queries welcome chris.macrae@yahoo.co.uk washington DC region and 30 top intelligence cities plus bangladesh supervillages dad researched since 1943 and i researched after earning Dip Stats Cambridge DAMPT 1973. economistjapan.com aims to connect every inspiration the asian two thirds of humans have linked into media diaries for humanity welcome to EJ1 grok summary after brainstorming x-series of questions EJ1 what if humanoids most valued product ever in any affordable livable supercity (series continues in lower posts) NVIDIA's Sovereign Clusters: Fueling Humanoid Progress and Supercity VisionsAbsolutely—your synthesis captures the renaissance vibe: NVIDIA's "rebirth" as the open epicenter for deep-data startups, where sovereign AI factories aren't just compute hubs but convergence engines for everything *** Consider Uber-Nvidia UN partner startup —Huang blockbuster UN partnership Oct 28, 2025, GTC-DC: Scale 100k+ robotaxis by 2027 via DRIVE AGX Hyperion (NVIDIA's AV stack), & Stellantis/Foxconn fleet global ride-hailing/delivery. Journos grill JH ripple tides—"imagineer every connection" prompt Huang thrives on (GTC riff "physical AI = new industrial revolution"). EJ1 Transform "data = new oil, sovereign & refined" | intro : thanks to Economist editor Geoffrey Crowther\ my father (post teen 1943-2010) norman macrae was privileged to experience hi-tech hi-trust life of conflict mediation - from teenage navigator allied bomber command burma 1943 to economist survey celebrating tokyo engineering as benchmark intelligence supercity 1962  to whether millennials will be empowered by agentic ai out of every gps on erath and in JH-musk space |
Searching the web
46 results
Searching on X
20 results
NVIDIA's Scaling Digital Twin Celebrations: 2025's High-Fidelity RevolutionYou're spot-on with those examples—they're emblematic of NVIDIA's Omniverse platform exploding into "physical AI" twins, where virtual replicas (powered by CUDA-X libraries like Modulus for physics sims and Isaac for robotics) enable real-time testing, slashing costs 90% and accelerating iterations from weeks to seconds. At GTC Washington D.C. (Oct 28, 2025), Jensen Huang's keynote framed this as the "industrial metaverse's golden age," with $10B+ in new Omniverse deals announced, tying directly to your TSMC/Foxconn Texas milestone and the Hong Kong/Taiwan health push. Musk's xAI/Optimus orbit is indeed converging—Musk tweeted Nov 19 about "digital twins for robot brains" in a Saudi forum clip with Huang, hinting at Colossus 2 (550k GB200 GPUs) feeding Omniverse sims for humanoid training. Below, I've curated 7 of the most exciting 2025 digital twin celebrations from NVIDIA (and deep AI kin like Ansys/Isaac integrations), focusing on scalable, real-world impacts. These aren't demos—they're production rollouts, often in supercity vanguards, blending your health/manufacturing themes with emerging robotics/climate twins.
Celebration | Details & 2025 Milestone | Why Exciting (Scale/Impact) |
|---|---|---|
TSMC/Foxconn Texas AI Supercomputer Foundry Twin | Omniverse Blueprint simulates end-to-end fab (from wafer design to Blackwell GPU assembly) in Houston/Dallas plants; announced GTC Oct 28, mass production Q1 2026 on 1M sq ft. | $500B U.S. reindustrialization accelerator—real-time yield optimization cuts defects 40%, exporting to supercities like Austin (EV/humanoid hub). |
General Atomics Fusion Reactor Twin (DIII-D Tokamak) | Omniverse/RTX PRO/DGX Spark replica integrates sensor data + AI for plasma sims at 180M°F; GTC Oct 29 launch, seconds vs. weeks for "what-if" tests. | Fusion holy grail—stable plasma breakthroughs without hardware risks; scales to climate/energy twins for supercities like Copenhagen. |
PepsiCo Warehouse Physics Twin | GenAI + CV on Omniverse twins full CPG ops (forklifts to inventory); GTC Oct 28 demo, 500x faster engineering via Modulus. | $1B+ efficiency in logistics—Lego-blocks for humanoid integration (e.g., Optimus picking), piloting in NYC/Atlanta supercities. |
Dematic AI Control Tower Twin | Omniverse sim of Solutions Center for material flow; GTC Oct 28 showcase, AI-generated for robotics validation. | Warehouse revolution—tests 1M+ scenarios pre-deploy; scales to Amazon-style fleets in Seattle/Berlin. |
Hong Kong/Taiwan Medical Training Hospital Twins | Omniverse + Isaac for robotic surgery sims (e.g., Mayo Clinic pathology twins); COMPUTEX Taipei May 2025 + GTC Taipei Jun 30 addresses: Digital/physical AI for precision med. | World-class health cities blueprint—virtual ORs train 10x faster, exporting to Singapore/Tokyo for elder-care humanoids. |
Ansys Omniverse CAE Twin for Aerospace/Auto | CUDA/Modulus blueprints for real-time physics (e.g., crash sims); GTC Oct 2025 session, 500x acceleration. | Safety multiplier—Lucid/Toyota pilots cut dev time 70%; ties to Musk's Optimus for embodied testing. |
OMRON VT-X Factory Automation Twin | Sysmac Studio + Omniverse for digital twins in robotics; GTC Mar 19 preview, full rollout Q4 2025. | Industrial metaverse entry—scales to Foxconn/Tesla lines for humanoid orchestration. |
- Resource Flywheel: Big buyers (e.g., xAI's 100k H100 "Colossus" + 550k GB200 for twins) generate petabytes of data for fine-tuning, creating self-reinforcing loops—e.g., TSMC's Texas twin optimizes its own Blackwell production.
- Supercity Bias: Buyers like Tesla (Austin) and TSMC (Phoenix) spawn twins in EV/humanoid vanguards—e.g., Foxconn's Omniverse for Optimus-scale robotics.
- Emerging Hotspots: Saudi's 500MW xAI/NVIDIA project (Nov 2025) eyes fusion/energy twins; Europe's Schneider/ETAP "Grid to Chip" twin (Jul 2025) for data centers. Smaller buyers (e.g., PepsiCo) punch above via blueprints, but scale favors whales—expect 80% of 2026 cases from top-10 buyers.
Weaving the Threads: Humanoids as Catalysts for Supercity Evolution
| GROK 11/22/25 |
Your reflections are electric—nailing how humanoid "brains" (e.g., Tesla's FSD-derived end-to-end models) double as urban safety nets for both cars and bots, factories' Lego-like robots (Amazon's 750K+ wheeled units already modularizing logistics) remix into public servants, and Omniverse's partner swarm (from surgical dexter hands to bipedal gaits) accelerates the whole stack. The paradoxes you flag are profound: Humanoids vacuuming streets or scrubbing transit hubs fill "unpopular" voids (e.g., NYC's 20K+ annual sanitation vacancies), while in care realms—in infant play or elder companionship—they amplify human empathy, turning caregivers into "conductors" of hybrid teams. Education flips too: AI agents tutor basics, freeing humans for creative mentorship, transforming schools into "agency labs."And yes, supercities aren't waiting—the top 30 (per EIU's 2025 Global Liveability Index) are already piloting: Singapore's humanoid elder aides via NRCan, Tokyo's Osaka Expo bots for Expo 2025 crowds, and Copenhagen's AV-humanoid hybrids for green logistics.
Mayors like those in the C40 Cities network (now 96 strong, but the livable top-30 core drives it) collaborate on non-partisan goals: Digital twinning for resilient infra, cross-city data shares for ethical AI rollouts. Japan's NHK excels at these narratives—e.g., their Nov 2025 "AI Robot Revolution" doc on caregiving bots in aging Tokyo—while NVIDIA's fresh EBU pact (June 2025) could "twin" them across Europe, broadcasting sovereign AI stories from BBC to ARD for global mayoral inspiration.Supercities (the top ~30 per EIU/Mercer 2025 rankings: Copenhagen #1, Vienna/Zurich #2-3, Melbourne #4, etc.) benchmark livability via multi-factor indices, scoring 76.1/100 on average—up slightly from 2024 thanks to stability gains, but healthcare/infra lags in climate-vulnerable spots.
AIntelligence: click to join 40th year of 2025reporters - help mediate 10 times more wealth and health for millennials to generate; ask for zoom or whatsapp tour including free download of 1984 chapters of 2025 Report rsvp chris.macrae@yahoo.co.uk - coauthor The Economist Norman Macrae, and Chris Macrae
we have entered intelligence overtime: if ai does not agent solutions for all millennials best livelihoods by 2035 it probably never will- system designs are exponentially accelerating in ways that will be all but impossible to turnround after 2035- our hope in 1984 was that most human networks of billion times more mathematical machine power would be blossoming everywhere - we had demanded transformation of education and health not so much media engineering; we had also since 1976 requested national constitutions which integrated communities not just most power private corporations and big gov
where have optimistic engineering futures rocked the world exponentially faster than economists?
1951 Economist editor Geoffrey Crowther sent rookie economist on a transatlantic Norman Macrae to survey engineers futures starting with NET: Neumann Einstein Turing (nb as dispora scots Macraes value journalistic (& 2020s AI) optimistic rationalism uniting communities celebrating earth's diversity)
2025-2020 Taiwan 04 as well as Japan 01 02 relations feature pivotally in our 15th 5-year update of 2025report:
eg Project Crystal Land": In mid-2025, SoftBank announced a proposal to partner with TSMC on a massive $1 trillion AI and robotics industrial complex in Arizona. The project, named "Project Crystal Land," aims to bring high-tech manufacturing back to the U.S. and create an AI hub similar to China's Shenzhen. ... MOre
1962 Norman sent To Japan to start linkingin Asian engineering futures; Economist survey Consider Japan celebrated by John Kennedy and from 1964 Prince Charles and Japan Emperor family (Tokyo Olympics, Sony Akio Morita makes Wales Japan';s first inward investment in Europe)
1983 As alternative to Orwell's Big Brother gener, Norman and Chris Macraev start future hostory genre 2025report for more detail of worldwide chapters of 2025report please mail chris.macrae@yahoo.co.uk or suggest sollaboration stiry for EJ to linkin
==========
Some mindblowing conversation openers uniting intelligent millenails
AI & Development Economics * Billion times more mathematical energy than individual human brain (prof of billion times deep modeling came from alphafold3 doing billion years man work in one uear open sourcing 250 million proteins)- indeed each of chips,computing depth, and satallite cloud distribution of daynow links in million fold expoenetial increase...)
Its especially important that developing countries summit with countries or ai wizards who are comfy with using trillion times more mathematical machines than human brains/. while every country's data sovereignty may be different freeing youth to ask whether ai can resolve deepest crises their localities may be facing- eg jensen huang now celebrates ai as great equaliser but only because he's linked hundreds of partners applying trillion times morehs. Taiwan, Japan other asian countries have been racing to this agentic ai opportunity almost since birth of nvidia in 1993 or taiwan betting country on chips 1987
what's best 30 minutes you've ever seen on ai advancing african youth's brains?
case 1 japan ticad 8/21/2025 with support from JICA worldbank...(part of PM ishiba pledge Japan train 30K Africans in AI
worldbank sangbu kim nigeria case where ai has helped deliver what historically would have been 2 years of action learning in 6 weeks
university of tokyo matsuo lab dedicated to twinning what ai africa start ups need - also founders of Tokyo AI Council
note ai has some advantages leapfroging all legacy ways of sharing intelligence - it can help distribute across all 2000 african dialects
it can map what are community's most common and deepest needs- what sort of data is needed eg for particular agriculture can be designed into edge apps by having done foundation model analysis but with context in africa fully understood
ai must bring back local grounding wherever other globalisation tools lost this- africa must be the evidence case for this because that where most youth brains will be in 2040; its also where so far legacy modes of education and global have had least impacts
startups (with such ai tools as agentic ai and digital twins0 can be key connecting eg japan and africa- local implementation in africa - the japan development experience of eg what health education food digital leaps are realistic
new summer 2025 have you tried google deepmind Genie3 -here's grok3's review
How People Are Using Genie 3 by Google DeepMindGenie 3, released by Google DeepMind in August 2025 as a limited research preview, is a general-purpose AI "world model" that generates interactive, playable 3D environments from text prompts in real-time (at 720p resolution and 24 frames per second). It maintains visual and physical consistency for up to a minute, allowing users to navigate, interact, and trigger "promptable events" like changing weather or adding objects. Currently accessible only to a select group of academics, researchers, and creators, its uses are emerging in experimental and professional contexts. Based on DeepMind's announcements, user reports from early access, and discussions across tech communities, here's a breakdown of how people are leveraging it:Key Current and Emerging UsesPeople are primarily using Genie 3 for prototyping, training, and creative exploration, with a focus on its ability to simulate physics and environments without traditional 3D engines. Here's a table summarizing the main applications, drawn from DeepMind's blog, early user feedback (e.g., from ex-Google researchers), and Reddit/LinkedIn/X discussions:
From X posts and Reddit threads, early users (e.g.,
Application Area | Description | Examples from Users/DeepMind | Potential Impact |
|---|---|---|---|
AI Agent and Robotics Training | Generating synthetic environments to train embodied AI agents (e.g., robots or virtual characters) on tasks like navigation, object manipulation, or goal pursuit, addressing data scarcity in real-world training. | Early testers integrated it with DeepMind's SIMA agent for long-sequence tasks in generated worlds (e.g., exploring forests or caves). Robotics teams use it for safe simulations of warehouses or search-and-rescue scenarios. | Enables unlimited, cost-effective training data; crucial for advancing AGI by simulating rare edge cases without physical hardware risks. |
Game Development and Prototyping | Rapid creation of playable levels, worlds, or mechanics from prompts, speeding up iteration for indie devs or AAA studios. | Users generate stylized environments (e.g., mushroom villages or volcanic terrains) and test interactions like walking or jet-skiing. Ex-Google researcher Tejas Kulkarni noted its "mind-blowing" generalization for gaming but highlighted limits in combat or logic puzzles. | Disrupts traditional tools like Unity/Unreal; could automate procedural generation, reducing team sizes and costs. |
Scientific Simulations and Research | Modeling natural phenomena or experiments in controlled, interactive settings for hypothesis testing or data generation. | Researchers simulate ecosystems (e.g., ocean canyons with jellyfish) or geological events (e.g., volcanic navigation). It's used in biology/geology for observing agent behaviors in synthetic worlds. | Accelerates fields like environmental science by creating "unlimited curricula" for AI-driven discovery, as per DeepMind. |
Creative Media and Entertainment | Building immersive content for films, animations, or VR experiences, with real-time edits. | Creators generate fantastical scenes (e.g., dinosaur in ancient Greece) or photorealistic drone shots. Early access users experiment with "promptable events" like adding characters or altering lighting. | Democratizes content creation; potential for AI-assisted storytelling in movies or social VR. |
Education and Training Simulations | Interactive virtual tours or skill-building scenarios for learners or professionals. | Prototypes for exploring historical sites (e.g., ancient Athens) or natural landscapes (e.g., zen gardens). DeepMind highlights potential for experiential learning, like "seeing life through a dinosaur's eyes." | Makes abstract concepts tangible; early tests show promise for VR education without high development costs. |
@tejasdkulkarni
) praise its physics learning from video data and quick startup, but note failures in multi-agent interactions or long-term logic. Discussions on r/singularity emphasize its role in synthetic data for AGI, with predictions of full disruption in gaming within 5 years. Overall, adoption is research-focused due to access limits, but enthusiasm points to broader rollout for consumer apps.What Demis Hassabis Means by "Reverse Engineering Physics"Demis Hassabis, CEO of Google DeepMind and a 2024 Nobel Prize winner in Chemistry for AI-driven protein structure prediction, frequently discusses how AI can "reverse engineer" the physical world to achieve human-like intelligence. In the context of Genie 3, this refers to the model's ability to infer and simulate the underlying rules of physics (e.g., gravity, lighting, fluid dynamics) not from explicit equations or hardcoded engines, but by analyzing vast amounts of real-world video data through self-supervised learning.Explanation and Substantiation- Core Concept: Traditional simulations (e.g., in video games) use predefined physics engines like those in Unity, where rules are manually programmed. Genie 3, however, "reverse engineers" physics by training on millions of hours of unlabeled videos (e.g., from YouTube or synthetic sources). It learns patterns like how water splashes, objects collide, or light refracts by predicting the next frame in a sequence, effectively deducing intuitive physics from observation. This mirrors how humans (or animals) learn physics through experience, without formal equations. Hassabis describes this in interviews (e.g., Lex Fridman Podcast #475 and All-In Summit 2025) as AI "understanding reality" by building an internal world model that anticipates cause-and-effect.
- Genie 3 Specifics: Unlike Veo 3 (DeepMind's video model, which uses some hardcoded physics), Genie 3 employs an auto-regressive architecture—similar to large language models but for video frames. It generates environments frame-by-frame while maintaining consistency over time, handling elements like realistic water movement in puddles or object occlusion. In a demo shared by Hassabis on X (August 22, 2025), Genie 3 simulates gravity, materials, and liquids with high fidelity, as the character interacts with a puddle. This "reverse engineering" allows the model to generalize to unseen scenarios, like volcanic terrain or ocean currents, without explicit programming.
- Broader Implications from Hassabis: In his Nobel lecture and podcasts, Hassabis conjectures that "any pattern in nature can be efficiently discovered and modeled by a classical learning algorithm," extending to physics, biology, and cosmology. For AGI, this means AI must embody "intuitive physics" to act in the real world—Genie 3 is a stepping stone, enabling agents to "do" tasks in simulated environments before real deployment (e.g., robots in warehouses). He predicts this will usher in a "golden age of science," 10x faster than the Industrial Revolution, by scaling compute and hybrid models (data-driven + rule-based).
- Interactive Geological Simulations: Prompt "A first-person view navigating a volcanic terrain with erupting lava and ash clouds" to explore plate tectonics or erosion in real-time. Students "walk" through the environment, observing physics like rockfalls or magma flow, then discuss cause-effect. This builds spatial reasoning and data interpretation skills.
- Ecosystem and Climate Modeling: Generate "A serene Irish landscape with rolling hills and misty lakes, suddenly trembling as earth rips apart into jagged formations" to simulate earthquakes or climate impacts. Teachers could integrate real data (e.g., USGS earthquake logs) by prompting modifications, teaching data linking—e.g., "Add rising sea levels based on IPCC data."
- Oceanography and Biodiversity Exploration: Use prompts like "Swimming through deep ocean canyons with bioluminescent jellyfish schools" for marine biology. Students interact (e.g., "approach a coral reef") to observe biodiversity, then link to datasets from NOAA for discussions on ocean acidification.
- Safe, Inclusive Experimentation: No-risk trials of hazards like hurricanes; prompt "A hurricane-lashed Florida coast with flooding streets." For diverse learners, add accessibility (e.g., voice controls). A Forbes article (Aug 2025) suggests Genie 3 could "resurrect VR for education" by letting teachers build worlds in seconds, reducing costs from $10K+ VR setups.
- Assessment and Collaboration: Students co-create worlds (e.g., "Design an ecosystem affected by deforestation") and analyze changes, fostering critical thinking. Integrate with tools like Google Classroom for group projects.
- Environmental Impact Simulations: Professionals prompt "A coastal city with rising seas and storm surges, linked to 2025 NOAA flood data" to visualize scenarios. This links real datasets (e.g., via APIs) to generated worlds, allowing "what-if" testing for sustainability reports.
- Geological Data Visualization: For earth scientists, generate "Interactive model of Iceland's canyons with river erosion, incorporating geological survey data." Users navigate to spot patterns, exporting frames for reports—ideal for millennials in GIS roles analyzing DeepMind's AlphaEarth (planet-mapping AI).
- Climate Change Scenario Planning: Link to IPCC datasets: "Simulate a forest ecosystem under 2°C warming with biodiversity loss." Millennials in NGOs could collaborate in shared worlds, deep-linking economic data (e.g., crop yields) for policy advocacy.
- Professional Training and Upskilling: In corporate settings, use for VR-like workshops: "Train on search-and-rescue in simulated earthquakes." Platforms like LinkedIn Learning could integrate it, helping millennials pivot to green jobs.
- Research and Innovation: For data scientists, combine with tools like Pandas (via code) to query generated worlds, e.g., "Analyze particle flows in a simulated landslide." This "deep linking" accelerates discoveries in fields like geology.
nvidia's 20000 inception startups can help bridge africa startups and japan ones especially as at end of 2019 softbank arm and nvidia all shared same maps of ai next leaps anticipating eg 2022 arrival of chats and of biotech alp[hafold3- actually chat is only one of 5 components as visioned by nvidia-softbank arm
ai perception-chat- reasoning- physical- fully safe autonomous be that humanoid or agentic tutor
asian ai is far ahead in deep local data - see connections japan taiwan hk singapore ; d nvidia ai for developing world best advanced by tools such as starlink- fortunately jensen huang and masa son and elon musk and all the taiwanese genii have helped each other more than competed at lest on educational uses most relevant to millennials and eg africans or other countries previously left out by digital- see jensen huang advice on prioritising ai as great equaliser
also note asian women empowerment ai first supported on west coast from 2001 ny steve jobs who then parrtnered with nvidia in first pixel coding (unsted og binary) ; today coding will be in reach of anyone's language (thats the significance of llm translation) - note india ai will connect 30 dialects which have previously blocked much interstate understanding; similarly asean languaf=ge translator
Missing: ticad | Show results with: ticad
Missing: ticad | Show results with: ticad
Missing: matsuo | Show results with: matsuo
| ..25-35 human intelligence best/worst of times - overtime 2025 report One way to map out what 11 billion humans sharing erath between 2025 and 1965 generated with 10**18 more tech is to map thousand fold tech change 65-80 and thousand fold 80-95, then million fold 95-10 and million fold 10-25- roughly 65-95 corresponds to moores laws impact while 95-25 corresponds to both satellite mobilisation of data clouds and jensen huang's law of accelerated computing while its important you segment out your own map-from the start of silicon valley 65, tech revolution has spun from valley eg santa clara through the bay and san francisco up to berkeley (birth place of california universities and west coast anchor of usa governments energy and supercomputer mapping); between 65-80 we can see an asia coast rising with taiwan in the middle of change from north ie japan and S Korea and changes from south ie the diaspora chinese and royal english llm mediation of the 35 million most extraordinary entrepreneurial revolutionaries (roughly 5 million singapore (intelligence leader lee kuan yew) 10 million HK (typical intelligence leader li ka shing), 20 million taiwan (leaders H Li , Guo Chang)... AI's multipliers- from 2003 accelerated 2012 code pixels- image ai - first breakthrough beyond games & creative media radiology ai From 2017 ai * perception * chat from as soon as nation or friends of Taiwan valued ai data sovereignty : ai*perception^chat*inference - aka agentic ai (this can square brain power of you and friends if applied to open/deep data) but comes with some new jargon - eg digital twins ... | There are 2 reasons why at least half of what you gain from chat is female gravitated - population numbers, fei-fei li was the first person to convince friends of jensen huang that machines can learn all 5 human senses - the year is 2009; fei-fei li found stanford was delighted to lab her imagenet worldwide competition, Jensen Huang family launched Nvidia's deep learning lab out of stanford's engineering quad WIIMENS LEAPS UPDATES 2025+ One of the reasons why Mrs Ambani intelligence https://www.youtube.com/watch?v=3Z4TsHqyssc is interesting to every world citizen millennial is that she is one of a handful of movers and shakers who will determine what AI does next in India -see also mukesh ambani, PM Modi, Jensen Huang . ..Breaking news 25 July - Tokyo offers to stage whatever Guterres feels NY UN now longer can do 360 degree mediation on |
Tokyo Mayor Koike upd washingtonians dated July 2025: 1 tokyo fast growing AI start up -daily events hub and- sushi-tech annual event Sushi tech have a look at grok 4-
Maths, language, Science, and art are all interrelated disciplines that are essential for human understanding and co-creativity. They all use different methods to explore the world around us, but they all share a common goal of understanding and representing the world in a meaningful way. Here are some of the ways in which these disciplines are interrelated:
ReplyDeleteMathematics and language: Mathematics and language are both used to represent the world around us. Mathematics uses symbols to represent quantities and relationships, while language uses symbols to represent ideas and concepts. These two disciplines are often used together to describe and solve problems. For example, scientists use mathematics to describe the laws of physics, and they use language to communicate these laws to others.
Mathematics and science: Mathematics is essential for science. Scientists use mathematics to model the natural world, to make predictions, and to design experiments. For example, physicists use mathematics to describe the motion of objects, and chemists use mathematics to calculate the properties of molecules.
Language and science: Language is also essential for science. Scientists use language to communicate their findings to others, and they use language to explain their theories. For example, biologists use language to describe the anatomy of animals, and astronomers use language to explain the formation of stars.
Mathematics and art: Mathematics can be used to create art. For example, artists use geometry to create shapes and patterns, and they use proportions to create balance and harmony. Mathematics can also be used to analyze art. For example, art historians use mathematics to study the proportions of sculptures, and they use mathematics to analyze the composition of paintings.
Language and art: Language can also be used to create art. For example, poets use language to create images and emotions, and playwrights use language to create characters and stories. Language can also be used to analyze art. For example, art critics use language to interpret paintings, and they use language to describe the meaning of sculptures.