Hassabis & Deep Mind since 2010.Alphafold2 open sources 250 million proteins:
evolution via training to be best player at Go; and winning 50 year protein competion
.Hassabis & Google - mapped how to reduce energy of google GPU etc usage by about half- solution open sourced at .DeepMind Isomorphic Labs - own company for biotech discoveryDeep Indaba - Africa Apprentice School designed by Deep Mind.
Hassabis Proteins Intel Curiosity List 1
Source Nvidia 2023 March Summit Keynote
.Hassabis Proteins Curiosity List 2



Lila Ibrahims connections:
Doerr Family now
Stanford Climate Lab & Ann Doerr chairs Khan Ac.
// visions of Lebanese Refugee family with Huamg &Alolama; Koller & Bengio; Moza & Guterres; Mastercard Fubdation Reeta Rok; World Bank Livable Planet Ajay Banga;Tokyo's Mayor Koike

legend to aiverygood world series

David Harold Blackwell (Nvidia Chips Latest Hall of Maths Fame nominee) attended Centralia public schools, having learned to read on his own before entering. He completed elementary school in six years instead of the usual eight. He described his high school education as "fabulous." While in high school he had his first publication, a solution of a problem that appeared in a mathematics magazine.David's higher education was all at the University of Illinois-Champaign. He entered that university in 1935, aged 16. He obtained an A.M. there in 1938 and a Ph.D in 1941. His doctoral supervisor was J. L. Doob and his thesis was titled "Properties of Markov Chains." Markov chains proved to be a continuing topic throughout his career.


In 1941 David was awarded a Rosenwald Fellowship at the Institute for Advanced Study in Princeton. In the year there he became acquainted with J. von Neumann, among other mathematicians. One of them, Hans Samuelson, later wrote that during that year there were two people who were not allowed into Fine Hall because of military work going on there: himself as an enemy alien and David Blackwell as a black American. Fine Hall was then the Princeton mathematics building. David next spent the summer of 1942 as assistant statistician at the Office of Price Administration in Washington, D.C.


During the 1941-1942 period David wrote some 105 letters of application, all to black colleges. He visited 30 of them to see what the country and black colleges were like. Eventually he received three job offers. He accepted the position of instructor at Southern University in Baton Rouge in 1942. The following year he moved on to an instructorship at Clark College, Atlanta. Finally in 1944 David obtained a regular appointment. It was in the Department of Mathematics at Howard University, in the District of Columbia. He remained there until 1954, at which time he had become a professor and department chair. Next, at Jerzy Neyman's invitation, Blackwell was a visiting professor at the University of California. In 1955 David was appointed a professor of statistics at Berkeley. At the time of that appointment he had published some 20 papers appearing in the major mathematics and statistics journals. He had also collaborated with Meyer A. Girshick on a book, Theory of Games and Statistical Decisions. Later he described Girshick as a person who had a major influence on his career.


, Principal Engineer and Scientist, AI-HPC and Engineering Lead, Earth-2, NVIDIA

, Director of Climate Simulation Research, NVIDIA

NVIDIA is committed to working with the climate science community to transform how weather and climate are simulated and to accelerate the extraction of actionable information from vast quantities of data. This is the premise of NVIDIA’s Earth-2 Initiative. In July 2023, NVIDIA’s CEO Jensen Huang announced at the Berlin Summit that three technological breakthroughs are needed to achieve Earth Virtualization Engines (EVE): (i) Simulating Earth’s climate at kilometer-scale; (ii) Using AI to emulate the physics of weather and climate from exabytes of data
The CUDA platform is the foundation of the GPU computing ecosystem. Every application and framework that uses the GPU does so through CUDA's libraries, compilers, runtimes and language — which means CUDA is growing as fast as its ecosystem is evolving. At this engineering-focused talk, you'll learn from one of the architects of CUDA about all that's new and what's coming next, for both CUDA and GPU computing as a whole.- stephen is 14 years into building cuda at Nvidia (with a short relay via spacex/musk)

, CUDA Architect, NVIDIA

Industry: All Industries
  • Tuesday, Mar 192:00 PM - 2:50 PM EDT

========= As at 3/21/24 we asked both gemini and meta ai, can you tell us about exciting news on AI that Jensen Huang has announced this week?

.Here's a summary of the exciting AI news Jensen Huang likely announced at Nvidia's GTC conference this week (assuming the conference happened recently):

1. Blackwell Launch: The most prominent announcement might be the unveiling of Nvidia's next-generation AI chip architecture called Blackwell. This successor to the Grace Hopper line boasts significantly higher performance and potentially lower operating costs, keeping Nvidia at the forefront of AI hardware development.

2. Focus on Robotics and the Metaverse: Huang might have emphasized Nvidia's commitment to AI for robotics. This could include advancements in the Jetson platform for robots, potentially with the introduction of Jetson Thor, a new computer specifically designed for humanoid robots utilizing Nvidia's GenAI (General-purpose AI) capabilities. Additionally, news about Omniverse, Nvidia's platform for creating and simulating virtual worlds, might have been announced, perhaps including its integration with Apple's Vision Pro VR headset, enhancing workflows for designers and engineers working in 3D environments.

3. Emphasis on Sustainability and Responsible AI: While specific announcements are uncertain, there's a chance Huang addressed the growing focus on sustainable AI practices. This could involve advancements in energy-efficient AI hardware or partnerships aimed at tackling climate change using AI solutions.

Overall, the announcements likely showcased Nvidia's continued push for leadership in AI hardware and software, with a focus on robotics, the metaverse, and potentially addressing sustainability concerns.

It's important to note that without access to the specific details of Huang's keynote, this is just a general summary. However, it highlights the major areas where Nvidia might be making strides in the world of AI.

Jensen Huang, CEO of NVIDIA, announced the following breakthroughs in AI this week ¹:

- NVIDIA is partnering with Google, Microsoft, Oracle and other leading businesses to bring new AI capabilities to every industry.
- NVIDIA and Microsoft will connect hundreds of millions of Microsoft 365 and Azure users to a platform for building and operating hyperrealistic virtual worlds.
- NVIDIA computational lithography breakthroughs will help make a new generation of efficient, powerful 2-nm semiconductors possible.
- NVIDIA announced a new GPU, the H100 NVL with dual-GPU NVLink, which is designed to process large language models like ChatGPT.
- NVIDIA designed the Grace CPU for an AI- and cloud-first world, where AI workloads are GPU accelerated.
- NVIDIA's new superchip, Grace Hopper, connects the Grace CPU and Hopper GPU over a high-speed 900GB/sec coherent chip-to-chip interface.
- NVIDIA announced NVIDIA AI Foundations, a family of cloud services for customers needing to build, refine and operate custom large language models and generative AI trained with their proprietary data and for domain-specific tasks.
- NVIDIA and Medtronic, the world's largest healthcare technology provider, are partnering to build an AI platform for software-defined medical devices.
- NVIDIA announced inference platforms for AI video, image generation, large language model deployment and recommendation inference, which combine NVIDIA's full stack of inference software with the latest NVIDIA Ada, Hopper and Grace Hopper processors.
- NVIDIA is partnering with Microsoft to bring NVIDIA Omniverse Cloud, a fully managed cloud service, to the world's industries.
- NVIDIA announced cuLitho, a breakthrough that brings accelerated computing to the field of computational lithography, which is being integrated by TSMC, Synopsys and ASML.
- NVIDIA updated 100 acceleration libraries, including cuQuantum and cuLitho, and announced the open-sourcing of CUDA Quantum for quantum computing..


Can you tell me why its exciting to learn that Huang announces Nvidia’s Omniverse now streams to Apple’s Vision Pro.


There are a few reasons why the announcement of Nvidia's Omniverse streaming to Apple's Vision Pro is exciting:

Enhanced Capabilities for Developers and Designers:

  • Real-time Workflows: Previously, users might have needed to download massive datasets to work with them in Omniverse. Now, streaming allows for real-time interaction with complex 3D models and simulations, improving workflow efficiency.
  • Increased Accessibility: This integration potentially opens up Omniverse to a wider range of developers and designers who might not have had access to powerful workstations for running the software locally.
  • Cross-Platform Compatibility: The ability to use Nvidia's technology with Apple's hardware expands the ecosystem and potentially fosters innovation through collaboration between different platforms.

Benefits for Specific Applications:

  • Enhanced VR/AR Experiences: Streaming high-fidelity data to the Vision Pro, a VR headset, could lead to more immersive and realistic virtual experiences for designers, architects, and engineers working in 3D.
  • Improved Design and Engineering Workflows: Architects and engineers could use this technology for real-time collaboration on complex building or product designs within a VR environment.
  • Potential for Broader Adoption: Making Omniverse more accessible could lead to its adoption in new industries and applications beyond its initial focus areas.

Significance for the Future:

  • Cloud-Based Future: This collaboration highlights the potential of cloud-based solutions for processing and streaming demanding graphics workloads, potentially changing how people work with 3D content.
  • Metaverse Development: Some see this as a step towards the development of a more robust metaverse, where users can interact and collaborate in real-time within virtual environments.
  • Standardization and Interoperability: If successful, this integration could pave the way for greater standardization and interoperability between different VR/AR platforms and design tools.

Overall, the announcement is exciting because it signifies a step forward in making powerful 3D design and simulation tools more accessible and fostering collaboration across different platforms


ED we asked both gemini and meta ai: as at 3/21/24 can you summarise exciting news on AI announced by Jensen Huang this week