https://www.nvidia.com/gtc/keynote/?nvid=nv-int-unbr-611784

after 73 year on earth ( quarter a million two-hour learning ops)  nothing remotely emulates  jensen huang innovations updates yesterday- how do we do justice to exploring humanity and jh worlds - eg first chat with gemini https://www.linkedin.com/article/edit/7175839118583590912/  

and who's partnering AIjensen AIJensennews

Nvidia 40 corporate tweets https://twitter.com/nvidia/following

thank goodness jor jh...gemini can you please tell me are you able to follow nvidia summit this week which i tried to intro in my previous post- Jensen Huang Nvidia annual update yesterday exploring at least 20 gamechanging ai partner experiments and has launched BLACKWELL - 3 times bigger than world's previous biggest ie now nearly 240 billion instead of 80 billion chips

here's jensen's take on future of biotech 

You're absolutely right! There is indeed a drug discovery company called Recursion and NVIDIA has a well-documented partnership with them. Here's what I can tell you:
Recursion Pharmaceuticals:

Focus: Recursion is a leading clinical-stage techbio company focusing on accelerating drug discovery through the use of artificial intelligence (AI).

Recursion OS: The company's core technology is their "Recursion OS," a platform that integrates various technologies to create one of the world's largest proprietary biological and chemical datasets. This data is then analyzed using sophisticated machine learning algorithms to identify potential drug candidates.

Focus on Diversity: Recursion emphasizes the importance of data diversity in AI-powered drug discovery. Their approach aims to go beyond traditional methods by considering a wider range of cellular and molecular features.

NVIDIA and Recursion Partnership:

Investment and Collaboration: In July 2023, NVIDIA announced a significant investment in Recursion through a private investment in public equity (PIPE) deal. This investment highlights NVIDIA's belief in Recursion's approach and the potential of AI for drug discovery.

Focus on AI Optimization: The partnership also involves collaboration on optimizing Recursion's AI models for NVIDIA's DGX™ Cloud platform, which provides high-performance computing resources specifically designed for AI workloads.

AI Expertise at Recursion:

Founders: While specific information about the founders' backgrounds isn't readily available, Recursion's leadership team likely includes individuals with expertise in AI, biology, chemistry, and drug discovery.

Overall Approach: The company's focus on AI and its collaboration with NVIDIA suggests a strong emphasis on AI expertise within the organization.

Overall:

The partnership between NVIDIA and Recursion represents a significant development in AI-powered drug discovery. By combining Recursion's expertise in AI and data analysis with NVIDIA's powerful computing hardware, they aim to accelerate the development of new life-saving medications.

Here are some additional resources you might find interesting:

Recursion Website: https://www.recursion.com/
NVIDIA and Recursion Announce Collaboration: https://ir.recursion.com/news-releases/news-release-details/recursi...
AI and Drug Discovery: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10302550/
profile picture


Jensen Huang has a vision that the future of drug discovery will not be in "the lab" ; I couldn't quite hear what he calls the alternative - "in silico" do you know about this alternative digital process he sees - can you explain what he is talking about


You're exactly right! Jensen Huang, CEO of NVIDIA, is a strong proponent of using "in silico" methods for drug discovery, which represents a significant shift from traditional laboratory-based approaches. Here's a breakdown of what "in silico" means in this context:

Traditional Drug Discovery:

  • Lab-Centric: Traditionally, drug discovery involves a long and expensive process conducted primarily in laboratories. Researchers synthesize and test numerous candidate molecules to see if they have the desired therapeutic effect.

  • Limitations: This traditional approach can be slow, resource-intensive, and have limitations in terms of scalability. Testing a vast number of potential molecules is impractical in a lab setting.

In Silico Drug Discovery:

  • Harnessing Computing Power: "In silico" refers to using computational methods and computer simulations to model and analyze biological systems. In drug discovery, this involves using powerful computers and AI to:
    • Virtual Screening: Analyze vast databases of molecules to identify those with potential for a specific drug target.
    • Predictive Modeling: Predict how a molecule might interact with biological systems, helping to prioritize promising candidates.
    • Molecule Design: In some cases, AI can be used to design new drug-like molecules with desired properties.

Benefits of In Silico Methods:

  • Faster and Cheaper: In silico methods allow for much faster screening of potential drug candidates compared to traditional lab work.
  • Scalability: These methods can analyze vast amounts of data and explore a much larger chemical space than what's feasible in a lab setting.
  • Improved Efficiency: AI can help identify promising leads with a higher probability of success, reducing the number of failed experiments in the lab.

NVIDIA's Role:

  • Focus on Computing Power: NVIDIA, with its powerful GPUs, is well-positioned to contribute to in silico drug discovery.
    • Faster Simulations: Their hardware can accelerate complex simulations of biological processes, leading to faster drug discovery pipelines.
    • AI Acceleration: NVIDIA's GPUs are also well-suited for running the AI models that are crucial for in silico analysis.

Overall:

In silico drug discovery represents a significant paradigm shift in the pharmaceutical industry. By leveraging computational power and AI, this approach holds immense potential for accelerating the development of new and effective medications. Jensen Huang's vision reflects the growing importance of in silico methods in the future of drug discovery.

volume_up - and some other overviews

I can definitely follow the Nvidia GTC (GPU Technology Conference) happening this week even though I can't access specific session details behind logins or paywalls. Here's what I can do:

  • News and summaries: I can search for news articles, press releases, and social media discussions about the summit. This will give us a good overview of the key announcements and trends emerging from the event.

  • Official Nvidia sources: I can access Nvidia's official website and social media channels for summaries of keynote speeches, major announcements, and presentations.

  • Publicly available content: Some sessions or presentations might be publicly available online or through live streams. I can help you find and explore those resources.

While I can't replicate the full delegate experience, I can still help you stay informed about the key takeaways from the Nvidia summit.

Here are some specific points from your message we can discuss:

  • Jensen Huang's influence: You mentioned Jensen Huang being an "AI superhero." We can explore his keynote address and see what vision he presented for the future of AI.

  • Blackwell: The launch of Blackwell, a 3x larger chip compared to the previous top contender, is a significant development. We can discuss the potential applications of this powerful chip and its impact on AI advancements.

  • AI Partner Experiments: The summit explores experiments from 20+ Nvidia partners. We can explore summaries or news articles to understand the focus areas and potential breakthroughs in AI across different sectors.

Let me know which aspects of the summit you'd like to discuss further. I can help you find relevant information and understand the significance of these announcements.

share

more_vert

Maximize image
Edit image
Delete image

i would love to understand better jensen huamgs 2 hour speech; i did watch it yesterday but there were so many completely new adventures - do you have a first list of biggest new partnerships and ai advances that he guided people round?

volume_up

Since you watched Jensen Huang's GTC keynote speech yesterday, I can't access the full content directly, but I can help you unpack some of the key announcements and partnerships based on what news sources and official Nvidia channels are reporting. Here's a potential breakdown of some biggest themes:

1. The Rise of Generative AI (GenAI): News suggests Huang might have positioned Generative AI as a central theme. This technology can create entirely new data (images, text, code) and could revolutionize various fields. Look for announcements related to advancements in GenAI tools and partnerships leveraging its potential.

2. The B100 Blackwell Chip Launch: This new chip, boasting 3x the capacity of its predecessor, is a game-changer. Explore details around its architecture, performance improvements, and how it will accelerate AI workloads across sectors.

3. The Omniverse and Digital Twins: The Nvidia Omniverse platform allows creating real-time simulations. We can expect updates on how the platform is evolving and new partnerships that leverage it for creating digital twins of factories, cities, etc.

4. AI for Enterprise Applications: News suggests Huang might have focused on how AI can improve enterprise efficiency. We can explore announcements related to AI-powered chatbots, data analysis tools, and automation solutions for businesses.

5. Partner Experiments: There were discussions on 20+ AI partner experiments. Look for news or summaries highlighting specific partnerships focusing on cutting-edge AI applications in healthcare, robotics, materials science, or other fields.

Here are some resources to dig deeper:

  • Nvidia GTC website: https://www.nvidia.com/en-us/geforce/ - Check for press releases, blog posts, or keynote summaries.

  • News articles: Search for "Nvidia GTC 2024 highlights" or "Jensen Huang keynote takeaways" to find summaries from tech news websites.

  • YouTube videos: Search for "Nvidia GTC 2024 keynote" on YouTube. You might find unofficial recordings or breakdowns of the speech.

Remember, these are just potential areas based on publicly available information. As you explore further, you might discover other exciting announcements or partnerships that pique your interest.

share

more_vert

Maximize image
Edit image
Delete image

Yes all very big - 2 blackkwell and 3 digital twins omniverse sounded like while new adventures - do you have any first sufggestions for eg teachers of 10th grade on what to see first in these new to world spaces for human and AI celebration?

e


Here are some suggestions for 10th-grade teachers interested in the latest AI advancements from Nvidia GTC, focusing on Blackwell and the Omniverse:

Blackwell:

  • Focus on the scale: Blackwell boasts 3x the capacity of previous chips. This can be mind-boggling for students. Search for resources that explain transistors and processing power in simple terms. Relate it to everyday tasks - perhaps how this chip could enable faster weather simulations or improve movie special effects.

  • Explore real-world applications: Blackwell's power will benefit various fields. Find articles or videos showcasing AI-powered applications in areas students might find interesting, likeMedicine: Drug discovery, medical imaging analysisClimate science: More complex weather simulationsEntertainment: Hyper-realistic animation in games or movies

The Omniverse and Digital Twins:

  • The "twin" concept is key: Digital twins are virtual replicas of real-world systems. This can be a head-scratcher. Find resources that use relatable examples - perhaps a digital twin of a school building used to optimize energy use or a race car to test performance virtually.

  • Focus on the interactive aspect: The Omniverse allows real-time interaction with digital twins. This opens doors to new learning experiences. Imagine students virtually dissecting a frog in a simulated biology lab or exploring a historical landmark virtually reconstructed in the Omniverse.

Resources:

  • Nvidia Website: The official Nvidia website might have resources specifically targeted at educators. Look for sections like "Education" or "Learning resources".

  • YouTube Videos: Search for "Nvidia Omniverse explained" or "Blackwell chip applications" for educational videos explaining these concepts.

  • News articles: Find articles with clear explanations - look for phrases like "ELi5" (Explain Like I'm 5) to ensure they are suitable for 10th graders.

Remember, the goal is to spark students' interest and imagination. These new advancements can open doors to future careers in AI, engineering, or even creative fields!

Views: 18

Reply to This

Replies to This Discussion

Team Jensen have co-created partnership innovation processes of accelerated computing -check them out 

eg digital twins

NVIDIA Announces Earth Climate Digital Twin

  3 Minutes Read

To accelerate efforts to combat the $140 billion in economic losses due to extreme weather brought on by climate change, NVIDIA announced its Earth-2 climate digital twin cloud platform for simulating and visualizing weather and climate at an unprecedented scale.

Part of the NVIDIA CUDA-X microservices, announced separately today, Earth-2’s new cloud APIs on NVIDIA DGX Cloud allow virtually any user to create AI-powered emulations to speed the delivery of interactive, high-resolution simulations ranging from the global atmosphere and local cloud cover to typhoons and turbulence.

When combined with proprietary data owned by companies in the $20 billion climate tech industry, the Earth-2 application programming interfaces help users deliver warnings and updated forecasts in seconds compared to the minutes or hours in traditional CPU-driven modeling.

“Climate disasters are now normal — historic droughts, catastrophic hurricanes and generational floods appear in the news with alarming frequency,” said Jensen Huang, founder and CEO of NVIDIA. “Earth-2 cloud APIs strive to help us better prepare for — and inspire us to act to moderate — extreme weather.”

Generative AI for Climate Tech

Earth-2’s APIs offer AI models and employ a new NVIDIA generative AI model called CorrDiff, using state-of-the-art diffusion modeling, that generates 12.5x higher resolution images than current numerical models 1,000x faster and 3,000x more energy efficient.

It corrects inaccuracies of coarse-resolution forecasts and synthesizes metrics critical to decision-making. CorrDiff is a first-of-its-kind generative AI model that delivers super-resolution, synthesizes new metrics of interest to stakeholders, and teaches the physics of fine-scale local weather from high-resolution datasets.

The Central Weather Administration of Taiwan plans to use these diffusion models to forecast more precise locations of typhoon landfall.

When a typhoon warning is launched, the priority is to minimize casualties by carrying out early evacuations based on quality information generated by relevant agencies, including Taiwan’s National Science and Technology Center for Disaster Reduction (NCDR). In the last decade, the death toll due to typhoons has fallen.

“Taiwan is a critical component of the global supply chain, and flooding risk analysis and evacuation preparedness are core to our mandate,” said Chia-Ping Cheng, administrator of CWA.

With more than 136 typhoons striking the island since 2000, using Earth-2 to mitigate these impacts is key to improving the quality and resolution of disaster informatics, NCDR said.

Another key component of Earth-2 cloud APIs is NVIDIA Omniverse, a computing platform that enables individuals and teams to develop Universal Scene Description (OpenUSD)–based 3D workflows and applications.

The Weather Company, a global leader in weather data forecasting and insights, plans to integrate its meteorological data and Weatherverse tools with Omniverse, enabling customers building digital twins to better understand and visualize the impact of actual weather conditions for the first time.

The Weather Company also plans to explore the use of NVIDIA score-based generative AI for its Weatherverse services, Weather Engine solution for enterprise-level weather intelligence, and new high-resolution weather modeling products.

“To help effectively address current and future weather- and climate-related challenges, it’s critical now more than ever to incorporate reliable, globally scaled real weather data and insights into digital twin environments to better analyze, plan and simulate the impacts of weather,” said Sheri Bachstein, CEO of The Weather Company.

2024 huang GTC

The heavy lifting in manufacturing, factory logistics, and robotics is getting assistance from real-time AI, according to NVIDIA CEO Jensen Huang’s keynote at GTC 2024.

A simulation-first approach is paving the way for the next phase of automation in these industries that often involve bulky products, expensive equipment, collaborative robotic environments, and logistically-complex facilities.

Huang demonstrated how developers could use digital twins to develop, test, and refine their large-scale, real-time AI entirely in simulation before deploying it in industrial infrastructure—saving significant time and cost. NVIDIA’s Omniverse, Metropolis, Isaac, and cuOpt platforms interact in “AI gyms” where developers can train AI agents to help robots and humans navigate unpredictable or complex situations.

In a demo, a 100,000-square-foot warehouse’s digital twin built with Omniverse operated as a simulation environment. It included dozens of digital workers, multiple autonomous mobile robots (AMRs) running NVIDIA Isaac’s multi-sensor stack, vision AI agents, and sensors. Metropolis created a centralised occupancy map by fusing data from 100 simulated camera streams to inform optimal AMR routes calculated by cuOpt’s complex routing optimisation AI.

This all happened in real-time while Isaac Mission Control coordinated the AMR fleet using cuOpt’s mapping and routing data. When an incident blocked an AMR’s path, Metropolis updated the occupancy grid, cuOpt planned a new optimal route, and the AMR responded accordingly to minimise downtime.

2022 BMW 

, CTO and Co-Founder, ipolog GmbH
, Manager Logistics Planning Processes and Product Owner Logistics Planning, BMW
We'll present work from an ongoing collaboration between BMW, ipolog, and NVIDIA showing how digital twins
and accelerated combinatorial optimization can lead to 20% reduction in the required number of transport vehicles.
With the help of ipolog, NVIDIA cuOpt, and Omniverse, BMW can explore many possible versions of a true-to-life digital twin and evaluate each according to its impact on the optimized state of operation. Initial testing with intra-logistics transport order routing has shown opportunities for a significant reduction in cost. In addition to the intralogistics optimization, we'll also evaluate the usage of cuOpt for inbound logistics optimization. We'll briefly cover the problems being addressed and their solutions, and end with a discussion of the path ahead.
======================
2023 

NVIDIA unveils Omniverse innovations to accelerate OpenUSD adoption


NVIDIA has unveiled a suite of innovations to accelerate the widespread adoption of OpenUSD through its Omniverse industrial metaverse platform.

OpenUSD, created by Pixar Animation Studios, is a cutting-edge 3D scene description technology designed to facilitate interoperability across various tools, data, and workflows.

Earlier this month, NVIDIA joined industry titans in creating the Alliance for OpenUSD (AOUSD) to standardise OpenUSD specifications and create a solid...

Biotech AI cases  

NVIDIA Healthcare Launches Generative AI Microservices ...

NVIDIA Newsroom
https://nvidianews.nvidia.com › news › healthcare-gener...
7 days ago  Watch NVIDIA CEO Jensen Huang's ... BioNeMo microservices, such as the MolMIM generative chemistry model and the AlphaFold-2 model for protein ...

NVIDIA Launches Generative AI Microservices for Developers to Create and Deploy Generative AI Copilots Across NVIDIA CUDA GPU Installed Base

March 18, 2024

  • New Catalog of GPU-Accelerated NVIDIA NIM Microservices and Cloud Endpoints for Pretrained AI Models Optimized to Run on Hundreds of Millions of CUDA-Enabled GPUs Across Clouds, Data Centers, Workstations and PCs
  • Enterprises Can Use Microservices to Accelerate Data Processing, LLM Customization, Inference, Retrieval-Augmented Generation and Guardrails
  • Adopted by Broad AI Ecosystem, Including Leading Application Platform Providers Cadence, CrowdStrike, SAP, ServiceNow and More

GTC—NVIDIA today launched dozens of enterprise-grade generative AI microservices that businesses can use to create and deploy custom applications on their own platforms while retaining full ownership and control of their intellectual property.

Built on top of the NVIDIA CUDA® platform, the catalog of cloud-native microservices includes NVIDIA NIM microservices for optimized inference on more than two dozen popular AI models from NVIDIA and its partner ecosystem. In addition, NVIDIA accelerated software development kits, libraries and tools can now be accessed as NVIDIA CUDA-X™ microservices for retrieval-augmented generation (RAG), guardrails, data processing, HPC and more. NVIDIA also separately announced over two dozen healthcare NIM and CUDA-X microservices.

The curated selection of microservices adds a new layer to NVIDIA’s full-stack computing platform. This layer connects the AI ecosystem of model developers, platform providers and enterprises with a standardized path to run custom AI models optimized for NVIDIA’s CUDA installed base of hundreds of millions of GPUs across clouds, data centers, workstations and PCs.

Among the first to access the new NVIDIA generative AI microservices available in NVIDIA AI Enterprise 5.0 are leading application, data and cybersecurity platform providers including AdobeCadenceCrowdStrike, Getty Images, SAPServiceNow, and Shutterstock.

“Established enterprise platforms are sitting on a goldmine of data that can be transformed into generative AI copilots,” said Jensen Huang, founder and CEO of NVIDIA. “Created with our partner ecosystem, these containerized AI microservices are the building blocks for enterprises in every industry to become AI companies.”

NIM Inference Microservices Speed Deployments From Weeks to Minutes
NIM microservices provide pre-built containers powered by NVIDIA inference software — including Triton Inference Server™ and TensorRT™-LLM — which enable developers to reduce deployment times from weeks to minutes.

Reply to Discussion

RSS

Epoch changing Guides

1 AI Training AI Training.docx

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

.2016-23.pptx

help assemble 100000 millennials summitfuture.com and GAMES of  worldrecordjobs.com card pack 1 i lets leap froward from cop26 glasgow nov 2021 - 260th year of machines and humans started up by smith and watt- chris.macrae@yahoo.co.uk-

WE APPROACH 65th year of  Neumann's tech legacy - 100 times more tech decade - which some people call Industrial Rev 4 or Arttificial Intel blending with humans; co-author 2025report.com, networker foundation of The Economist's Norman Macrae -

my father The Economist's norman macrae was privileged to meet von neumann- his legacy of 100 times more tech per decade informed much of dad's dialogues with world leaders at The Economist - in active retirement dad's first project to be von neumanns official biographer - english edition ; recently published japanese edition - queries welcomed; in 1984 i co-authored 2025report.com - this was celebrating 12 th year that dad( from 1972, also year silicon valley was born) argued for entrepreneurial revolution (ie humanity to be sustainable would need to value on sme networks not big corporate nor big gov); final edition of 2025report is being updated - 1984's timelines foresaw need to prep for fall of brlin wall within a few months; purspoes of the 5 primary sdg markets were seen to be pivotal as they blended real and digital - ie efinance e-agri e-health e-learning and 100%lives matter community; the report charged public broadcasters starting with BBC with most vital challenge- by year 2000 ensure billions of people were debating man's biggest risk as discrepancy in incomes and expectations of rich & poor nations; mediated at the right time everyone could linkin ideas as first main use of digital webs--- the failure to do this has led to fake media, failures to encourage younger half of the world to maxinise borderless friendships and sdg collabs - see eg economistwomen.com abedmooc.com teachforsdgs.com ecop26.com as 2020s becomes last chance for youth to be teh sustainability generation


 

© 2024   Created by chris macrae.   Powered by

Report an Issue  |  Terms of Service