Thinks 981

McKinsey advice to CIOs and CTOs on Generative AI: “Move quickly to determine the company’s posture for the adoption of generative AI, and develop practical communications to, and appropriate access for, employees. Reimagine the business and identify use cases that build value through improved productivity, growth, and new business models. Develop a “financial AI” (FinAI) capability that can estimate the true costs and returns of generative AI. Reimagine the technology function, and focus on quickly building generative AI capabilities in software development, accelerating technical debt reduction, and dramatically reducing manual effort in IT operations. Take advantage of existing services or adapt open-source generative AI models to develop proprietary capabilities (building and operating your own generative AI models can cost tens to hundreds of millions of dollars, at least in the near term). Upgrade your enterprise technology architecture to integrate and manage generative AI models and orchestrate how they operate with each other and existing AI and machine learning (ML) models, applications, and data sources.”

Dr. Rina Bliss: “Up until the early 2000s, we believed that genetics predicted our intelligence and our IQ. We thought that genetics was telling us everything and that it could actually predict how well we would do on a particular test. Science since then has advanced greatly. We’re lucky to have research now that shows us that what genetics gives us is our brain architecture, our basic brain architecture, like the structures of our brain. And it doesn’t give us the quality of our thinking, the quality of our thoughts. It doesn’t tell us where we’re going to end up. Also, neuroscience has taught us that our brains are plastic; we are neuroplastic. That means we can change, and we do change. We are inherently developing and growing all the time, not just in our early childhood, but throughout our lives.”

Marc Andreessen: “The interesting thing about a system like GPT-4 is it has both: I would say, it has roughly human equivalent IQ–fluid intelligence–roughly of about 130, 135. And, I can tell you why I think we know that. But, then of course, which is sort of analogous to a quite smart person. It’s probably analogous to the IQ level of basically your typical student at the university where you are. However, it has, of course, far superior crystallized intelligence to any human, because it’s a computer. The other thing that’s happening is it just knows about so many more things, and that doesn’t translate into a higher level of fluid intelligence. But, when you use it, boy, is it useful because it turns out it knows a lot about everything in a way that any individual person does not. And so, basically, as a user of this, you get this kind of turbo-boost. You get its fluid intelligence augmenting your own, but you also get its crystallized intelligence and its entire memory augmenting yours. I think it’s the combination of those two things that give it such immediate practical payoff.”

NYTimes: “The hush at the end of the musical performance. The pause in a dramatic speech. The muted moment when you turn off the car. What is it that we hear when we hear nothing at all? Are we detecting silence? Or are we just hearing nothing and interpreting that absence as silence? The “Sound of Silence” is a philosophical question that made for one of Simon & Garfunkel’s most enduring songs, but it’s also a subject that can be tested by psychologists. In a paper published…in the Proceedings of the National Academy of Sciences, researchers used a series of sonic illusions to show that people perceive silences much as they hear sounds. While the study offers no insight into how our brains might be processing silence, the results suggest that people perceive silence as its own type of “sound,” not just as a gap between noises.”

iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce (Part 10)

A New Era

The foundation of our new era in eCommerce is formed by four essential building blocks:

  1. Mirror World: This is a digital rendering of the physical world, embodying a virtual landscape where millions of customers interact with brands. It symbolises a virtual reflection of our eCommerce business ecosystem, where every customer is unique and is represented by a digital entity with its own needs, preferences, and behavioural patterns. This dynamic setting allows customers, represented by their digital twins, to engage with a brand’s products or services, building a thriving, interactive space.
  2. Digital Twins for Customer Profiling: These software models are personalised depictions of individual customers, amalgamating their demographic, psychographic, and behavioural data. The creation of these digital twins allows brands to tailor predictions for the next best action for each customer, offering personalized recommendations and services that significantly enhance their experience and increase conversion rates.
  3. Metaverse Interactions: As a more engaging term for the Mirror World, the Metaverse signifies an immersive arena where brands and digital twins of customers co-exist and interact. These interactions illuminate customer behaviour, preferences, and purchasing patterns, arming brands with the knowledge to refine marketing strategies, enhance product offerings, and personalise services.
  4. Generative AI for Predictive Modelling: The multitude of data emanating from interactions in the Metaverse is processed using Generative AI. This AI model identifies patterns, deduces inferences, and forecasts based on the data. It helps predict the customers’ next move, simulate diverse scenarios, and provide a test bed for marketers to assess varying strategies.

The combination of these building blocks paves the way for an interactive, immersive, and personalised eCommerce experience, known as the “iDarpan”. This name encapsulates the idea of the digital ecosystem reflecting the customer’s unique needs, behaviours, and interactions. It is, in essence, a mirror image of their digital persona.

iDarpan is a digitally powered twin, enhanced by Generative AI, projecting a comprehensive model of each customer to suggest their next course of action, maximizing their lifetime value. It resonates with elements from the gaming industry and software agents, offering a highly tailored, personalized customer journey. It serves as a test lab for marketers, enabling them to experiment with various paths to enhance customer loyalty and boost lifetime value.

Furthermore, iDarpan seamlessly aligns with the objectives of Martech 2.0, blending in with concepts like  Inbox Commerce, Adtech-Style Performance Pricing, and profitable growth for brands. It supports the pursuit of near-zero customer acquisition costs and profitability amplification by focusing on fostering existing customers and maximizing their lifetime value.

Thinks 980

John Cochrane: “The case for free markets never was their perfection. The case for free markets always was centuries of experience with the failures of the only alternative, state control. Free markets are, as the saying goes, the worst system; except for all the others. In this sense the classic teaching of economics does a disservice. We start with the theorem that free competitive markets can equal — only equal — the allocation of an omniscient benevolent planner. But then from week 2 on we study market imperfections — externalities, increasing returns, asymmetric information — under which markets are imperfect, and the hypothetical planner can do better. Regulate, it follows. Except econ 101 spends zero time on our extensive experience with just how well — how badly — actual planners and regulators do. . . .” [via National Review]

Donald Boudreaux: “Industrial policy’s root problem isn’t that economists have yet to study adequately; it’s root problem that it ignores market prices. Information about relative scarcities supplied by market prices is essential for determining not only which outputs to produce but also how best to produce these – for example, for determining which of the countless possible mixes of different inputs for producing steel is the least costly. Get this mix wrong and either too little steel is produced or too many resources are used to produce steel, leaving fewer resources available to produce other outputs. Multiply such a mistake across several industries through many years and economy-wide growth is significantly lowered even if every firm showered with industrial-policy privileges appears to be successful. Detailed information about relative resource scarcities – scarcities that often change unexpectedly – is available only if market participants on the spot are free to make buying, production, and selling decisions using their own local knowledge. One result of such decision-making is an ever-changing pattern of market prices that conveys throughout the economy information about relative resource scarcities. Because it intentionally disregards market prices, industrial policy blinds economic decision-makers to information that is required to ensure maximum economic growth.”

Vice: “Venture firms that were lucky enough to raise money right before the bottom fell out of the tech industry might not have a chance of survival, but because they’d need to raise again for some time, they can mask their future failure. The New York-based VC (and podcaster) Logan Bartlett referred to this group of venture firms as “dead, but still walking.” (Bartlett puts his firm in the “pragmatic and disciplined” bucket of investors, obviously.) All the doom and gloom is leading to making fewer big, wild bets, which, theoretically, is the entire point of the enterprise. “VCs, in general, are becoming more risk averse,” said Abelon, the VC at Two Sigma Ventures. “There is less interest in investing in non-consensus or out-of-favor areas.”  Instead, at least according to some of the VC themselves, a good amount of the “dry powder”—or uninvested money—is helping to mask how much less valuable the VC’s collections of startups have become…“This system has a lot of lags built into it. So it’s going to take quite a bit of time to work its way through,” said Wenger. But, he said, the VC slowdown has clearly started, and it’s not close to over either. “The big reckoning will come when all that money runs out.””

Tom Wozniak writes about AI in email marketing: “It certainly seems feasible that the next generation of AI tools could combine aspects of traditional AI and generative AI to provide something even more full-featured. Imagine an email campaign that would first rely on AI to analyze all past campaign data to develop an overarching strategy, along with specific tactics. It matches products and offers to email recipients on a 1-to-1 basis, predicting what offer, product, and message should be sent to each member of your email list, along with when it should be sent to drive the highest ROI. Next, it dips into the generative AI arena to produce individualized email copy for each recipient and does all of this in real-time. That all seems very much in the wheelhouse of next-generation AI tools. At the same time, just because something is possible, doesn’t mean it’s actually a good idea. Hyper-personalization is a great example. There’s logic behind a process of true 1-to-1 personalization, but will it actually hold up when performance data is analyzed? We already know it’s possible to overdo it on personalization when it seems to veer into creepy territory and consumers start to feel like marketers know them just a bit too well. Will the ability of AI to make this type of intensive audience segmentation and personalization not only possible but potentially lead to marketers overstepping into the creepy zone? Probably.”

iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce (Part 9)

Consumer Copies

Imagine being able to use Generative AI to “copy” the behaviour of every consumer in the form of a “digital twin” and immerse a digital twin for every customer into a “mirror world.” This is what I think of as “iDarpan”. What would this world of marketing look like? Let’s begin by looking at some of the current thinking.

This is from a 2022 Gartner document entitled “A Digital Twin of a Customer Predicts the Best Consumer Experience”: “A digital twin of a customer is more than the concept, familiar to marketing executives, of a “persona.” Instead of merely collecting data points, it provides context and predictions of future behaviors. It uses both online and physical interactions and it’s dynamic, updating as new information comes in and recognizing that a single person can exemplify more than one persona … and those personas may shift over time. The twin collects enough data to accurately simulate the customer experience — moving them to more positive consumer-business relationship stages by fulfilling expectations and providing unexpected moments of delight.” It adds: “A digital twin can help businesses improve that experience and retain loyalty while also identifying the friction points that lead customers to defect to competitors…The digital twin synchronizes with its physical representation using real-time data inputs and event-stream processing, where action is taken on a series of data points originating from a system that continuously creates data.”

I asked ChatGPT and Bard how the ideas of mirror world and digital twins can come together for marketing.

[ChatGPT]

Mirror Worlds and Digital Twins, both as software models of real-world systems, can provide invaluable insights for marketing in several ways:

  1. Customer Behavior Modeling: Digital Twins could model customer behaviors based on various parameters, which might include demographics, purchase histories, social media interactions, and more. By simulating different marketing strategies or campaigns, marketers can gain insights into potential customer responses and refine their strategies accordingly.
  2. Market Simulation: Mirror Worlds and Digital Twins could simulate an entire market segment or even a global market. By analyzing these simulations, marketers can better understand market trends, identify potential gaps in the market, and predict how changes might affect market dynamics. This could be particularly useful in product development, pricing strategies, and planning market entry or expansion.
  3. Product Development and Testing: In the development phase of a product or service, Digital Twins could be used to simulate and test different design iterations and features in various market conditions. This can allow marketers to gauge potential reception and usability before the actual launch.
  4. Personalized Marketing: With the help of detailed customer models, companies can offer highly personalized marketing experiences. For example, a Digital Twin of a customer can provide insights into the individual’s preferences, enabling marketers to tailor specific messages, offers, or product recommendations.
  5. Immersive Customer Experiences: Mirror Worlds can be used to create immersive, interactive experiences that engage customers in unique ways. For instance, a virtual store where customers can explore and interact with products virtually before purchasing.
  6. Crisis Management and Scenario Planning: Digital Twins can simulate potential crises or unexpected market changes, helping marketers to plan effective strategies and responses.
  7. Supply Chain and Logistics: A Digital Twin of a company’s supply chain can help marketers understand how changes in the supply chain might impact product availability and delivery times, which are crucial elements of customer satisfaction.

[Bard]

The Mirror World and Digital Twins ideas can be applied to marketing in a number of ways, including:

  • Personalized marketing: Digital twins can be used to create personalized marketing campaigns that are tailored to the individual needs and interests of each customer. This can be done by using data from the digital twin to track customer behavior, preferences, and interactions with the brand.
  • Predictive analytics: Digital twins can be used to predict customer behavior and to identify potential opportunities for cross-selling or upselling. This can be done by using data from the digital twin to track customer engagement, purchase history, and product preferences.
  • Virtual reality and augmented reality: Mirror Worlds and Digital Twins can be used to create virtual reality and augmented reality experiences that can be used to promote products and services. This can be done by using data from the digital twin to create realistic and immersive experiences that can help customers to better understand the product or service.
  • Customer service: Digital twins can be used to improve customer service by providing customer support agents with real-time data about customer interactions with the brand. This data can be used to help agents to resolve customer issues more quickly and efficiently.

Here are some specific examples of how Mirror Worlds and Digital Twins are being used in marketing today:

  • Nike: Nike is using digital twins to create personalized marketing campaigns for its customers. The company uses data from its digital twins to track customer behavior, preferences, and interactions with Nike products. This data is then used to create personalized marketing campaigns that are tailored to the individual needs and interests of each customer.
  • Amazon: Amazon is using digital twins to predict customer behavior and to identify potential opportunities for cross-selling or upselling. The company uses data from its digital twins to track customer engagement, purchase history, and product preferences. This data is then used to predict which products customers are likely to be interested in, and to create targeted marketing campaigns.
  • Walmart: Walmart is using virtual reality and augmented reality to promote its products and services. The company has created a virtual reality experience that allows customers to walk through a Walmart store and see products in 3D. The company is also using augmented reality to allow customers to see how products will look in their homes.

Mirror World, Digital Twin, Metaverse, and Generative AI – all of these technologies can be combined together to reimagine marketing and eCommerce.

Thinks 979

David Brooks: “Two years ago, [Douglas] Hofstadter says, A.I. could not reliably perform this kind of thinking. But now it is performing this kind of thinking all the time. And if it can perform these tasks in ways that make sense, Hofstadter says, then how can we say it lacks understanding, or that it’s not thinking? And if A.I. can do all this kind of thinking, Hofstadter concludes, then it is developing consciousness. He has long argued that consciousness comes in degrees and that if there’s thinking, there’s consciousness. A bee has one level of consciousness, a dog a higher level, an infant a higher level, and an adult a higher level still. “We’re approaching the stage when we’re going to have a hard time saying that this machine is totally unconscious. We’re going to have to grant it some degree of consciousness, some degree of aliveness,” he says. Normally, when tech executives tell me A.I. will soon achieve general, human level intelligence, I silently think to myself: “This person may know tech, but he doesn’t really know human intelligence. He doesn’t understand how complex, vast and deep the human mind really is.” But Hofstadter does understand the human mind — as well as anybody. He’s a humanist down to his bones, with a reverence for the mystery of human consciousness, who has written movingly about love and the deep interpenetration of souls. So his words carry weight. They shook me.”

FT: “It takes courage to go against the prevailing economic or political dogma. For the past 20 years or so, questioning the notion that free trade was always and everywhere an unadulterated good was verboten in the US. That changed in 2018, when Robert Lighthizer, the US trade representative under President Donald Trump, levied tariffs on China, a move that triggered a broader debate about decoupling, the relationship between trade and diplomacy, and what the post-neoliberal world should look like. In his new book, No Trade Is Free, Lighthizer lays out the dynamics behind America’s new trade stance, arguing that the last two decades of what he would call a “radical free trade agenda” is a historical anomaly for the country, which like “all the great economies” was “built behind a wall of protection and often with government money”. This is an interesting observation for a Republican to make, but it reflects the fact that conservatism in the US didn’t always equate to a laissez-faire view on trade.”

Simon Kuper: “Possibly the main reward for writing books is getting invited to literary festivals, where you meet other authors. The company is delightful: good writers, almost by definition, are good storytellers and judges of character. The festival venue is usually delightful too. You might sleep in a stately home, take long walks in the garden with newly met writers, then finish the day with whisky nightcaps in the library. For a weekend, you live like an 18th-century author staying with an aristocratic patron. Along the way, I’ve been taking notes for an informal study of writers: who exactly are the people who go into the world’s worst business?…Audiences at literary festivals are mostly older people who venerate books as the highest in human endeavour. They aren’t exceptions. British publishers sold 669mn books last year, a record. Spend time among authors, and it’s hard to feel the culture is in decay.”

Economist: “The fact that companies raise their prices in response to shortages is not only defensible but desirable. The alternative to letting the price mechanism bring supply and demand into line is to rely on something worse, such as rationing or queues.”

Shane Parrish: “The difference between failure and success is often just staying with a problem a little longer. One more rep. One more step. One more minute. One more revision. One more attempt. The difference between average and outstanding is often just one more.”

iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce (Part 8)

Digital Twins – 3

Unity offers use cases from retail:

  • Design and planning – Create 3D virtual stores to visualize and simulate the optimal experience prior to construction; utilize planograms and store planning applications to maximize space, improve efficiency, and collaborate remotely.
  • Sales and marketing – From integrating 3D assets into e-commerce sites to creating virtual showrooms in VR, retailers can use digital twins to increase conversion and make purchase decisions more accurate, which limits returns and mitigates the environmental footprint of e-commerce.
  • Operations – Digital twins of product SKUs and stores can assist in the development of myriad applications to improve operational efficiency, from autonomous checkout to intelligent in-store navigation.

From “New Paradigm of Data-Driven Smart Customisation through Digital Twin”: “Big data is one of the most important resources for the promotion of smart customisation. With access to data from multiple sources, manufacturers can provide on-demand and customised products. However, existing research of smart customisation has focused on data generated from the physical world, not virtual models. As physical data is constrained by what has already occurred, it is limited in the identification of new areas to improve customer satisfaction. A new technology called digital twin aims to achieve this integration of physical and virtual entities. Incorporation of digital twin into the paradigm of existing data-driven smart customisation will make the process more responsive, adaptable and predictive. This paper presents a new framework of data-driven smart customisation augmented by digital twin.”

A research paper published in May 2022 summarises applications of digital twins across industries. From the section on retail: “The retail sector includes all the stores and shops that sell the products or goods to the consumer/customer directly. The success of any retail business depends on its customer base; attracting new customers is not enough, and maintaining/sustaining the existing ones by providing the best customer support is equally important. Digital Twin [DT] technology in the retail sector offers great potential in terms of consumer experience and marketing. By creating a DT of the customer, retail shops will be able to provide a unique and tailored customer experience based on customers’ patterns of interest. Customer satisfaction can be enhanced further by providing them with relevancy-based suggestions based on their DT without irritating them with multiple recommendations. DT technology enables retailers to turn their products into a dynamic platform that continuously acquires data regarding customers’ needs and buying behavior in order to provide them with better products and services. Combining the data from a customer’s DT with machine learning to understand the customer’s behavior will be beneficial for the customers as well as the retailers.” From one of the referenced papers: “With digital twins, consumer activities can be monitored through their online personas or avatars in online stores and social media. While they represent limited information about an individual, it is likely personal avatars will become an important element to retail in the future through the further development of sophisticated digital assistants.”

Can we create a mirror world with digital twins of customers and predict (probabilistically) what each of them is likely to do next? This is the idea I call “iDarpan”.

Before I get to iDarpan, I want to take a small detour to mention a book I came across recently. Here is its beautiful cover:

From the book’s introduction: “Just as great medieval cathedrals were raised by architects, masons, geometers and bishops to give humankind a glimpse of the infinite, supercomputers are the cathedrals of the information age, where novel worlds of endless variety, even entire universes, can be simulated within these great engines of logic, algorithms and information. You can also re-create the inner worlds of the human body, and not just any body, or an average body, but a particular person, from their tissues and organs down to the molecular machines at work within their cells, their component proteins along with their DNA. The eventual aim of this endeavour is to capture life’s rhythms, patterns and disorders in a computer, not just of any life or an average life, but of one particular body and one particular life—yours.” More: “If we are to create digital twins, how well do we have to know ourselves? To create Virtual You, we need to understand how much data and what kinds are sufficient for a digital twin to be animated by a computer. As Aristotle once remarked, knowing yourself is the beginning of all wisdom.”

The same can be said about the “Virtual You” in marketing and iDarpan.

Thinks 978

WSJ: “When computer-animation researchers Ed Catmull and Alvy Ray Smith were starting Pixar as a graphics computer company in 1986, they sought advice from a former colleague, Jim Clark, about how to run a business. Mr. Clark, founder of high-flying Silicon Graphics, told them: “Oh, it’s pretty easy. You’ll figure it out in about a year.” What mattered, rather, was that they were smart and knew computer graphics cold. That, more or less, is the thesis of Amanda Goodall’s thought-provoking “Credible: The Power of Expert Leaders.” Ms. Goodall, a business-school professor at the University of London, contends that the leaders who create and sustain greatness in an organization are those, like Messrs. Catmull and Smith, with a background as recognized experts in the organization’s business. Hospitals, for instance, are best run by respected doctors, and technical companies are best run by engineers. While such leader-experts were once the rule, Ms. Goodall says, “the pendulum has swung way too far down the generalist managerial path.””

Ramkumar Ramamoorthy: “While there is no denying the fact that we still churn out colleges under the affiliating system of education—along with Pakistan and Bangladesh, the two other countries where this system is in vogue—and spew out students who are not readily employable, it’s important to recognize that India has come a long way, especially in the last 10 years. The growth of micro, small and medium enterprises across industries, the global capability centers of Fortune 2000 companies, and startups is in part due to the explosion of this high-quality talent during this period. It is also important to mention the role played by the 2% corporate social responsibility (CSR) mandate by the government in catalysing the participation of corporates in education. After all, education receives an outsized amount of the annual CSR spend, followed by healthcare and livelihood. As a nation, we can brood over what’s not happening. Or we can look at the newer developments around us and find ways to accelerate them. Given the pace and scale of adoption of these seven trends, it wouldn’t be surprising if this new technology-enabled foundation results in exponential employability in the next five to ten years.”

NYTimes: “Netflix remains locked in its goal: It wants to dominate the entertainment world, but it is pursuing that ambition one country at a time. Instead of creating shows and movies that appeal to all 190 countries where the service is available, Netflix is focusing on content that resonates with a single market’s audience…“When we’re making shows in Korea, we’re going to make sure it’s for Koreans,” said Minyoung Kim, Netflix’s vice president of content in Asia. “When we’re making shows in Japan, it is going to be for the Japanese. In Thailand, it’s going to be for Thai people. We are not trying to make everything global.”…The company is also betting that a compelling story somewhere is compelling everywhere, no matter the language.”

Ninan: “India’s economic reforms, 1991 and after, were an investment in freer markets, domestic as well as global. The reforms were influenced by the ideas of the Reagan-Thatcher era on a reduced governmental role in the economy. The domestic initialisation for this was LPG: Liberalisation, privatisation, globalisation. Though implemented in stages and only partially, the belief was that greater market orientation would work to India’s benefit. And it did, delivering faster economic growth, lower inflation, a better trade balance, and external economic viability. But disenchantment has grown because of the failure to boost manufacturing, creating a scarcity of quality jobs and an increase in inequality. In addition, there has developed a vulnerability to China on systemically important products and materials, in parallel with the need to go green (solar energy, electric vehicles et al). The response is a more restrictive approach to trade (tariff hikes, new non-tariff barriers, restrictions on Chinese products) and the re-birth of government-directed industrial investment. This last involves the full gamut of policy tools: Investment subsidies, production incentives, tariff protection, and favoured business houses. It’s not a 180-degree reversal of 1991 (especially since those reforms were never complete), but a change of direction. The government gets a bigger, not smaller, role…India has been well and truly bitten by the big-country bug, and is committed once more to import substitution-on-crutches.”

iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce (Part 7)

Amplitude offers this helpful chart:

The Economist (in May 2022): “Digital Twins are virtual representations of a component, a device or even an entire production line in a factory. Fed with data from sensors installed on its physical opposite number, the digital version can be used to plan maintenance, spot any emerging problems and simulate the effect of upgrades and design changes. Aircraft engines in particular are followed by their manufacturers in this way. General Electric, Rolls-Royce and Pratt & Whitney, the three principal firms involved, maintain simulations of individual engines at engineering centres on the ground. These suck in real-time data from their counterparts in the air. At Cranfield University, in Britain, however, a group of engineers hope to go further than this. They propose expanding the idea of digital twinning to produce what they rather grandiosely refer to as a “conscious aircraft”. This would involve creating a digital twin of an entire plane by merging its various monitoring systems, and interpreting the result using artificial intelligence (AI).”

ChatGPT provides a list of use cases for digital twins.

  1. Manufacturing: This is one of the earliest adopters of digital twin technology. It’s used to optimize production processes, troubleshoot problems, predict equipment failures, and reduce downtime. A digital twin of a manufacturing process can simulate different scenarios and their outcomes, enabling more efficient production planning.
  2. Aerospace and Defense: Digital twins have been used to design, simulate, and maintain complex systems such as aircraft and spacecraft. They can also provide real-time diagnostics, predictive maintenance, and performance optimization of these complex machines.
  3. Automotive: In the automotive industry, digital twins are used for virtual testing of vehicle designs before physical prototypes are built. This can save time and resources by identifying potential issues early in the design process. They can also be used for predictive maintenance of vehicles.
  4. Energy and Utilities: Digital twins can simulate and monitor energy generation and distribution systems like power plants, solar farms, and electrical grids. They can be used to optimize energy generation and distribution, improve sustainability, and anticipate and solve potential issues before they occur.
  5. Healthcare and Biomedical: Digital twins are being used to model human physiology in detail, which can be used for personalized medicine, testing treatments, or studying diseases. They can also be used for hospital management to optimize operations and patient care.
  6. Smart Cities: Cities are using digital twins to simulate traffic patterns, utilities, and public services. This can help city planners optimize infrastructure, improve sustainability, and plan for various scenarios such as natural disasters or large public events.
  7. Supply Chain and Logistics: Digital twins can simulate and monitor every aspect of a supply chain, from manufacturing to delivery. This can be used for optimizing logistics, predicting potential disruptions, and improving efficiency.
  8. Construction and Infrastructure: Digital twins of buildings or infrastructure projects can be used to improve the design process, simulate different construction strategies, monitor the health of the structure, and manage maintenance tasks.
  9. Oil and Gas: Digital twins can be used for the design and operation of oil and gas equipment and facilities. They can simulate and predict the performance of oil wells, pipelines, and refineries under various conditions.
  10. Retail and E-commerce: Digital twins can model customer behavior, optimize store layouts, improve supply chain management, and enhance the overall customer experience.

Thinks 977

Nathan Baschez: “It’s easy to see why Facebook and Twitter struggled to keep so many different types of people all under one roof. For a long time, they’ve functioned kind of like the “downtown of the internet,” where people come together to meet but retreat back to their neighborhoods for more meaningful interactions. But now, thanks to Elon, it feels increasingly precarious to rely on Twitter as a public space. The rules seem to change every day, and the service feels increasingly buggy and broken. This throws everything off balance. The question is, what could come next?…The future of social networks is smaller communities.”

Nabeel S. Qureshi: “I came across a fantastic book called Think Like A Super-GM, by Michael Adams and Philip Hurtado. The authors take 100 or so chess puzzles, of varying difficulty, and then ask chess players of different skill levels (amateur to grandmaster) to solve them, while recording their thinking process out loud. It turns out comparing the thought process of less skilled vs. more skilled players gives you many useful insights! (I’d love to see this concept used for books in other disciplines.) The lesson I found the most striking is this: there’s a direct correlation between how skilled you are as a chess player, and how much time you spend falsifying your ideas. The authors find that grandmasters spend longer falsifying their idea for a move than they do coming up with the move in the first place, whereas amateur players tend to identify a solution and then play it shortly after without trying their hardest to falsify it first. (Often amateurs, find reasons for playing the move — ‘hope chess’.) Call this the ‘falsification ratio’: the ratio of time you spend trying to falsify your idea to the time you took coming up with it in the first place. For grandmasters, this is 4:1 — they’ll spend 1 minute finding the right move, and another 4 minutes trying to falsify it, whereas for amateurs this is something like 0.5:1 — 1 minute finding the move, 30 seconds making a cursory effort to falsify it.”

Economist: “Creativity is both prized and puzzling. Although associated with certain qualities—imagination, originality, artistic flair—it defies easy definition. Many philosophers contend that if a product (an artwork, a technological invention, a mathematical solution or a mere idea) is creative, it must be both new and valuable. Intention is also important: most would agree that a snowflake is not creative, nor a work composed by artificial intelligence. But beyond that there is little consensus. Explanations for where it originates range from the dreaming subconscious to wide-eyed attentiveness; from ponderous reflection to the flash of insight; from godly inspiration to grinding toil. Plato wrote that poets are inspired by the Muses in a divine madness, whereas Aristotle considered their work to be rational and focused on outcomes. Immanuel Kant thought creativity had to be both “original”—since “there can be original nonsense”—and “exemplary”, born of an innate imaginative capacity. For Friedrich Nietzsche it was a balancing act between a “Dionysian” ecstasy and “Apollonian” robustness. Yet creativity is enormously sought after. A poll of over 1,500 CEOs in 2010 ranked it as the most important leadership quality for success in business; the World Economic Forum has called creativity “the one skill that will future-proof you for the jobs market”. Nor is it just lucrative: creativity promises self-fulfilment, happiness and moral good in and of itself.”

Economist: “The world is in the grip of a manufacturing delusion…Manufacturing boosters make four arguments in favour of attempting to reverse this trend. First, politicians in the West say that factories are a source of solid jobs that produce a bigger and more satisfied middle class. Second, boosters view manufacturing as a driver of innovation and growth. This is urgently needed to fuel the green transition—the third reason—which will be more palatable to electorates if it delivers local jobs. Finally, tensions between America and China have pushed world leaders to reconsider which goods are strategically important, and therefore should be produced closer to home…Only once the agenda fails—either because the green transition does not create the jobs or economic growth electorates have been led to expect, or because subsidised production falls short of hopes—will a new generation of leaders begin to question whether industry is the cure for humanity’s greatest ills.” More: “Subsidies and protection for manufacturing will harm the world economy.”

iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce (Part 6)

Digital Twins – 1

An idea independent of and yet connected to “Mirror World” is that of a “Digital Twin.”

Wikipedia: “A digital twin is a digital representation of an intended or actual real-world physical product, system, or process (a physical twin) that serves as the effectively indistinguishable digital counterpart of it for practical purposes, such as simulation, integration, testing, monitoring, and maintenance. The digital twin has been intended from its initial introduction to be the underlying premise for Product Lifecycle Management and exists throughout the entire lifecycle (create, build, operate/support, and dispose) of the physical entity it represents. Since information is granular, the digital twin representation is determined by the value-based use cases it is created to implement. The digital twin can and does often exist before there is a physical entity. The use of a digital twin in the create phase allows the intended entity’s entire lifecycle to be modeled and simulated. A digital twin of an existing entity may be used in real time and regularly synchronized with the corresponding physical system. Though the concept originated earlier, the first practical definition of a digital twin originated from NASA in an attempt to improve physical-model simulation of spacecraft in 2010. Digital twins are the result of continual improvement in the creation of product design and engineering activities. Product drawings and engineering specifications have progressed from handmade drafting to computer-aided drafting/computer-aided design to model-based systems engineering and strict link to signal from the physical counterpart.”

IBM: “A digital twin is a virtual model designed to accurately reflect a physical object. The object being studied—for example, a wind turbine—is outfitted with various sensors related to vital areas of functionality. These sensors produce data about different aspects of the physical object’s performance, such as energy output, temperature, weather conditions and more. This data is then relayed to a processing system and applied to the digital copy. Once informed with such data, the virtual model can be used to run simulations, study performance issues and generate possible improvements, all with the goal of generating valuable insights—which can then be applied back to the original physical object. Although simulations and digital twins both utilize digital models to replicate a system’s various processes, a digital twin is actually a virtual environment, which makes it considerably richer for study. The difference between digital twin and simulation is largely a matter of scale: While a simulation typically studies one particular process, a digital twin can itself run any number of useful simulations in order to study multiple processes.”

Rameshwar Balanagu writes:

The ability to ingest data in real-time and technological advancements that made it more affordable spurred the adoption of digital twin technology for building digital replicas. Progress in artificial intelligence has led to optimization, better predictability and improved value. Once a digital twin is analyzed and better understood, both proactive and predictive maintenance can be done to respond to and recreate unplanned situations, thereby making timely decisions possible. This can help optimize a company and also contribute to the bottom line by making customers happy through more personalized experiences.

…A digital twin could be considered a lifeline for an enterprise, providing real-time insights and the ability to predict the next best offer or fix leaks in a process. It can also help optimize a network and perform automation akin to surgery to remove blockages or bottlenecks, such as in fulfilling an order in a timely manner. This, in turn, leads to greater customer satisfaction and protects the customer base….It can help customer experience teams by recommending the shortest path to customer satisfaction, highlight pain points, optimize service and suggest areas of automation.

McKinsey: “A digital twin could provide a 360-degree view of customers, including all the details that a company’s business units and systems collect about them—for example, online and in-store purchasing behavior, demographic information, payment methods, and interactions with customer service. It would also generate insights derived from the data, such as the average length of a customer service call. AI use cases leveraging the twin could include customer churn propensity models or a basket of the next products a customer would be likely to buy…When companies interconnect two or more digital twins, they can simulate the complex relationships among different entities and generate richer behavioral insights for even more sophisticated use cases and greater value…As organizations begin to connect these multiple twins of different business domains, functions, and operational ecosystems, the enterprise metaverse could start to take shape. A retailer, for instance, could connect the digital twin of its retail store to digital twins of its warehouses, supply chain, call center, and more until every part of the organization was replicated, sharing insights, simulating scenarios, and enabling automation and AI use cases.”