Jensen100

Breaking - help us video tour every placesmost youth inspiring intelligences

Breaking 16 March2026 at nvidia youtube today replay Jensen GTU speech - his global update of partners and purposes of computers with billion times more maths brainpower than separate human minds- note search out last time jensen keynoted in place you care about for more personalised ai agency nb jensen cases cover all tech needs to bring together to advance human work - eg 5 layers of full stack ai - energy , supercomputer chips, place unique investment purpose of tech and peoples, ai models, scaling community actions/aps. There are at least 3 gameboards beyond LLM agency: Einsteins' solutions to natures biggest puzzles such as illnesses and resource sustainability, space, how world class citizens demand last mile services from autonomous robots and eg drones.

Nptable other talks include: open models (below) updaye on robotics, and futures as anticipated by nvidia's daly and googe's dean

Breaking Jensen Huang hosts open model session

Open Models: Where We Are and Where We’re Headed [S82480] March 18 3.30est

Harrison Chase | Co-Founder and CEO | LangChain

Jensen Huang | Founder and CEO | NVIDIA

Michael Truell | CEO and Co-Founder | Cursor

Misha Laskin | Co-founder and CEO | Reflection AI

Aravind Srinivas | CEO & Co-founder | Perplexity

Mira Murati | Founder and CEO | Thinking Machines Lab

Arthur Mensch | Co-Founder and CEO | Mistral

Daniel Nadler | CEO | OpenEvidence

Hanna Hajishirzi | Professor, Sr. Director NLP | AI2

Anjney Midha | Founder | Founder, AMP PBC

Robin Rombach | Co-Founder and CEO | Black Forest Labs

Help us clarify which ai superstars you may want to know Case Jensen Huang One of keys to life in 2026 is understand 3 million fold tech chnages: what did people do with million fold more chip power 1965-95 then 95-2025 what did they do with million times deeper computer brainpower acceleration and million fold more data transmitted by satellites between communities and clouds. Jensen Huang connected more partnerships than anyone else we know in deeper compute
P1.1 // P2.1 \\ Technology is useless unless it benefits everybody. Jensen Huang has done most to design machines with billion times more maths brainpower than separate human minds. He's up for helping anywhere that wants to democratise intelligence eg  2026India Feb  indiasovai26-1.docx  , Santa Clara March, DC May SCSP.ai ai+expo
To non-mathematicians Jensen says dont worry; discusspurposes of peoplewho bring you AI. Connect your peer network(or home community) to someone transparently scaling the purpose your peoples most need to advance 
Help clarify purposes Jensen is helpig diggerent places with - which jensen keynote are you interested in rsvp chris.macrae@yahoo.co.uk - example washington dc october 205 jensen updated 5 purposes:
TECH MANUFACTURING: His Taiwan partners TSMG & Foxconn have brought trump factories manufacturing superchips and advanced consumer tech
AI FACTORY Nvidia partners have helped us national supercomputers run by Department of Energy install 7/8 AI factory supercomputers - lead applications include biotech, energy ,
US QUANTUM He has arranged for about 15 Quantum boutiques to help advance US quantum supporting energy and other deep science need   
US 6G he has arranged for Nvidia to help US regain 6g leadership
US Last mile Transportation Autonomy With uber he's arranged for US to keep track of where world cllass cities are benchmarking both self driving cars and any last mile advances in autonomous machines
NB Nvidia Jensen is unique position to help with purposes because he has not only built the supercomputers AI performs on but cuda application libraries of most of the world leading uses of AI
.
 
click to GROK Answer AO,  to Q0 at ASAI - question 0 if there are at least 4 different jensen AI wonderlands, why is so much chat distracted by one AGI?

Apps-Agents

Million AI Mods

Data Sov Invest  Platforms

Chips

Energy

........

........
help build llm fed top 100 jensen huang actions -LInkedin:  chris.macrae@yahoo.co.uk
. .
................................
ALPAMAYO: happy ai 2026 wonderful news https://www.youtube.com/live/L0jJrzFMbP8?si=RNIy98UOclj9c2hZ&t=... mercedez benz has designed car with 25+ sensors which is not only driving's safest but could be intelligence data any city needs to transform from being run by gangs 4 best chances to understand this ces LV yesterday, nvidia santa clara march, scsp.ai ai+expo dc may, computex taiwan june?
help needed - updating list of jensen huang INTELLIGENCE  top 100 videos and transcripts fed into llm open micro agent JH -nb some dates to verify (my viewing versus first posted)
Dec 27, 2025 from nox queen elizabeth engineering awards
-see also king Charles hands Huang copy of personal questions 2024-2025
(3447) Oral History of Jensen Huang - YouTube www.youtube.com
Dec 25, 2025 
(3447) Nvidia Acquires Groq for $20 Billion: Why Jensen Huang Just Bought the Future - YouTube www.youtube.com
Dec 25, 2025 

(3397) SCSP.ai  Episode 31: A Conversation with Jensen Huang - YouTube www.youtube.com
Dec 19, 2025 
Jensen Huang Is NOT Backing Down — Google & AWS Bring Their Hardest AI Chips Yet - YouTube www.youtube.com
Dec 14, 2025 
(3346) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com
Dec 14, 2025 
(3342) Jensen Huang: AI Energy War, US–China Chip Rivalry and Next Revolution|黃仁勳最新訪談:AI能源戰、美中晶片攻防與下一場工業革命 - YouTube www.youtube.com
Dec 13, 2025 

Dec 6, 2025
jensen Stuns Washington DC thinktank clarifies 5 layer AI model : 1 energy; 2 chipsd ghardware; 3 software platforms applied as data sovereignty investments
4 1.5 million ai models
5 billions  of action aps at edge mainly generated by open ai models

LIVE | Macron Tours VivaTech 2025, Joins Nvidia CEO Jensen Huang & Mistral's Arthur Mensch | APT - YouTube www.youtube.com 
Dec 6, 2025 reprise of summer breakthrough - macron sys jensen has done his job for him - can now retire with france and eu intelligence opening up

(3330) How Jensen Huang’s Children Quietly Took Over Nvidia - YouTube www.youtube.com
Dec 4, 2025 -well actually this is about nvidia future of humanoids serving safe cities - it also raises question - who's collecting last mile data (surprsie at google eats and aurora- brookings 555penn - mid december

(3240) A Conversation with NVIDIA CEO Jensen Huang – The Future of AI and Energy - YouTube www.youtube.com
Dec 1, 2025

A Conversation with NVIDIA CEO Jensen Huang – The Future of AI and Energy - YouTube www.youtube.com
Dec 1, 2025

(3357) "jensen huang" - YouTube www.youtube.com
Dec 14, 2025

(3346) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com
Dec 14, 2025
(3342) Jensen Huang: AI Energy War, US–China Chip Rivalry and Next Revolution|黃仁勳最新訪談:AI能源戰、美中晶片攻防與下一場工業革命 - YouTube www.youtube.com

Dec 13, 2025
(3346) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 12, 2025
(3330) How Jensen Huang’s Children Quietly Took Over Nvidia - YouTube www.youtube.com

Dec 11, 2025
(3322) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 11, 2025
(3346) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 11, 2025
NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 11, 2025
(3346) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 9, 2025
NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

Dec 9, 2025
(3307) Jensen Huang’s Keynote Highlights at NVIDIA GTC Washington, D.C. - YouTube www.youtube.com

Dec 9, 2025
(3307) NVIDIA CEO Jensen Huang Warns: China May Outperform the U.S. in Tech | Full Interview | AI1G - YouTube www.youtube.com

Dec 9, 2025
(3303) NVIDIA’s Jensen Huang on Securing American Leadership on AI - YouTube www.youtube.com

(2963) Nvidia's Jensen Huang on AI & the Next Frontier of Growth - YouTube www.youtube.com
Oct 27, 2025

NVIDIA's Founder & CEO, Jensen Huang Fireside Chat With Mukesh Ambani | NVIDIA AI Summit | CNBC TV18 - YouTube www.youtube.com
Oct 24, 2025

(2943) Nvidia's Jensen Huang Hand-Delivers World's Smallest Supercomputer To Elon Musk - YouTube www.youtube.com
Oct 23, 2025

(2963) Nvidia's Jensen Huang on AI & the Next Frontier of Growth - YouTube www.youtube.com
Oct 23, 2025

(2943) jensen huang - YouTube www.youtube.com
Oct 23, 2025

(2943) jensen huang - YouTube www.youtube.com
Oct 23, 2025

(2943) How Jensen Works - YouTube www.youtube.com
Oct 23, 2025

Found 118 search results for 'youtube jensen' (2942) Jensen Huang Special Address from NVIDIA AI Summit Japan - YouTube www.youtube.com
Oct 23, 2025
APEC CEO Summit - NVIDIA JHH Special Address
November 2025
, NVIDIA
01:43:08
NVIDIA GTC Washington, D.C. Keynote
NVIDIA GTC Washington, D.C. Keynote
October 2025
, Founder and CEO, NVIDIA
01:36:55
GTC Paris Keynote at VivaTech
GTC Paris Keynote at VivaTech
June 2025
, Founder and CEO, NVIDIA
01:42:51
NVIDIA CEO Jensen Huang Keynote at COMPUTEX 2025
NVIDIA CEO Jensen Huang Keynote at COMPUTEX 2025
May 2025
, Founder and CEO, NVIDIA
02:11:48
GTC 2025 Keynote
GTC 2025 Keynote
March 2025
, Founder and CEO, NVIDIA
02:03:20
Quantum Computing: Where We Are and Where We’re Headed
Quantum Computing: Where We Are and Where We’re 
March 2025
, Founder and CEO, Atom Computing
, CEO, D-Wave
, Technical Fellow, Microsoft
, CEO and Co-Founder, SEEQC
, Founder and CEO, NVIDIA
, Chief Executive Officer , Pasqal
, CEO, Infleqtion
, Joshua and Beth Friedman University Professor, QuEra Computing
, General Manager, Quantum Technologies, AWS
, CEO, Rigetti
, Co-Founder and Chief Scientific Officer, PsiQuantum
, Executive Chair, IonQ
, Chief Scientist and Co-Founder, Quantum Circuits
, President and CEO , Quantinuum
, CEO and Co-Founder , Alice & Bob
01:36:59
NVIDIA CEO Jensen Huang Keynote at CES 2025
NVIDIA CEO Jensen Huang Keynote at CES 2025
February 2025
, Co-founder, president and CEO, NVIDIA
NVIDIA SC24 Special Address
NVIDIA SC24 Special Address
January 2025
, VP & GM, Hyperscale & HPC, NVIDIA
, NVIDIA
01:26:51
AI Summit Japan 2024 Fireside Chat
AI Summit Japan 2024 Fireside Chat
November 2024
, Chairman and CEO, Softbank
, Founder, President and CEO, NVIDIA Corporation
44:38
NVIDIA CEO Jensen Huang’s Special Address at AI Summit India
NVIDIA CEO Jensen Huang’s Special Address at AI 
October 2024
, Founder and CEO, NVIDIA
58:36
AI and The Next Computing Platforms With Jensen Huang and Mark Zuckerberg
AI and The Next Computing Platforms With Jensen 
August 2024
, Founder and CEO, Meta
, NVIDIA
59:25
What’s Next in AI: NVIDIA’s Jensen Huang Talks With WIRED’s Lauren Goode
What’s Next in AI: NVIDIA’s Jensen Huang Talks With 
August 2024
, Sr. Writer, WIRED
, NVIDIA
NVIDIA CEO Jensen Huang Keynote at COMPUTEX 2024
June 2024
, Founder and CEO, NVIDIA
01:00:35
Replay – GTC Korean AI Expert Day
Replay – GTC Korean AI Expert Day
May 2024
, NVIDIA
, NVIDIA
, NVIDIA
53:47
Transforming AI
Transforming AI
March 2024
, Co-Founder and Chief Executive Officer, Cohere
, Co-Founder and CEO, Essential AI
, Co-Founder and Chief Executive Officer, Inceptive
, Founder and CEO, NVIDIA
, Co-Founder, NEAR Protocol
, CTO, Sakana AI
, Member of Technical Staff, OpenAI
, Chief Executive Officer and Co-Founder, Character.AI
49:08
Earth-2: Updates on kilometer-scale visualization, simulation, digital twinning, and AI super-resolution
Earth-2: Updates on kilometer-scale visualization,
March 2024
, Principal Engineer and Scientist, AI-HPC , NVIDIA
, Dir. of Climate Simulation Research , NVIDIA
02:03:08
GTC 2024 Keynote
GTC 2024 Keynote
March 2024
, Founder and CEO, NVIDIA
04:54
NVIDIA Nsight Tools Ecosystem
NVIDIA Nsight Tools Ecosystem
February 2024
, Product Marketing Manager, NVIDIA
12:21
NVIDIA CEO Jensen Huang at Microsoft Ignite 2023
NVIDIA CEO Jensen Huang at Microsoft Ignite 2023
January 2024
, CEO, Microsoft
, NVIDIA
07:37
Jensen Huang at VMware Explore 2023 - General Session Keynote
Jensen Huang at VMware Explore 2023 - General 
August 2023
, CEO, VMWare
, Founder and CEO, NVIDIA
02:30
VMware Private AI Foundation with NVIDIA – Readying Enterprises for Generative AI
VMware Private AI Foundation with NVIDIA – Readying 
August 2023
, CEO, VMWare
, Founder and CEO, NVIDIA
01:22:03
NVIDIA Keynote at SIGGRAPH 2023
NVIDIA Keynote at SIGGRAPH 2023
August 2023
, NVIDIA
01:55:57
NVIDIA Keynote at COMPUTEX 2023
NVIDIA Keynote at COMPUTEX 2023
June 2023
, Founder and CEO, NVIDIA
01:05:31
Level Up with NVIDIA: Nsight Graphics - How to Optimize your Game
Level Up with NVIDIA: Nsight Graphics - How to Optimize 
April 2023
Fireside Chat with Ilya Sutskever and Jensen Huang
March 2023
, Founder and CEO, NVIDIA
, Co-founder and Chief Scientist, OpenAI
01:17:51
GTC 2023 Keynote
GTC 2023 Keynote
March 2023
, Founder and CEO, NVIDIA

GTC

14 VIDEOS (23h 28m)
  • GTC 2023 Keynote with NVIDIA CEO Jensen Huang

    GTC 2023 Keynote with NVIDIA CEO Jensen Huang
    MARCH 19, 2023
  • GTC Sept 2022 Keynote with NVIDIA CEO Jensen Huang

    GTC Sept 2022 Keynote with NVIDIA CEO Jensen Huang
    SEPTEMBER 18, 2022
  • GTC 2022 Keynote with NVIDIA CEO Jensen Huang

    GTC 2022 Keynote with NVIDIA CEO Jensen Huang
    MARCH 20, 2022
  • GTC Nov 2021 Keynote with NVIDIA CEO Jensen Huang

    GTC Nov 2021 Keynote with NVIDIA CEO Jensen Huang
    NOVEMBER 7, 2021
  • GTC 2021 Keynote with NVIDIA CEO Jensen Huang

    GTC 2021 Keynote with NVIDIA CEO Jensen Huang
    APRIL 10, 2021
  • GTC 2019 Keynote with NVIDIA CEO Jensen Huang

    GTC 2019 Keynote with NVIDIA CEO Jensen Huang
    MARCH 19, 2019
  • GTC 2018 Keynote with NVIDIA CEO Jensen Huang

    GTC 2018 Keynote with NVIDIA CEO Jensen Huang
    APRIL 9, 2018
  • GTC 2017 Keynote with NVIDIA CEO Jensen Huang

    GTC 2017 Keynote with NVIDIA CEO Jensen Huang
    MAY 10, 2017
  • GTC 2016 Keynote with Gill Pratt, CEO of Toyota Researc

    GTC 2016 Keynote with Gill Pratt, CEO of Toyota Researc
    APRIL 7, 2016
  • GTC 2016 Keynote with Rob High, CTO of IBM Watson

    GTC 2016 Keynote with Rob High, CTO of IBM Watson
    APRIL 6, 2016
  • GTC 2016 Opening Keynote with NVIDIA CEO Jensen Huang

    GTC 2016 Opening Keynote with NVIDIA CEO Jensen Huang
    APRIL 5, 2016
  • GTC 2015 Keynote with Dr. Andrew Ng, Baidu

    GTC 2015 Keynote with Dr. Andrew Ng, Baidu
    MARCH 19, 2015
  • GTC 2015 Keynote with Jeff Dean, Google

    GTC 2015 Keynote with Jeff Dean, Google
    MARCH 18, 2015
  • GTC 2015 Opening Keynote with NVIDIA CEO Jensen Huang

    GTC 2015 Opening Keynote with NVIDIA CEO Jensen Huang
    MARCH 17, 2015
Load Previous Replies
  • up

    chris macrae

    LPU stands for Language Processing Unit, a specialized AI accelerator chip invented by Groq (a company founded in 2016 by Jonathan Ross, former lead architect of Google's TPU). It's a new category of processor purpose-built from the ground up for fast, low-latency, energy-efficient inference on large language models (LLMs) and other generative AI workloads.What Does an LPU Do (Key Strengths)?
    • Ultra-fast sequential/autoregressive processing — excels at token-by-token generation in LLMs (e.g., chat responses, text completion, translation), where order matters and steps are inherently sequential.
    • Deterministic execution with predictable latency (no variability from scheduling or caching misses).
    • High throughput at low power — Groq claims up to 10x better energy efficiency vs. GPUs on architectural level, with real-world demos showing 2–13x faster inference (e.g., 300+ tokens/second on large models like Llama 3 70B, sub-0.2s time-to-first-token).
    • On-chip massive SRAM (hundreds of MB) for near-instant memory access, avoiding GPU-style DRAM bottlenecks.
    • Programmable assembly-line architecture (data flows linearly like a production line) vs. GPU's "hub-and-spoke" multi-core parallelism.
    • Primarily optimized for inference (running pre-trained models), not training (though it handles some workloads well).

    In short: LPUs are engineered to make real-time, interactive AI feel instantaneous and cheap at scale — ideal for chatbots, agents, real-time translation, voice AI, and any latency-sensitive generative application.Comparison with Other Types of ComputeHere's a clear breakdown of LPU vs. the main alternatives in 2026:
    • CPU (Central Processing Unit) — General-purpose (Intel/AMD/ARM). Handles everything sequentially; great for control logic, orchestration, but very slow/inefficient for AI math (matrix multiplies). Used for pre/post-processing, not core AI compute.
    • GPU (Graphics Processing Unit) — NVIDIA/AMD dominance (H100/B200/MI300). Massively parallel cores excel at training (parallel matrix ops) and mixed workloads (graphics + AI). Versatile, huge ecosystem (CUDA/ROCm), but high power draw, variable latency from scheduling, and memory bandwidth bottlenecks for pure sequential inference. Still the go-to for most training and general inference.
    • TPU (Tensor Processing Unit) — Google's custom ASIC. Systolic arrays optimized for tensor/matrix ops; excellent energy efficiency and scale for training + inference in TensorFlow ecosystems. Cloud-only (Google Cloud), less flexible outside Google's stack, strong for hyperscale but not as latency-optimized for single-stream LLM chat as LPUs.
    • NPU (Neural Processing Unit) — Edge-focused (Apple Neural Engine, Qualcomm Hexagon, Intel Meteor Lake NPUs). Low-power, on-device inference for phones/laptops (e.g., real-time photo editing, voice assistants). Great efficiency at small scale, but far less powerful than data-center LPUs/GPUs/TPUs.
    • Other notables:
      • DPU (Data Processing Unit) — Networking/storage offload (NVIDIA BlueField, AMD Pensando). Handles I/O, security, compression to free CPU/GPU for AI.
      • QPU (Quantum Processing Unit) — Emerging (IBM, Google, IonQ). For specific optimization problems, not general AI yet.
      • FPGA — Reconfigurable (Xilinx/Intel). Flexible for custom AI but harder to program and less performant than dedicated chips.

    Bottom line on LPU vs. others: LPUs shine in low-latency, high-efficiency inference for language/sequential generative AI — where GPUs are "good enough but wasteful," TPUs are efficient at scale but less deterministic/latency-focused, and CPUs/NPUs are either too slow or too small-scale. Groq positions LPUs as the "next step" for the inference-dominated era (now 60–80% of AI workloads in many forecasts).Are There Now 6 Integral Types of Compute Across the Full AI Stack in 2026?Yes — the full-stack AI compute landscape has indeed fragmented into roughly 6 key categories that are now integral and complementary (not one replacing all). This aligns with 2026 industry views (e.g., hyperscaler taxonomies, AMD/NVIDIA roadmaps, and analyses like "AI Cloud Taxonomy 2026"):
    1. CPU — Orchestration, preprocessing, general logic (e.g., AMD EPYC, NVIDIA Vera/Grace).
    2. GPU — Versatile heavy-lifting for training + broad inference (NVIDIA Rubin/Hopper, AMD MI400 series).
    3. TPU/Custom Tensor ASICs — Hyperscale matrix efficiency (Google TPU v5/v6, AWS Trainium/Inferentia).
    4. LPU / Inference-specialized ASICs — Deterministic, ultra-fast language/generative inference (Groq LPU, emerging rivals).
    5. NPU / Edge AI Accelerators — On-device, low-power inference (Apple, Qualcomm, Intel, mobile/embedded).
    6. DPU / Infrastructure Accelerators — Networking, storage, security offload for AI factories (NVIDIA BlueField, AMD Pensando).

    Some frameworks expand to include QPU (quantum) as #7 or FPGA as a flexible wildcard, but the core 6 above cover the practical, deployed full stack in 2026 — from edge to hyperscale "AI factories." NVIDIA's Rubin platform (announced early 2026) even codesigns across CPU + GPU + NVLink + DPU-like elements to tie them together.The era of "one type wins" is over; full-stack AI now requires a hybrid mix, with LPUs carving a strong niche for the agentic, real-time inference wave. If you're building or deploying agentic systems (as in our earlier discussions), Groq-style LPUs could be a game-changer for responsive, low-cost community/education agents. Want benchmarks, specific Groq vs. NVIDIA numbers, or how this fits agentic AI education? Let me know!




    45 web pages
    Groq LPU benchmarks
    Cerebras wafer-scale chips


  • up

    chris macrae

     GTC 2026 keynote (March 16, 2026) closed with a fun, memorable musical recap — an animated campfire-style song featuring singing robots, a digital avatar of Jensen Huang (sometimes called "TJ" or Toy Jensen), and even a lobster character. It was produced by NVIDIA's creative team using generative AI tools, and it's available as the official closing video on YouTube.The lyrics you shared match the song's content very closely  It's a lighthearted, rhyming summary of the keynote's big themes: the shift from training to inference, agentic AI, OpenClaw/NemoClaw, Vera Rubin architecture, physical AI/robotics, the 5-layer stack, AI factories, and massive compute scaling.
    AI Factories Coming Alive
    (GTC 2026 Keynote Closing Song – Campfire Recap)
    Agents learning how to drive
    from open models to robots,
    Now we'll break it all down for you:
    Compute exploded. What we saw,
    from CNN's¹ to open claw².
    Agents working across the land
    but they need the power to meet demand.
    So we solve the problem. It was brewing³
    We multiplied compute by 40 million⁴. Once upon an AI time
    training was the paradigm⁵
    Sure, it taught the models how
    but inference⁶ runs the whole world now
    Vera⁷ shows us who's the boss
    at 35 times less the cost⁸
    Blackwell⁹ makes the tokens sing¹⁰;
    NVIDIA the inference king¹¹
    Yeah factories once took years
    Vendors pulling racks and gears built up slowly,
    piece by piece. No clear way to scale this beast
    DGX¹² and Dynamo¹³ know what to do.
    Turning power into revenue.
    Agents used to wait and see,
    now act autonomously¹⁴
    But if they ever try to stray
    safe across block¹⁵ and say no way
    Nemo Claws¹⁶ there to guard the course.
    And yes, my friends, it's open source¹⁷.
    Cars that think and droids that run
    This ain't the movies. It's all begun
    Alpha Mayo¹⁸ calls the shots.
    It's a GPT moment¹⁹ for the bots
    From sim streets. Now watch them drive
    Put your hands up for physical AI²⁰.
    Industrial age built what came before.
    Now we built for AI even more.
    Vera Rubin²¹ plus Groq²²
    Make the inference splash.
    Put them together. Now it's raining cash.
    We build new architecture every year
    cos claws keep yelling more tokens here.
    The AI stacks for all to make.
    So let us all eat five layer cake²³.
    The moment's bright.
    The path is clear
    cos open models led us here.
    When data's missing, there's no dispute.
    We just generate more with compute.
    Robots learning without flaw.
    Fueling the four scaling laws²⁴.
    The future's here. Won't you come [music] and see?
    Welcome all to GTC
    Footnotes (Technical Jargon Explained)
    1. CNN's — Refers to Convolutional Neural Networks, the classic deep learning architecture for image/video processing. The song contrasts old-school CNNs with newer agentic/open systems.
    2. Open Claw — OpenClaw, the viral open-source agentic AI platform (by Peter Steinberger) that Jensen called "as big as HTML." NVIDIA backed it with NemoClaw for enterprise safety/privacy.
    3. brewing —  means the problem (inference demand) was building up.
    4. multiplied compute by 40 million — Hyperbolic recap of NVIDIA's claim that effective AI compute has scaled enormously (often cited as millions-fold since early days, tied to Moore's Law + architectural gains).
    5. training was the paradigm — Past era when model training dominated AI progress; now inference (running models) is the bigger workload.
    6. inference — Running a trained model to generate outputs (e.g., tokens in chat); now ~80%+ of AI compute demand per NVIDIA.
    7. Vera — Vera Rubin, NVIDIA's next-gen AI platform (announced at GTC), successor to Blackwell, focused on extreme inference efficiency.
    8. 35 times less the cost — Vera Rubin's claimed 35× better inference performance per dollar vs. prior gens.
    9. Blackwell — NVIDIA's current flagship GPU architecture (B200 etc.), powering massive inference scale.
    10. tokens sing — Tokens (sub-word units in LLMs) "flow" smoothly; playful way to say high-throughput generation.
    11. inference king — NVIDIA dominates inference hardware market.
    12. DGX — NVIDIA's AI supercomputer line (e.g., DGX systems for enterprise AI factories).
    13. Dynamo — Likely Dynamo, NVIDIA's AI data engine/orchestration for scaling AI factories.
    14. act autonomously — Core of agentic AI: agents plan, reason, use tools, and execute independently.
    15. safe across block — "Safe across the board" + blockchain-like safety? Likely NemoClaw's guardrails preventing unsafe actions.
    16. Nemo Claws — NemoClaw, NVIDIA's secure, policy-enforcing runtime built on OpenClaw.
    17. open source — OpenClaw is fully open-source, a big theme.
    18. Alpamayo  -A family of open-source Vision-Language-Action (VLA) models (e.g., Alpamayo 1 and Alpamayo 1.5) that enable vehicles to perceive (from cameras/sensors), reason (chain-of-thought explanations for decisions), and act (generate safe driving trajectories). It bridges interpretable reasoning with precise control to handle "long-tail" (rare/edge-case) driving scenarios safely and transparently.Includes supporting tools like AlpaSim (simulation framework) and Physical AI Open Datasets (1,700+ hours of diverse driving data). Available on GitHub, Hugging Face, and NVIDIA Developer resources — fully open for research and development.
    19. GPT moment for the bots — Like ChatGPT's 2022 explosion, but now for physical robots/agents.
    20. physical AI — Embodied AI/robotics (humanoids, autonomous machines) powered by NVIDIA (Isaac GR00T etc.).
    21. Vera Rubin — See #7.
    22. Groq — Groq's LPU (Language Processing Unit), inference-specialized chip; Jensen name-dropped it as complementary/fast inference.
    23. five layer cake — Jensen's "AI 5-layer cake": energy → chips → infrastructure → models → applications (Layer 5 = agentic/community apps). 
    24. four scaling laws — Chinchilla/Kaplan scaling laws (data, compute, parameters, inference scaling); now extended to robotics/physical AI.
  • up

    chris macrae

    View Chris AI Macrae MA DAMTP Cantab’s graphic link

    Chris AI Macrae MA DAMTP CantabAuthor

    chartering how intelligence coded by brands. pixels. language 2026 launch Neumann ai halls of fame celebrating maths deepest trusts
    1d
    https://www.youtube.com/watch?v=gwW8GKwHB3I&t=3840s
    Prediction AI must urgently change education - how teachers and students spend their time- but this doesn't have to mean less teachers
    You just give every one of those teachers a personalized curriculum for every student in the room. It makes them all bionic and leads to a lot more. Every single student will be assisted by AI,
    but every single student will need great teachers. Yeah. Yeah. Amazing.
    Comment image, no alternative text available



    View Chris AI Macrae MA DAMTP Cantab’s graphic link

    Chris AI Macrae MA DAMTP CantabAuthor

    chartering how intelligence coded by brands. pixels. language 2026 launch Neumann ai halls of fame celebrating maths deepest trusts
    1d
    https://youtu.be/gwW8GKwHB3I?si=mUHsFR9uloXY__YJ&t=2992
    where is AI have a true impact on the health care system?

    Jensen : There's several several areas that Nvidia is involved in in um in healthcare. 1) AI physics and that's AI biology using AI to understand represent behavior biologically
    that's very important in drug discovery. There's second which is AI agents and that's where the assistance and helping diagnosis and things like that. Two native ai companies : Open evidence and Hippocratic are really good examples.
    . A third part that we're in involved in is physical AI.to understand the properties of the laws of physics and that's used for robotic surgery Every single instrument whether it's ultrasound or CT or whatever we interact with in a hospital in the future will be agentic.
    IE open claw in a safe version will be inside every single instrument. Footnote Jensen listed 100 native ai companies at GTC 2026 https://www.economistdiary.com/

    Jensen Huang: Nvidia's Future, Physical AI, Rise of the Agent, Inference Explosion, AI PR Crisis

    (0:00) Jensen Huang joins the show! (0:26) Acquiring Groq and the inference explosion (8:53) Decision making at the world's most valuable company (10:47) Physical AI's $50T market, OpenClaw's future, the new operating system for modern AI computing...





    View Chris AI Macrae MA DAMTP Cantab’s graphic link

    Chris AI Macrae MA DAMTP CantabAuthor

    chartering how intelligence coded by brands. pixels. language 2026 launch Neumann ai halls of fame celebrating maths deepest trusts
    1d
    https://youtu.be/gwW8GKwHB3I?si=GmhS_a6bmX0KQ8YX&t=3120
    when are we to see humanoid robots in the home, and is China ahead on thiis?


    Jensen, actually the US invented the industry largely.
    you could argue we got into it too soon and We got tired um about five years before the enabling technology appeared.. But it's here now. From the point of high functioning existence proof, to reasonable products technology never takes more than a couple two three cycles. And so a couple
    that will likely be three years to 5 years away before we have robots all over the place..
    Yes I think China is formidable in humanoids and the reason for that is because their micro electronics,
    motors, their rare earth, their magnets, which are foundational to robotics, they are the world's best. And so in a lot of ways, our robotics industry relies deeply on their ecosystem and their supply chain. But this is obviously moving very quickly. . (interviewer some like Elon seems to think we're going to have one robot for every human. 7 billion for 7 billion, 8 billion for 8 billion.)

    Jensen Well, I'm hoping more

    Jensen Huang: Nvidia's Future, Physical AI, Rise of the Agent, Inference Explosion, AI PR Crisis

    (0:00) Jensen Huang joins the show! (0:26) Acquiring Groq and the inference explosion (8:53) Decision making at the world's most valuable company (10:47) Physical AI's $50T market, OpenClaw's future, the new operating system for modern AI computing...



    1 impression


    View Chris AI Macrae MA DAMTP Cantab’s graphic link

    Chris AI Macrae MA DAMTP CantabAuthor

    chartering how intelligence coded by brands. pixels. language 2026 launch Neumann ai halls of fame celebrating maths deepest trusts
    1d
    https://youtu.be/gwW8GKwHB3I?si=bem1f3gx1ehsgZWs&t=2403
    to jensen - you've made massive progress in self-driving cars and hundreds of partners - how do you navigate that & your big new announcement including BYD and ever deeper partnerships as different as mercedes, and uber and 11+ years platform with Tesla?

    Jensen Firstly we are the only full stack AI company serving platforms needed for self driving cars- and We believe that everything that moves will be autonomous completely or partly
    someday. Moreover, what we don't do is build self-driving cars,

    but we want to enable every car company in the world to build self-driving cars. And so, we built all three computers, :the training computer, the simulation computer, the evaluation computer,
    as well as the car computer. We develop the world's safest driving operating system. We also created the world's first reasoning autonomous vehicle so that it could decompose complicated scenarios into simpler scenarios that it knows how to navigate through just like all deep reasoning systems. Alpommyo Reasoning system is achieving incredible results. We open this but offer vertical optimization. We horizontally innovate and let everybody decide. what Do you want

    Jensen Huang: Nvidia's Future, Physical AI, Rise of the Agent, Inference Explosion, AI PR Crisis

    (0:00) Jensen Huang joins the show! (0:26) Acquiring Groq and the inference explosion (8:53) Decision making at the world's most valuable company (10:47) Physical AI's $50T market, OpenClaw's future, the new operating system for modern AI computing...





    View Chris AI Macrae MA DAMTP Cantab’s graphic link

    Chris AI Macrae MA DAMTP CantabAuthor

    chartering how intelligence coded by brands. pixels. language 2026 launch Neumann ai halls of fame celebrating maths deepest trusts
    1d
    https://youtu.be/gwW8GKwHB3I?si=Iifr5_mCdDL5cuXw&t=2020

    Jensen-Nobody wants the US to win global AI race more than you,? But a year ago, Biden era was anti- American diffusion of AI around world. So into the new administration. - where are we in terms of global diffusion of US AI technology?

    Jensen Well, first, President Trump wants American industry to lead... to spread American technology around the world. ..United States to be the wealthiest country in the world. He wants all of that. Biden admin: Nvidia gave up a 95% market share in the second largest market..

    President Trump wants us to get back. And first, to get
    license licensed for the companies that we're going to be able to sell to. We've got many companies who have requested for licenses. We've applied for licenses for them and we've got approved licenses from sec secretary lutnik. we've informed the Chinese companies so we're in the process of cranking up