IN SEARCH OF INTELLIGENCE unites families advancing next generation's life on earth. December 2024, Wash DC, chris.macrae@yahoo.co.uk ; linkedin UNwomens::: 2025Reporter Club Over 60% of people depend on pacific trades. Because of Western era of Empire, Pacific people's growth expoennentials have depended on what von neumann called designing development rpind above zero-sum trading maps through 3 waves of "millions times more tech brainpower : Mooere's engineers of linkining in silicon chip valley 95-65; Satellite Data worlkdwiode 5G to 1G (2015-1990), Partners of Jensen Huang's Deep Data Computing & Learning ets Stanford Engineeriing Quadrangle 2010
That's our open syatem foundations observation. scaling over 75 years since John Von Neumann asked Economist journalists to mediate futures of brainworking through 3 million fold hi-tech waves :Moore's Silicon Valley,*Satellites 1G to 5G Death of Distance mobilising data round earth* Jensens platforms for DEEP LEARNING Data Science aligned to Einstein's 1905 nano-science-Earth revolution. NB Miraculous Transformations In tha last 5 quarters of human endeavor, may we commend projects emerging from 6 summits linkedin by Taiwanese-Americans gravitated by Jensen Huang (Nvidia) and 4 summits living up to King Charles wishes for humanity : Nov 2023 London Turing latest Deep Minds,, May 2024 Korea, Summer 2024 semi-private Japan State Visit to London (Charles 60th Anglo-Japan reunion as 1964 delegate to Tokyo Olympics), December 2024 India's Wadwani AI in DC (with next round of King Charles Series - Macron Paris Feb 2025)
..
Jensen's health AI meta-collab: Hong Kong Digital Twin 2020s supercity health centres :Tokyo Update Maso Son & Japan Royal LLM everywhere; India's sata socereignty od world largest population with Ambani & Modi; NVidia in DC with eg LOgkhttf Martin ; Taiwan RWins galore eg Fioxconnn extension to foundry for autonomous as well as mobile world; San Jose March 2-24 tenth annual upfate of most joyful parternship tech world has ever generated
Over the past year, key international organizations, like the G7, OECD, and Global Partnership on Artificial Intelligence (GPAI), have shaped the global AI governance conversation and focused on foundational principles, critical risks, and responsible AI development. Looking ahead to 2025, how are G7 countries and corporations planning to implement AI governance frameworks and address challenges, such as the growing energy demand for AI technologies?
Join the Wadhwani AI Center for the International AI Policy: Outlook for 2025 conference. This full-day event will be held at CSIS headquarters on December 9, 2024, from 9:00 AM to 6:00 PM ET and will convene leading policymakers, industry experts, and thought leaders to explore the latest international efforts in AI governance.
Featuring keynote speeches from distinguished figures, including Ambassador Shigeo Yamada of Japan to the United States, Ambassador Laurent Bili of France to the United States, and Sara Cohen, Deputy Head of Mission at the Embassy of Canada, this conference will highlight key international perspectives in AI governance.
On the C-SPAN Networks: Helena Fu is a Director for Critical and Emerging Technology in the Department of Energy with one video in the C-SPAN Video Library; the first appearance was a 2024 Forum.
WHY WOULD PUBLIC SERVANTS WANT TO GOVERN INTELLIGENCE WHEN THEY COULD BE INVITING PEOPLES TO PLAY GIANT LEAPS IN PRODUCTIVITY & RENEWABLE GENERATION - JOIN THE AI GAMES : ADVANCE THE HUMAN CONDITION EVERYWHERE
-PREVIOUS REFERENCE 1957 COMOUTER & THE bRAIN - JOHN VON NEUMANN!
Summer may have come to end but in WashingtOn DC AI is heating up. No sooner than NIST 2 day summit on how standards have clarified AI through the first 11 months of the AI Executive order than Nvidia CEO helped clarify AI is future of energy is future of AI in any place that values its peoples. Next week in DC starting 7 Oct Nvidia stages 3 day AI summits and Bloomberg Johns Hopkins 1 day AI Ethics summit.
Jensen Huang
On the C-SPAN Networks: Jensen Huang is a Co-Founder and CEO for the NVIDIA Corporation with one video in the C-SPAN Video Library; the first appearance was a 2024 Speech.
Join conversation with BPC President and CEO Margaret Spellings and NVIDIA Founder and CEO Jensen Huang at the Bipartisan Policy Center on Friday, September 27, 2024, at 10 a.m. ET.
The discussion will focus on how artificial intelligence is impacting energy worldwide and the role of accelerated computing in promoting sustainability and tackling climate change.
NVIDIA is helping to transform the energy sector. As the AI-driven transformation continues, questions are emerging around how the federal government can advance applications that reduce greenhouse gas emissions, as well as how policy can help balance growing electricity use from AI with sustainable solutions
* *.
(video timestamp) 4:43 Spellings: at BPC are proud of the role that we play as a place to bring people together to find common ground and to drive towards Solutions and there's no thing that needs more thinking around tthan Ai and energy and so we're thrilled to welcome Jensen Huang here today
5:01 Jensen Huang- thank you
Margaret
Spellings:Jensen is the founder in of Nvidia a 3 trillion doll company with about 30,000 employeesI'm so impressed with you why don'ty you tell us about how you got started give us your kind of so-called origin story and how it is that you came to be
sitting with me here today
Jensen: my gosh from where from zero!
Spellings: tell us the story from start of Nvidia
Jensen: back in 1993, we were engineers in Silicon Valley designing computers and we observed that there was a better way of Designing computers : the current computer that we use was invented the year after my birth 1964 by IBM it's called the IBM system
360 and it described a central processing unit CPU multitasking separation of operating system separation of hardware and software and that basic Technologiesis used today. thge traditional supercompueter is a lot better, a lot faster but the basic architecture of it is the same it's a general purpose computer that aims to do anything.
So, 30 years ago ins 1993, we observed that that there are problems that are quite specialized where a general purpose approach is not necessarily the best for hatdware or software- consider eg if you want t do physics simulations and data processing and computer graphics image processing simukltaneoulsy - ecah of these problems have algorithms inside that are
very computationally intensive needing their own specialized processor -if we could add a chip to connect these multiple subprocessors
the whole could io a hundreds of times faster= the reason for that is of course each chip can focus on what it does best and we offload and accelerate this thing SO AT NVIDIA we call this ACCELERATED COMPUTING =and over time we accelerate an application 10 20 50 times and as our computera architecture has only added one
more chip we can reduce the amount of Power/energy used by 25 times and the amount of cost by 25 times and so this approach has
led to solving all kinds ofuniquely interesting problems:
...the first application we used it for in commercial use was for video games (and you know for a lot of people
Nvidia is still the video game company as we build more computers for video games than any company in the
world when you have when you play PC games it's probably Nvidia inside when you play the Nintendo it's Nvidia
inside and so so we're well known for that..
when it comes to our industrial applications the first one was molecular Dynamic simulation for virtual screening and seismic processing for energy Discovery and then you know Fluid Dynamics, weather simulation, and then one day (2009 leades in) artificial intelligence found us|
9:07
and so accelerated Computing has emerged to explore extraoedinary future sof computing; it turns out what we may call Sustainable Computing is where you get into the savings of energy
and so the integrated observation that we make : a general purpose approach to solving every problem is energy inefficient:that's a little making a factory for building a car and the assumption that you make is that every single car that you make will be different and so you have a generalist team of people that okay build me a van okay now build me a sports car okay now build me a truck and and so because every single one is intended to be different - compare that yo if you all of a sudden said to yourself for the next 1 million cars they're goi g to be exactly the same; the efficiency by which you could build that 1 million cars compared to the generalist build at one at it's like manufacturing versus crafting
AND the amount of energy you use is going to be substantially lower and so we've come to the conclusion over 32 years that
there are some parts of the job that needs generalized and you need to do it sequentially just step by step, however there are some parts of the job where (say) you're calculating physics while you're just trying to figure out how molecules move around you wjile you're trying to figure out how artificial intelligent neural network is predicting the next token. So, in those type of applications,: and you could have just a mountain of processing at the same time
if we talk about analytical threads in the execution of a program then the traditional CPU can compute one or two threads at one time while Nvidia's accelerated computting can compute tens of thousands of threads at the same time
11.25
Thus for work that you can break up into a whole bunch of little threads we can get it done a lot faster and you know as a result much more energy efficient
SPELLINGS: so let's talk more about Ai and energy I mean there's kind of Hysteria going on right now about oh my God this this industry Innovation is going to swamp our energy demand and we're going to have blackouts and you know this those sorts of things.. obviously energy abundance is a key issue for all of us here in the United States especially I'm from Texas
so we talk about that a lot but can you give us your thinking on AI and energy at Nvidia and more and more broadly how you think about AI and energy
JENSEN so the first thing is to realize that before you can use AI you have to teach an AI; this is no different
than with human intelligence you have to teach the actual intelligence. SO with AI its the teaching process consumes a lot of energy and the reason why it consumes a lot of energy is that the artificial intelligence network through trial and error is trying to figure out how to predict something and it's recognizing patterns and relationship among tons and tons of
information and from all of that data it finds out what's the relationship and the pattern such that it can learn a knowledge out of it (we call it representations); and so you're trying to discover knowledge out of data and
you're just swimming in it, processing it repeatedly looking for that pattern relationships
12:59
eventually you'll learned the knowledge that's embedded inside; you've learned /transformed future patterns of understanding
and/or predictions - so so that that's the AI=data procesing goal = and these data centers could consume today a 100 megawatts and in the future it'll probably be 10 times or 20 times more than that
13:30
BUT it doesn't have to necessarily be built in one place -and we need to anticipate using synthetic data such as when two AI models are going to be talking to each othe rjust like the two of us are right, and just through conversation Q&A we're going to make each other smarter
13:48
and so future AI models are going to rely on other AI models to learn and you could use AI models to curate the data. Thus the future AI will include teaching another AI (24/7)
14:01
and so there's a lot of different ways that that AI will learn the future but nonetheless it's going to take energy to do so the important thing to realize about AI is that it doesn't necessarily care where it learns, it doesn't care where it goes to school and so there are places in a world where we have excess energy; ok it's not necessarily connected to the Grid it's hard to
transport that energy but we can transport the data center too we can build a data center near where
there's excess energy and use the energy there
14.49
The other the big idea about about AI however is the goal of AI is to do things more productively right with a lot less energy and there are a whole bunch of examples of this where we're using AI'
One of my favorite examples (Taiwan is investing deeply in worldwide partners to advanbce this) is using AI to predict weather by training an AI model the physics of weather prediction which connects with atmospheric physics and a long range weather prediction requires you to understand ocean physics land physics Cloud physics .. radiation reflection absorption conduction...thermodynamics, fluid dynamics all of those forms of physics comes together to affect the future climate .15:26 So, we wil teach an AI how to do that through previous observation data and we're starting to make great progress there
that AI model can predict whether and predict climate thousands of times more energy efficiently and so the thing to remember you teach the AI model a few times but you use it continuously everywhere around the world and so the benefits of
using AI to predict weather and instead of using old supercomputers to predict weather as we do now right, we can save a
ton of energy. So that's one simple example.
But the examples just go on and on, right now AI can be part of the
solution as we think about climate not so much part of the problem
And that's just one example
SO using artificial intelligence to solve (Sustainability-critical) problems will consume less energy overall...
along with weather forecasting, consider use of artificial intelligence to design the smart grid ; you know today our power grid is not at all smart but we can make it smart and so we work with a company called Utilidata and PG&E
https://www.nvidia.com/en-us/industries/energy/power-utilities/
.Q what's diferent about Nvidia's accelerated comouting? Huang: our computers can analyse tens of thousands of threads at same time making them thosuands of time more efficient for Deep DATA/Learning cases than clasical computer that only does a few threads so Our Intelligence Partnerships can be more efficient at eg weather forecasting or Artificial Intel or both, and we can aim to share these transfromativve models/standards with thousands of times less energy than old computers
Q if you running the department of energy and had checkbook you know how do you see those Investments being deployed um uh the the thing I recommend most for for um every employee Nvidia everyleader that I meet is engage artificial intelligence try to have a tactical feel>ne of the things that that I would really love to see the United States do is for the governmen to become a practitioner of AI don't just be a governor of AI
Q what's impact of your AI of workforce and jobs? A:in the US but but in the world the first thing we need to do is demystify this technology for people and the reason for that is because it's useful to them it canEmpower them but not not if they don't understand it and as it turns out it's< actually relatively easy to understand very few people in the world know how to program but everyone knows that knows how to ask someone else to do something for them and it's as simple as that walking up the computer and tell it you know what you want and for the first time it might even give you a reasonable answer back
a question want to ask you about obviously you're wildly successful about. to be admitted to the nationaly and so on and and how do you think about your you know responsibilityprimary); margin-left: var(--ytd-transcript-segment-text-margin-left); overflow-wrap: break-word; width: 295.753px;" tabindex="-1">remit now how do you think about that well the most the the first thing that that um uh be a good father that that's number one be a good father and husband" probably the single best thing that that um any of our employees any any oneof us has ever done we we've built what what is what is recognized<>one of the most consequential technology companies in history yeah technology is used um in groundbreaking work in so many different fields of Science.
16:45 So, we create an AI computer and it is integrated into the smart grid ; the goal is to integrate sustainable energy, forexample it could recognize where there's a weakness in a grid and figure out where the various distributed energy sources are to keep the grid going.It can do a better job predicting the power surges that's about to happen so you can redirect energy accordingly. It can help us not over provision in the grid. You know today the grid has the ability to handle a lot more power delivery because of the promise that we made the society. We may over provision by a factor of two just mecause there are a few days of the year that we need to serve that peak deamnd for heat or cooling.We could redirect the energy in a smarter way - there's lots of examples like that.
Spellings: so here we are in Washington and obviously we're alll about federal policy. The federal government has been an important partnerin innovating some of the things that you're talking about how do you see the fuyure of Department ofEenergy if you had checkbook
Jensen: The thing I recommend most is similar to what I ask of every employee at Nvidia and every Company CEO that I meet. Engage artificial intelligence try to have a tactical feel for it.It's not really that mystical as you and I see sitting here having conversations with each other. It turns out there's there are
1several things that we should observe about artificial intelligence today. We are facing the most advanced Computing technology ever created. We have made the computer easier to use than ever to the point where almost anybody can talk to the computer, prompt it for something, ask it to do something for you including write software for you and it will write software for you; and it could make drawings for you, create schematics for you, it could make charts and graphs, it could read something for you, translate something for you, summarize something for you, solve problems for you and so this incredible thing this computer is now democratized for the very first time in history this incredible system of ftechnology is becoming available to everybody to use.
So, the first thing to do is to try to understand how you could take advantage of this technology yourself. Now, of course, once you go down that Journey you'll discover all the same things that scientists and engineers and all of us are starting to discover that not only is it more energy efficientbut we can use our energy better ; we could be more energy sustainable , we could create new materials so that we could create sustainable energy more effectively . Some of the important work that we're doing is in carbon capture: just trying to figure out in a reservoir how much pressure can we pump into
21:23
carbon into this Reservoir and how much this Reservoir has. We can select locations of the best injection Wells for carbon capture and this simulation takes supercomputers just an enormous amount of calculation but we've taught in AI how to select these sites to use much less energy and so there's a lot of different ways that
2 we can use artificial intelligence to help. Being inspired by these ideas can help all of us.Of course some of the things that that I would recommend is I would really love to see the United States do is for the government to to become a practitioner of AI don't just be a governor of AI. As a practitioner of AI :, at the Department of Energy every single Department could be a practitioner andthe scientists would be more than happy to jump on it and create new AI algorithms you know to advance our country
Spellings: fabulous Jensen you were a startup innovator w many moons ago but you have an affinity for startups- can you talk to us about your your Inception partnership Network? and how you see that ecosystem of of innovators/startups?.
Jensen: well, we know a lot about this
2 technology and we have a lot of scale and resources and we have we have abilities and so so when we see companies around the world that are trying to apply AI for some particular domain - it could be a domain like for example Utilidata I just love that company// They' ae a company that wanted to build a smart grid but they didn't understand artificial intelligence that well and so working together we became an expert in artificial intelligence and the application for smart grids
Another example : we work with a company that has satellites out in space and they take images of the earth at a spectrum that is beyond human visionbut we can teach an artificial intelligence how to see something from it. This has started to be usewd to discover gas leaks and Reservoir leaks and such.
So Nvidia can help companies with unique imaginations with our AI capabilities and so we're working with thousands of startups.
24.29 Spellings: and do they find you or do you find
24:29
you find them?
Jensen: Both. I do a lot of reading about companies thatare doing some really interesting things. For example, it could be about a compoany that is working out how to keep Birds safe in the middle of a wind farm. All kinds of great ideas
Spellings: you won't be surprised to that I'm going to ask you about Workforce -there's a lot of implications to the good and and a lot of fear around what is the meaning of AI for our
25:00
American Workforce or Workforce globally. How do you think about that as your own human capital
25:06
asset as a company and how you develop and grow but also you know the broader implications uh for the workforce?
Jensen: First in the US but also in the world, the first thing we need to do is demystify this technology for people and the reason for that is because it's useful to them it can Empower them but not not if they don't understand it. And as it turns out it's actually relatively easy to understand. Very few people in the world know how to program a computer but everyone knows that knows how to ask someone else to do something for them and it's as simple as that/ It's becoming as simple as walking up the computer and tell it you know what you want and for the first time it might even give you a reasonable answer back.lAnd you don't even need complete sentences you could be grammatically incorrect you justget started with a problem definition and if it doesn't understand what you mean it'll actually ask you back what you mean - and just go back and forth until it figures out what you want and it does it for you. We need to demystify artificial intelligence so we can empower the population to take advantage of this amazing technology that's only been available for a few percentage of the world in the past. And so we could close the technology divide, we could enable everybody to take advantage of it and so the first thing that we've done is : we teach a class called Deep learning Institute and we go around the world and we're doing we're doing a fair;y large campaign in California in community colleges, in high schools and such. And anybody who would like to learn tp teach them about about the capabilities of
26:47
artificial intelligence. We should do that all over the countr,y we should be teaching everybody - exposing people to
26:54
this technology. And I think it's easy to use it's fun to use it's inspiring to use you can ask it to help you draw something, give you a recipe, you know help you write a business plan, you know all kinds of things .
Lessons| obviously there's no substitute for the ability to to read and compute and I know you all have been involved in in education programs at your Alma Maters and so forth but how do you think about your own human capital? and what do you look for in your people and your leaders. given all the promise that AI has for the workforce you know what are you looking for as you look for and recruit leaders and people to join you in
27:32
building Nvidia?
TBC
All the same things I look for in the past um nothing's going to change the one thing that's going to
27:38
change is is the amount of software programming that we do the actual programming that we do will reduce or
27:45
another way of saying it is the way we program computers will change because you're just going to ask a computer to
27:50
do it exactly exactly we're going to describe very clearly what we want the computer to help us do right and the
27:56
computer will do it for us so the way that we would design chips in the future would be describing probably the
28:02
specifications of the chip which is telling somebody what you want is is
28:08
often times where the genius is right right yeah where the genius is yeah doing it doing doing the actual skill of
28:15
course there's great craft and and um great dedication and um U but you know
28:21
to to to be able to explain a future that you would like to create um and have have uh AIS that that um uh help
28:28
you go do that is is pretty terrific and so my prediction is is that the first
28:34
thing the first thing companies like ourselves would do is use artificial intelligence to improve our productivity
28:40
that's what we've done we've got AIS all over our companies designing our chips writing our software helping us debug
28:47
things help us do verification we're starting to work on using it for marketing and customer support and
28:53
things like that and so so uh number one help us be more productive when a company becomes more productive they
29:00
make more money when they make more money they hire more people and the reason for that is because we have more
29:06
ideas we like to go pursue right right and so I would love for United States to be more productive because we'll have
29:12
more money and then because we have abundance of ideas we'll be more prosperous so so I I think the the um
29:19
the idea the idea that that it's it's human versus AI is not quite right is
29:25
humans using Ai and with respect to anybody who who's concerned about an AI
29:30
taking their job you should probably worry about someone who uses AI taking your job yeah and so so that that
29:37
reminds you to to get going and to go learn this uh learn this new tool yeah
29:43
and to make this new tool you know your advantage and surely as a company we're going to do that yeah and as a country
29:49
we should do that and and obviously what are those skills that are necessary to be able to be precise and you know at at
29:57
the telling what to to do that's part of the the AI equation that's right wow uh
30:02
okay National Security MH obviously you know a huge you know Nexus between our
30:09
nation security and and these issues talk about that how you see the world and and the National Security
30:15
implications for this technology taking a step back
30:21
um countries are starting to awaken uh to the importance of artificial
30:27
intelligence to their country mhm on first principles it is apparent and the reason for that is
30:34
simple no country in the world would say uh we should Outsource our intelligence
30:40
to anybody else no country in the world should say would say we have an abundance of intelligence this is good
30:47
enough let's put a lid on this one let's wean oursel off of
30:53
[Laughter] this and so so I think I think it's it's
30:58
now very clear that the that artificial intelligence is about the The Accelerated production of intelligence
31:06
hey please remind me to talk about um artificial intelligence as an industry
31:11
and the production of it I just wanted because for energy is so important um and uh uh countries are also starting to
31:19
realize that the land they're on is part of their natural resource and Sovereign resource but their language culture
31:27
people their way of thinking right is part of
31:32
their natural resource and it's that is codified in data and so to to allow
31:40
other countries to come in and scrape your data Harvest your data Harvest your
31:45
natural resource exactly refine it and then import it back to you as artificial
31:50
intelligence is unacceptable and happening yeah that's right and so so
31:56
countries are starting to realize that they have to take control of their own artificial intelligence production and
32:02
this is where the word sovereign AI if you will is starting to float around uh countries in the in the west countries
32:09
in the East are are quite concerned and quite motivated to secure their AI
32:16
infrastructure just like they secure their their telecommunications their power grids
32:22
they like nuclear assets nuclear assets they want to really secure their artificial intelligence infrastructure
32:28
and so that's that's really one of the the major Dynamics that's happening around the world that that they realize
32:35
now the incredible potential of this technology to accelerate their uh
32:41
climbing if you will you know in the world's um various uh social ladders and
32:49
so this is a a great tool for them to propel their National prosperity and and
32:55
I so I think on on first principles people people Now understand uh the incredible importance of artificial
33:01
intelligence for their National Security National prosperity and National
33:07
development yeah and so so I think I think every country is starting to to realize that now from our United States
33:13
uh we need to realize that this technology is is uh indigenous to us it was created here congratulations we have
33:20
thank you and and we're proud to be an American company and uh if not for the United States and and all of the
33:25
resources that was that was made available uh in video wouldn't be Pro wouldn't be possible and so I I think the the the um
33:34
uh uh the the country's desire uh to uh
33:42
number one protect this technology uh for our own benefit uh is fantastic and
33:48
we want to use this technology of course to accelerate and Propel the United States further the important thing is to
33:54
realize also that to balance that with the idea that that American Technology around the
34:00
world sets American Standards all around the world right exactly we would like we
34:06
it's fantastic that the world speaks English yeah it's fantastic that um that
34:11
the world is is powered by American Technology and we would like of course
34:17
uh Nvidia technology to also be used all over the world to set the pace for the
34:22
world um to make sure that the American Technologies are used to build other nations and other Industries around the
34:29
world and so we want to find the balance between National Security and of course
34:34
um prosperity for American companies around the world and so that balance is hard to strike and um but whatever
34:40
whatever the administration does of course is something will support yeah I want to ask you about regulation and and
34:47
the role in that but you were going to say for a second about uh AI production this is the big observation from an
34:54
energy perspective this is really important to know um for the very first time time a
35:00
computer is a tool but it's also a factory it used to be a data center
35:06
where data is stored but in the future these computers that we build um
35:13
will be used in a way that's very different than the past these computers for example I have I have a phone in my
35:19
pocket right now it's a computer and it's a tool of mine just like a Quin art just a lawn mow just like anything any
35:27
other tool Mone a tool when you're using it you're using it when you're not using it sitting idle my phone's sitting idle
35:32
right now however in the world of artificial intelligence there will be systems there will be AIS that are doing
35:39
things for us all the time we ask it to go do something and it does it all the time just like we ask one of our
35:45
employees to do something it does it all the time and and um we like it to be uh
35:51
human in the loop but as autonomous as as autonomous as possible as govern as necessary and so
35:59
these computers are off working on things designing chips writing software optimizing things going through plans
36:07
evaluating all the various plans that we have and trying to figure out which one is the best to come back and recommend
36:13
it to us and so the exploration of the design space exploration of the the the
36:19
optimization Space is really really large and we want these AIS to go explore them to go look for new
36:25
scientific discovery for example and so so it's off in in these machines and it's running all the time in a lot of
36:32
ways these computers in the future will be in AI Factory right and there's a new
36:38
Factory that is being created right now there's a new industry that's that's being created right now it's called AI
36:44
right and remember a new industry requires energy and this is a new
36:50
addition to the past and so while accelerated Computing what Nvidia does um allows us to save a lot of energy in
36:59
the way that we use the compute so every every every software that can be accelerated should be accelerated um we
37:07
should modernize old data centers with the new type of computing models that
37:12
are accelerated and we'll save a lot of energy in doing that and that's a classical data center that what that's
37:17
what we used to build but there's a new thing that's called AI factories and that's going to consume energy but what
37:24
of course comes out of it is artificial intelligence that will help us to save energy somewhere else right and so this
37:29
is a this is a if you will an industrial revolution a new assembly line a new you
37:35
used your car analogy a bit ago um regulations and guard rails and
37:40
policymaking OB you know there's a lot of energy on the hill and and rightly about how do we think about you know
37:47
preserving Innovation while protecting National Security our children you know
37:52
fill in the blank and our role in the world Visa the Europeans or other
37:58
me how do you think about those issues as you know members of the Congress down
38:03
the street here start to put pen to paper on the way forward for your industry well first to help them
38:09
understand the technology all of the potential uh incredible good that it can do uh around the world uh recognizing
38:17
the the uh the threats and the danger of this this technology of course
38:23
um the technology is fundamentally intelligence and intelligence could be
38:28
used in a lot of different ways for for great and for Peril and so and so we we
38:33
uh one help them understand the state of the technology where are we today um uh
38:39
where will it be in some reasonable time and how to how to think about the technology more practically instead of
38:46
theoretically scence science fiction wise right and so um without without us
38:52
demystifying it it's hard for people to understand this technology and so one help people understand the technology um
38:58
help people understand the the uh the very very good use that's already coming out of it um and in various fields of
39:05
science whether it's in health care or um climate science or education education or everybody should have their
39:12
own tutor um and so I have my own tutor today and my tutor is perplexity I I use
39:18
it almost every day what what is this tutor perplexity perplexity perplexity it's a great it's a great great uh great
39:24
resource um it's an AI and uh calls upon other AIS and and um uh you could ask it
39:32
all kinds of questions and it's really really really helpful anyways it's taught me a lot about about
39:38
um about digital biology and so it's really great so you're obviously a half
39:44
so one one uh make sure that that that we educate them about about um uh the
39:50
opportunities around the world so that they understand that exporting American
39:55
Technology is winning abroad and we want to win here we want to win abroad we
40:01
want to win everywhere and and um all of the policy makers I've met wants America
40:06
to win and that's great that's great but there is the you know the other side of the coin we hosted uh Brad Smith from
40:13
Microsoft I don't know a few weeks ago and they released a report on on AI
40:18
generated content the implications for kids and others and so forth so you know how what do you what about that you know
40:24
keeps you up at night piece of it the darker side of AI how do you think of that well it's um I it's going to take
40:31
AI to catch darker side of AI MH and and the reason for that is is pretty clear
40:37
you know they AI is going to be producing uh um fake fake uh uh data and
40:44
and um false information at very high speeds and so take ve somebody with very
40:50
high speeds to detect that and um to shut it down higher speeds higher speeds
40:56
that's right exactly and so so so I think this is no this is very similar to Cy cyber
41:02
security it it you're almost every single company in every single country is being uh haed hacked and you know
41:10
attacked at almost all times right and so it's going to take even better cyber security to defend ourselves and so I
41:17
think the um uh we just have to make sure that we stay ahead and AI will help us do that it's going to take AI to help
41:24
us stay ahead yeah yeah so before we go a question want to ask you about obviously you're wildly successful about
41:30
to be admitted to the nationaly and so on and and how do you think about your you know responsibility
41:37
as a citizen as a philanthropist supporting education I mean just you know kind of own that piece of your
41:43
remit now how do you think about that well the most the the first thing that
41:49
that um uh be a good father that that's number one be a good father and husband
41:55
uh number two I hoping you were going to get get that in there that husband pays cuzz there she is right there
42:01
yeah brought my wife yeah um uh the first thing uh building Nvidia
42:09
is probably the single best thing that that um any of our employees any any one
42:14
of us has ever done we we've built what what is what is recognized
42:20
one of the most consequential technology companies in history yeah uh and uh our
42:26
technology is used um in groundbreaking work in so many different fields of Science and
42:32
industries uh uh We've um uh of course
42:38
uh uh invented invented Technologies over the course of three decades yeah
42:46
that that um uh nobody nobody could
42:51
imagine right and and um so I'm proud of that that's probably our most important
42:57
work and applying this technology uh and advancing it further for some of the
43:04
most challenging and pressing issues of our time whether it's uh digital biology
43:10
or Health Care is is some of our some of our um uh best futures um I can't
43:19
imagine you what we're going to be like in 10 years frankly yeah and when we apply artificial intelligence to um uh
43:28
the field of biology and to for us to not to move Beyond calling it life
43:34
sciences uh to life engineering just like we do and for us to be able to
43:41
understand uh biology the way we understand U many other fields of science would be incredible and so so I
43:47
think that that's probably our our single greatest potential of helping and
43:53
um and working on it yeah well congratulations you obviously have built something
43:58
incredibly powerful and fascinating and you're a learner every day I can tell
44:04
already so all right we're going to have questions from the audience and I think there's some out uh in The Ether we have
44:11
several hundred people online that are that are watching as well so hands popping up everywhere if we could get
44:18
some microphones around yeah hi my name is Chris Barnard first of all thank you for everything you do as an investor
44:25
from 2017 a personal thank you as well the stocks been doing very well um obviously we saw some very
44:32
exciting news last week with Microsoft helping constellation reopen Three Mile Island and the power of nuclear to
44:38
potentially help this AI future I wonder if you have any thoughts on how nuclear can be an integral part of this thank
44:44
you nuclear nuclear is going to be uh a vital integral part of this no one no
44:50
one energy source will be sufficient for the world yeah and so we'll have to find
44:56
that balance balance it's it's not one particular way versus others but but
45:02
there are a lot of good ways and and but there's no better way than to not waste
45:08
energy and and there there are a couple of ways that that we can contribute to doing that accelerated Computing is one
45:15
way and uh the reason why we've become so successful is because the
45:21
computational energy necessary to get the work done using the Nvidia approach
45:27
is orders of magnitude less than using general purpose Computing and um not
45:32
wasting energy not wasting money not wasting time is probably the single best thing we can do um uh there's a whole
45:39
bunch of other ways that we could not waste energy um I would really love to see our power grid all be smart you know
45:46
to today our nation's power grid was built a long time ago because we're one of the earliest countries to become
45:53
prosperous and and that power grid could uh benefit from uh the insertion of
45:59
artificial intelligence and smart technology into it and that smart grid uh that grid when becomes smart uh will
46:07
help us uh properly provision technology to the right places and you know connect the right uh sources and syns like we
46:15
connect the right drivers and writers you know and so in order for Uber to work you need a smart grid and and we
46:22
could we can go create that smart grid exactly others
46:28
we're for the col McCormack from Georgetown University in carbon direct one of the huge challenges with renewable energy today is the
46:34
interconnection queue we have thousands of gws of solar wind and batteries waiting to connect sometimes for years
46:42
for studies to be completed what can tech companies like Nvidia do to speed up the interconnection queue and get
46:48
that renewable energy generating faster than it is today yeah um you you know the reason
46:54
why fossil fuel is so effective is because uh time mother nature compressed
47:01
it into a transportable for form for us and we can take it anywhere and refine
47:06
it from anywhere and um uh the challenge of course with electric energy is the
47:11
battery costs a lot of money and uh and solar and sun is only out for about half
47:17
of the day and and so there there are a variety of of challenges of sustainable energy in that way one way that I
47:24
described earlier is instead of transporting the energy to where we need it let's transport the data center to
47:33
where there's energy source and we put that data we can build a data center anywhere the computer the AI doesn't
47:40
care where it goes to school and and you know although we
47:45
would like the AI to be trained as continuously as possible taking a nap
47:51
for a couple of hours while the sun is down it's it's okay you know we can live with that and and so so so long as the
47:57
energy is is um abundant and and there's going to be excess anyways um I I think
48:04
that is a great way to do it and we can then take that AI compress it that energy compress it into this little tiny
48:11
thing called large language model and we can transport that anywhere we like to use it so others up here let's see there
48:18
we go you're next hi Katie with Constellation Energy we actually made that announcement uh last week about
48:24
bringing the nuclear plant back to congratulations thank you thank you it's very exciting um but kind of pulling off
48:30
of what you were just saying um we have heard uh we have lots more to offer
48:35
right we have lots more nuclear energy in this country that can be used to serve data centers AI factories um but
48:42
we've heard about some proposals that would require what they say is additionality for AI and this idea that
48:49
if you're going to build an AI Factory you have to build commensurate energy to go along with it and I'm just curious
48:54
your thoughts on the feasibility of that and whether that's going to allow us to really win the race on AI or if there
49:00
needs to be some other policies to consider about how we can use both existing and new
49:07
resources I was I was uh I was here a couple weeks ago and the administration
49:13
was very clear that that um uh they would like American companies to have uh as
49:22
much opportunity to build data centers here in America and and and uh the admin
49:28
Administration recognizes that that um uh permitting and getting access to the
49:34
power in various various places around the country could be difficult um and
49:40
that they would like to be an ally to help um uh with with uh uh accelerating
49:48
that process so that the American companies don't have to look offshore and outside our country to do so and so
49:55
I I think this is one building the AI infrastructure of our country is a vital
50:01
National interest and and although although uh it consumes energy uh to
50:10
train the models the models that are created will do the work much more
50:16
energy efficiently and so when you think about the longitudinal the life the
50:21
lifespan of an AI um the Energy Efficiency and the productivity gains
50:27
that we'll get from it from an industry from from from our society is going to be is going to be incredible and um uh
50:35
and so we we spent some time to help people understand the big pictures of AI uh the challenges of of um provisioning
50:42
energy to AI but also some of the some of the things to to uh realize that the
50:48
AI is running an AI Factory and training an AI doesn't have to be like running a hospital it doesn't need to have 99.9
50:56
9999 99% up time you know if it's down if it's down a couple percent you know
51:03
5% from time to time it's okay it's okay you know just stop studying for a few
51:09
hours you know you'll pick up where you left off and so it's actually called checkpoint and restart you know take a
51:16
break and we'll pick up where you left off and so so I I think um we should understand the the the challenges but
51:24
also the differences challenges and the differences of provisioning uh energy to artificial intelligence that's like this
51:31
question on the screen here will AI really save energy or we just use the efficiencies to power other tasks so
51:38
you've answered that in part but is there any way to say like how much or
51:43
what our Target might be well we have many examples uh one example one example
51:48
is uh the example was giving about weather simulation right right yeah we we uh predict weather 3,000 times less
51:56
energy than a supercomputer mhm um the the number of examples are are
52:02
quite abundant um but it doesn't change the fact that this question is the other
52:09
side of it is probably right that we'll end up saving energy but society would
52:14
then apply the energy saved to go do something else yeah and and um we call
52:20
that Prosperity yeah economic grow yeah economic growth uh the Improvement of
52:26
quality of life which we want to see the fact of the matter
52:31
is on an absolute basis I hope that we all
52:38
hope that the population of Earth consumes more energy
52:44
someday because it's directly related to quality of life it's directly related to
52:50
Prosperity we we want every everyone to enjoy this quality of life yeah and so
52:56
absolutely amen all right over here yes there's a microphone where are we we okay over
53:03
here but please microphone come over here oh you've got one okay yes ma'am okay thank you so much thank you Mr
53:09
Jensen really appreciate your commentary today and I want to touch on one of your critical points which is the importance
53:16
of educating policy makers on the realities of AI so my name is Amita
53:21
lazari I come from the tech policy profession previously at Intel and today I'm a startup founder co-founder of a
53:27
company called open policy and we use Ai and work with some of the best unicorns in the world to better connect them to
53:33
what's coming from policy and be able to scale policy engagement a profession that has uh you know some special
53:40
expertise that requires that translation and I want to ask your opinion on how AI can be used to scale uh think thank work
53:48
that this connection between Innovation and policym and just liberate all of this information that is here in DC
53:54
about what's coming and bring it to C Valley you said it so fast I think my
54:03
data rate is about 80% of yours and and
54:09
is uh I I think I think I I I think I understand if I answer a wrong question
54:17
uh let me apologize in advance the um AI has a wonderful ability to
54:26
teach to explain very complicated Concepts
54:32
and I use AI today to as I was mentioning to Margaret that I use it
54:37
literally every day I literally use AI every single day and I use it to explain
54:44
things to me and when when um uh it's a New Concept uh I might ask it to explain
54:50
it as simply as possible and then I can dig further and further and further and
54:55
and uh delve further into it and and I love the fact that they could explain it as a fifth
55:02
grader I love the fact that that um it can give me more depth and and I can
55:08
then ask it you know explain it to me now from their first principles of Science and and um uh uh now explain it
55:17
with analogies now break it down step by step
55:23
you know all these different ways of learning because you know when we engage new ideas we need to engage it at
55:28
different levels and ideally you know at the highest possible level and break down the information you know into its
55:35
Elemental Parts over time and so I I do think that that uh the work that you're
55:40
doing using AI um to expose the Technologies to policy
55:47
makers would be a wonderful benefit to them now in the future hopefully they'll just use it themselves you know just
55:54
it's on the phone just you know which is the way I use it and and so it's like my my phone now is is super smart yeah but
56:02
the ability to query in a intelligent and useful way is certainly a skill that
56:08
you obviously have sir hey Jensen thanks for coming here Mike Chan from Deep Ventures um first of
56:14
all you and my wife share a last name so we should talk about that sometime um
56:19
okay uh second of all I invest in if you're suggesting I owe you money
56:27
check my I um I'm just kidding uh so I uh invest humor is
56:33
allowed in DC abely this is my first meeting a the course correct
56:39
immediately um so I invested in crypto startups and our industry would kind of
56:46
like to thank your industry for taking a little bit of the heat off of the negative PR of Bitcoin mining and and
56:53
all that but but that that being said um you know a lot lot of power producers energy producers um the excess energy
57:01
they allocate that to Bitcoin mining because there's a very clear Market there um kind of onetoone financial
57:06
Market there do you see something like that possible in terms of like a smart Grid or like having those companies be
57:12
able to dedicate some of that excess energy to training models and like and
57:19
providing that power to you just gave um uh a an a current example of excess
57:26
energy being used to convert in to store that
57:32
energy essentially what Bitcoin is doing is taking excess energy storing it into
57:39
a new form it's called currency and you take that currency and you take it wherever you like and so you took energy
57:46
from one place and now you've transported it everywhere now of course
57:51
that's just Bitcoin imagine a much more Universal currency called
58:00
intelligence using exactly all the same concept that you described you you find
58:05
places with excess energy go put a data center there trans transfer that energy
58:13
compress it into an artificial intelligence model take that model all over the place to use it make sense same
58:20
idea excellent okay we're going to ask this question and then one more it says can you discuss the difference in
58:26
requirements for hydrogen production with AI versus without I have no idea I
58:32
was going to say I mean ask ask your phone to answer this this question all right thank you for that though okay all
58:38
right okay last question yeah hello I'm a lawyer from South Korea I've
58:44
observed how MD AI technology are revolutionizing various industrious in
58:50
the legal sector the adoption of AI is accelerating particularly in area like
58:56
document analysis Automation and Regulatory Compliance monitoring which
59:01
hold significant Potential from your perspective how do you envision AI te
59:08
technology being utilized in the legal and Regulatory Industries in the future
59:14
and what Innovations might we expect to see in these fields thank you regulatory
59:21
implications of AI regulatory impc ation of
59:27
AI um there will be no task done no knowledge task
59:36
done in any industry by anyone that will
59:42
not involve AI in the loop in the near
59:47
future any information knowledge worker it could be information about an
59:54
engineer um legal documents and software code reads
1:00:00
similarly if well written and I AI contributes to to software coding
1:00:08
significantly today we use AI to code write our software inside our company we
1:00:13
use AI to debug our software which is to find the flaws in it you will use AI to
1:00:19
produce legal documents you will use AI to analyze documents you will use AI to
1:00:24
enhance the legal documents and so uh every aspect of of information
1:00:31
knowledge will involve that therefore all policy will involve AI in
1:00:38
the future and the reason for that is policy is code it's code for for
1:00:44
appropriate behavior and code um uh if
1:00:50
if written well um uh doesn't contradict itself
1:00:56
and and um achieves the mission the the goal of of uh the policy and so uh
1:01:04
policy light code will also en be enhanced with AI uh almost everything
1:01:09
that we do in the future will have ai in the loop and and human in the loop you
1:01:14
know we'll be collaborating uh to to do everything that is the perfect note to end on Jensen I think so let join me in
1:01:22
thanking this fantastic thank you thank you thank you
=================
Nvidia DC summit 8.9 October
, VP and General Manager of Enterprise Platforms, NVIDIA
Don't miss this special address from Bob Pette, where he’ll discuss how NVIDIA's accelerated computing platform is delivering breakthrough performance in the next wave of AI, sensor processing, digital twins, cybersecurity, autonomous systems, and...
Industry Segment: All Industries
Tuesday, Oct 810:00 AM - 11:00 AM EDT
JW Marriott - Grand Ballroom
Talk or Panel
, Vice President of Developer Programs and Corporate Marketing, NVIDIA
Preparing the workforce for a future where AI drives innovation across every industry needs public and private partnerships that can bridge the skills gap and ensure that urban and rural communities can participate. This session will explore how...
Industry Segment: Public Sector
Tuesday, Oct 81:00 PM - 2:00 PM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
, Director, AI Foundations, Lockheed Martin
Lockheed Martin is taking advantage of our system engineering heritage and machine learning operations (MLOps) to meet the standards set by the new Executive Order on AI safety and security. Our framework—implemented in our AI factory MLOps and...
Industry Segment: Public Sector, Aerospace
Tuesday, Oct 81:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
, Deputy Director of the Office of Data Science Strategy, National Institutes of Health (NIH)
, Federal Healthcare Leader, NVIDIA
, Chief Data Scientist, Enterprise Intelligence and Data Solutions Program Executive Office, Defense Healthcare Management System (EIDS, PEO DHMS)
, Chief Technology Officer, Advanced Research Projects Agency for Health (ARPA-H)
, Assistant Secretary for Technology Policy, National Coordinator for Health Information Technology, and Acting Chief Artificial Intelligence Officer, U.S. Department of Health and Human Services
Federal health agencies are using AI to enhance public health outcomes, streamline operations, and advance medical research. This panel discussion will feature prominent representatives from major NIH institutes who will share their insights on...
Industry Segment: Public Sector, Healthcare & Life Sciences
Tuesday, Oct 81:00 PM - 1:40 PM EDT
JW Marriott - Grand Ballroom Salon II & III
Talk or Panel
, Graduate Fellow with the Berkeley Risk and Security Lab, a Research Fellow at Berkeley’s Human Rights Center, and an AI Policy Fellow at the Center for Security in Politics, Berkeley AI Research
NVIDIA's advanced computing capabilities, combined with pioneering machine learning models, are transforming the field of remote sensing and geospatial intelligence. This presentation will explore the groundbreaking work of Berkeley Artificial...
Industry Segment: Public Sector
Tuesday, Oct 81:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
Live (All Audiences Ungated)
, Vice President Generative AI Software Product Management, NVIDIA
This talk will kick off a day of discussions, workshops, and demonstrations, providing an overview of NVIDIA's generative AI platform and its transformative capabilities. We'll explore how the platform drives innovation, accelerates research, and...
Industry Segment: Public Sector, All Industries
Tuesday, Oct 81:00 PM - 1:40 PM EDT
JW Marriott - Grand Ballroom Salon I
Talk or Panel
, Vice President, Omniverse and Simulation Technology, NVIDIA
Join us for a strategic session presented by NVIDIA's Rev Lebaredian, where we'll explore the integration of NVIDIA’s advanced technologies: OVX for simulation, DGX for AI model training, and Jetson for edge inference. These platforms collectively...
Industry Segment: Public Sector, Defense
Tuesday, Oct 81:00 PM - 1:40 PM EDT
JW Marriott - Grand Ballroom Salon IV
Talk or Panel
Live (All Audiences Ungated)
, Vice President, Omniverse and Simulation Technology, NVIDIA
, Artificial Intelligence Research Engineer Manager, Lockheed Martin
, NG Fellow/ Space Sector Data & AI Architect, Northrop Grumman Space System
, Executive Vice President, PLM Products, Siemens Digital Industries Software
Advanced manufacturing is being revolutionized by the integration of digital twin technology, driving unprecedented levels of precision, efficiency, and innovation in the public sector. Join distinguished leaders from Huntington Ingalls, Lockheed...
Industry Segment: Public Sector, All Industries
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Grand Ballroom Salon II & III
Talk or Panel
, Head of Advanced Computing, Georgia Tech Research Institute
The minimum variance distortionless response (MVDR) beamformer is used in phased array systems to preserve gain in a given direction while reducing gain in other directions which correspond to interfering signals. Because this algorithm requires...
Industry Segment: Public Sector
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
Live (All Audiences Ungated)
, Senior Computer Scientist, Air Force Research Laboratory (AFRL)
, Director, U.S. Army Artificial Intelligence Integration Center (AI2C)
, Chief Technology Officer, U.S. Central Command
This session explores some of the Department of Defense’s most exciting science and research initiatives in Generative AI for national security. These initiatives by the Air Force Research Lab and the Army AI Integration Center (AI2C) are...
Industry Segment: Public Sector, Defense
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Grand Ballroom Salon I
Talk or Panel
, Chief Technology Officer, Boston Dynamics
Learn what mobile robots are up to in the real world and how Boston Dynamics applies emerging AI to deliver value to our customers. We are witnessing the transition from research to reality for robots capable of moving around, and interacting...
Industry Segment: Public Sector, All Industries
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Grand Ballroom Salon IV
Talk or Panel
, Senior Solution Architect, NVIDIA
, Senior Solution Architect, North America Enterprise Software, NVIDIA
In this session, we'll explore the diverse landscape of Generative AI (GenAI) tools and techniques, providing a roadmap for incorporating these technologies into daily workflows. We'll examine popular commercial GenAI tools like Claude and...
Industry Segment: Public Sector, Government / National Labs
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon F
Talk or Panel
, Fellow, Lockheed Martin
Modern sensor systems require the creating, moving, processing, and decision-making of vast amounts of sensor data in a relevant timeframe. Traditional sensor processing challenges, bottlenecks, and pressure points can be reframed as opportunities...
Industry Segment: Public Sector
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
Live (All Audiences Ungated)
, CTO, US Public Sector, HPE
AI in Government has a massive potential to revolutionize Agency operations and citizen services, but the traditional three tiered Enterprise we've grown up with needs to evolve to support the AI workloads that will underpin modern organizational...
Industry Segment: Government / National Labs
Tuesday, Oct 82:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
Live (All Audiences Ungated)
, Senior Director, Global Head of Business Development, Life Sciences, NVIDIA
, Director, Advanced Research Projects Agency for Health (ARPA-H)
The convergence of AI and digital biology data is reshaping the global healthcare and biotech landscape. Join the discussion to understand the critical factors driving innovation, the role of public and private investment, and the challenges and...
Industry Segment: Public Sector, Healthcare & Life Sciences
Tuesday, Oct 83:00 PM - 3:40 PM EDT
JW Marriott - Grand Ballroom Salon I
Talk or Panel
, Co-Founder & CTO, Plato Systems, Plato Systems
, Director of Product Marketing, NVIDIA Metropolis, NVIDIA
"We're witnessing the evolution of factory automation with generative AI, visual language models (VLMs), sensor fusion, and digital twins. Learn how these technologies are transforming factory operations with automated visual inspection, sensor...
Industry Segment: Public Sector, Manufacturing
Tuesday, Oct 83:00 PM - 3:40 PM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
, Developer Advocate Manager, NVIDIA
Advancements in Large Language Models (LLMs) have enabled developers to create a variety of applications such as code generation, translation, and text summarization. The effectiveness of all these models depends on the quality of the data used...
Industry Segment: Public Sector, Financial Services
Tuesday, Oct 83:00 PM - 3:40 PM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
, Senior Product Marketing Manager - LLMs, NVIDIA
, System Software Manager, NVIDIA
NVIDIA RTX AI provides an end-to-end, GPU-accelerated platform for building and deploying state-of-the-art AI models across PC and cloud. Developers can use RTX to build private, on-device AI that keeps your data and applications secure, while...
Industry Segment: Public Sector, Government / National Labs
Tuesday, Oct 83:00 PM - 3:40 PM EDT
JW Marriott - Capitol Ballroom Salon F
Talk or Panel
Live (All Audiences Ungated)
, Chief Information Officer and Director of the Digital Capabilities Directorate, Air Force Research Laboratory
, US Army Chief Information Officer, US Army
, Principal Deputy Assistant Secretary of the Army for Acquisition, Logistics and Technology, US Army
, Vice President of Federal, NVIDIA
, Chief Technology Officer and Director Emerging Technology Directorate, Department of Defense
As generative AI continues to revolutionize industries worldwide, the Federal Government stands on the brink of a technological transformation that promises to enhance efficiency, improve decision-making, and drive innovation. This panel of...
Industry Segment: Public Sector
Tuesday, Oct 83:00 PM - 3:40 PM EDT
JW Marriott - Grand Ballroom Salon II & III
Talk or Panel
, Solution Architect, NVIDIA
In this generative AI session, we delve into fine-tuning of Large Language Models (LLMs) and the critical considerations for deploying these models in production for diverse enterprise needs. We explore cutting-edge techniques and best practices for optimizing LLMs, covering parameter-efficient fine-tuning methods like LoRA and Prefix Tuning, domain adaptation strategies, and balancing model size with computational resources for LLM inference. Key topics include hardware optimization with NVIDIA GPUs, performance evaluation metrics, and real-world case studies. This session is tailored for AI researchers, machine learning engineers, and data scientists familiar with LLM basics, offering insights to enhance model adaptation and deployment strategies.
Industry Segment: Public Sector, All Industries
Tuesday, Oct 83:00 PM - 3:40 PM EDT
, Program Manager Earth System Science Domain, NVIDIA
, CEO, The Weather Company
During March 2024, NVIDIA launched the Earth-2 digital twin program that provides enabling technologies for improved prediction in the modeling of Earth’s weather and climate based on advances in HPC and AI. These developments include GPU...
Industry Segment: All Industries
Wednesday, Oct 91:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
, Co-Leader, Biomarker and Genomic Sciences Group, National Institute of Standards and Technology
, Computational Scientist, Frederick National Laboratory for Cancer Research, National Cancer Institute
The aim of translational genomics is to get better diagnoses and treatments to patients, faster. In this talk, we’ll discuss how accelerated computing is facilitating modern genomics research by speeding up the development of benchmark human...
Industry Segment: Public Sector, Healthcare & Life Sciences
Wednesday, Oct 910:00 AM - 10:40 AM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
, Principal Developer Technology Engineer, NVIDIA
, Senior Engineering Technical Fellow, RTX
Raytheon (an RTX business) has mature, operational, HF Over-the-Horizon Radar (OTHR) sensor systems that provide the US Navy surveillance capability over vast theater areas. Recently, Raytheon has been using investment from the U.S. government and...
Industry Segment: Public Sector
Wednesday, Oct 99:00 AM - 9:40 AM EDT
JW Marriott - Grand Ballroom Salon IV
Talk or Panel
, Vice President and Chief Architect of AI systems, NVIDIA
As the variety and size of generative AI models and the processing needs continue to increase, the compute infrastructure needs to adapt to handle them relaibly. See how we're meeting these needs as we deploy with Blackwell architecture by...
Industry Segment: Public Sector, General
Wednesday, Oct 911:00 AM - 11:40 AM EDT
JW Marriott - Capitol Ballroom Salon F
Talk or Panel
, Director of Product Management, NVIDIA
See how NVIDIA and our partners are advancing OpenUSD as the data ecosystem for industrial digital twins and the next era of AI, including physical AI in autonomous vehicles and robots. We’ll cover pipelines for sensor simulation, CFD, data...
Industry Segment: Public Sector
Wednesday, Oct 92:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
Live (All Audiences Ungated)
, Director of the Energy Program, Bipartisan Policy Center
, Director of Michigan Institute for Computational Discovery and Engineering (MICDE), University of Michigan
, Director, Office of Critical and Emerging Technologies, Department of Energy
Artificial intelligence (AI) is transforming scientific discovery, economic growth, and national security, and with increased investment and strategic planning, the U.S. government can lead the way in developing safe and trustworthy AI for...
Industry Segment: Public Sector, Government / National Labs
Wednesday, Oct 91:00 PM - 1:40 PM EDT
JW Marriott - Grand Ballroom Salon II & III
Talk or Panel
, Engineering Manager, Cybersecurity AI, NVIDIA
, Senior Staff Engineer, Trend Micro
As cyber threats evolve at an unprecedented pace, the cybersecurity industry faces mounting challenges in detection, response, and workforce capabilities. This talk explores the transformative potential of generative AI in bolstering cyber defense...
Industry Segment: Public Sector
Wednesday, Oct 910:00 AM - 10:40 AM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
, Director, Quantum Algorithm Engineering, NVIDIA
Quantum Computing has the potential to revolutionize industries and usher in a new era of high-performance computing. However, realizing this potential crucially hinges on AI supercomputing to tackle algorithm research and overcome the design,...
Industry Segment: Public Sector, All Industries
Wednesday, Oct 911:00 AM - 11:40 AM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
, William Lincoln Smith Professor, Northeastern University
, Wireless Architect, NVIDIA
The rollout of 5G Advanced and subsequent transition to 6G represent radical transitions unlike any experienced in previous-generation cellular system. 5G Advanced will see the introduction of artificial intelligence and machine learning in all...
Industry Segment: Public Sector, Telecommunications
Wednesday, Oct 91:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon F
Talk or Panel
, Senior Principal, Strategic Outreach, MITRE Public Sector
Executing covert, autonomous UUV missions is crucial for extending the US Navy’s subsurface advantage. Currently, there's a unique opportunity to develop digital twins to provide unprecedented autonomous navigation intelligence for UUV mission...
Industry Segment: Public Sector
Wednesday, Oct 910:00 AM - 10:40 AM EDT
JW Marriott - Grand Ballroom Salon IV
Talk or Panel
, GVP, Data & AI, Oracle
, Oracle AI Specialist, Oracle
The rapid growth of foreign language data has created strain on analysts and linguists alike. Machine translation of foreign language data has proven to have limitations with questionable reliability and considerable cost. Cross language...
Industry Segment: Government / National Labs
Wednesday, Oct 99:00 AM - 9:40 AM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
, Applied Research Scientist, NVIDIA
, Senior Clinical and Head of MRI and Artificial Intelligence Sections, National Cancer Institute, NIH
This talk presents a collective body of work that has arisen out of the NIH research collaboration with NVIDIA beginning in 2019, starting with various organ-specific segmentation models and recently producing the NVIDIA VISTA-3D NIM foundation...
Industry Segment: Public Sector, Healthcare & Life Sciences
Wednesday, Oct 99:00 AM - 9:40 AM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
Live (All Audiences Ungated)
, Vice President, DGX Systems, NVIDIA
, Director, AI Foundations, Lockheed Martin
Enterprises in 2024 are making generative AI a cornerstone of their business strategies, whether it's to accelerate innovation, enhance operational efficiency, or unlock new revenue streams. This transformative shift brings with it the challenge...
Industry Segment: Public Sector, General
Wednesday, Oct 910:00 AM - 10:40 AM EDT
JW Marriott - Grand Ballroom Salon I
Talk or Panel
, CUDA Architect, NVIDIA
The NVIDIA CUDA platform is the foundation of the GPU computing ecosystem. Every application and framework that uses the GPU does so through its libraries, compilers, runtimes, and language—which means CUDA is growing as fast as its ecosystem is...
Industry Segment: Public Sector, All Industries
Wednesday, Oct 92:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon D
Talk or Panel
, Field CTO, Dell Technologies
Learn why the need for rapid decision-making and real-time data processing is paramount. Deploying next-generation artificial intelligence (AI) at the mission edge has become a strategic necessity for both Federal and commercial sectors. AI and...
Industry Segment: Public Sector
Wednesday, Oct 91:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
, Solutions Architect, NVIDIA
, Solutions Architect, Leidos
, Chief AI Officer, Leidos
Leidos will showcase an AI-enhanced command and control system designed to reduce cognitive load for decision-makers in rapidly evolving disaster response scenarios. With real-time signal processing and AI agent capabilities, the system integrates...
Industry Segment: Public Sector
Wednesday, Oct 92:00 PM - 2:40 PM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
Live (All Audiences Ungated)
, Vice President of Federal, NVIDIA
, SVP & Chief Technology Officer, MITRE
MITRE’s Federal AI Sandbox is a transformative initiative designed to accelerate AI discovery and innovation for the US federal government in domains like cybersecurity, climate, and healthcare. Gain valuable updates on the project’s progress,...Charles Clancy
Charles Clancy is senior VP and general manager of MITRE Labs, MITRE’s research, technology, and innovation organization. Before joining MITRE in 2019, Charles was the Bradley Professor of Electrical and Computer Engineering at Virginia Tech and led the Hume Center for National Security and Technology. He started his career at the National Security Agency, leading wireless R&D programs. Charles has led the development of international security standards for the IEEE, IETF, and Wireless Innovation Forum. He's published over 250 books, academic papers, and patents related to telecommunications.
Industry Segment: All Industries
Wednesday, Oct 99:00 AM - 9:40 AM EDT
JW Marriott - Grand Ballroom Salon I
Talk or Panel
, Senior Product Manager, Cesium
, Senior Solutions Architect, NVIDIA
Recent advances have allowed for surface mesh creation from real world image sources, spanning autonomous vehicles to airborne mapping systems. Many surface mesh extraction techniques, such as neural radiance field or gaussian splatting based...
Industry Segment: Public Sector, All Industries
Wednesday, Oct 91:00 PM - 1:40 PM EDT
JW Marriott - Capitol Ballroom Salon E
Talk or Panel
, Principal Solutions Architect, AWS
Join us as we explore the transformative journey of generative AI, from ideation to deployment. In this session, AWS will guide you through the end-to-end lifecycle of generative AI, highlighting key trends and best practices. We'll begin by...
Industry Segment: Public Sector
Wednesday, Oct 910:00 AM - 10:40 AM EDT
JW Marriott - Capitol Ballroom Salon G
Talk or Panel
Live (All Audiences Ungated)
, Principal Solution Architect, NVIDIA
, Director of Imagery and Remote Sensing, Esri
, Senior Director of Research at Clarifai, Clarifai
, President, The Cardillo Group, LLC
The volume of multi-spectral geospatial data processed daily is massive, and it is growing exponentially thanks to a growing fleet of Earth Observation satellites and other data capture devices powered by increasingly capable sensors. The task...
Industry Segment: Public Sector
Wednesday, Oct 92:00 PM - 2:40 PM EDT
JW Marriott - Grand Ballroom Salon II & III
Talk or Panel
, GPS Principal, Deloitte
, Chief Technology Officer, IRS
The passage of the Inflation Reduction Act provides the IRS an opportunity to reimagine the taxpayer experience and utilize best-in-class technologies. This fireside chat between the Chief Technology Officer of the IRS, Kaschit Pandya, and...
Industry Segment: Public Sector
Wednesday, Oct 92:00 PM - 2:40 PM EDT
SOME BASIC PIECES OF AI20s
Do you know how 5G works - slide from Charles Clancy SVP Mitre 2020 Presentation at Nvidia Summit -related to safety AI 2g
cloud is network - aps like autonomous driving neerd 1/1000 sec response ; integrates low latency subnet for eg gov safety ai- from 2024 companies like dell lenovo hgp unlikely to market devices without ai-5g+ world
can you tell me when is next itu plenoipotentialry and as far as good ai goes what may be some of the main standard advances to be designed ?
The next ITU Plenipotentiary Conference is scheduled for 2026 in Dubai, United Arab Emirates. This event is a crucial gathering for the International Telecommunication Union (ITU) where members determine the organization's strategic direction and elect its senior management.
As for good AI standards, the following advances may be considered crucial:
Ethical Frameworks:Developing robust ethical frameworks to guide AI development and deployment, ensuring that AI systems align with human values and avoid harmful biases.
Transparency and Explainability:Enhancing transparency and explainability of AI algorithms to understand how decisions are made, fostering trust and accountability.
Bias Mitigation: Implementing techniques to mitigate bias in AI models, ensuring fairness and preventing discrimination.
Data Privacy and Security: Strengthening data privacy and security measures to protect sensitive information and prevent unauthorized access.
Interoperability: Promoting interoperability between AI systems to enable seamless communication and collaboration.
Human-AI Collaboration: Fostering effective human-AI collaboration by designing AI systems that complement human capabilities and support human decision-making.
Continuous Learning and Adaptation: Developing AI systems that can continuously learn and adapt to new data and changing environments.
These advancements are essential to ensure that AI is developed and used responsibly and benefits society as a whole.
