MxMIndia

Tag: Artificial Intelligence

  • Technology, Oh my GAAD!

    Technology, Oh my GAAD!

    Shruti PushkarnaToday marks the 13th edition of Global Accessibility Awareness Day, commonly known as GAAD. A movement initiated in 2012 by Joe Devon and Jennison Asuncion with the intention of taking accessibility knowhow to mainstream developers. And much has transformed thanks to this global drive.

     

    Technology, more specifically AI and Generative AI are the hot topics at every forum. Whether it’s the fear of losing our jobs to chatbots or driving business efficiencies with machine learning and artificial intelligence, tech innovations are rapidly altering the work culture.

     

    Accessibility is no longer an alien concept to average social media users, who stumble upon several tips to omit barriers in physical and digital spaces, using simple tech solutions. As an inclusion advocate, I believe technology enables and empowers everyone, including the most vulnerable.

     

    But do product developers, service providers, and industry experts understand how technology can mainstream marginalized communities like Persons with Disabilities?

     

    I’m not so sure.

     

    Last week, I was in the city of Nizams, or should I say the emerging IT capital of India, Hyderabad. I was attending an annual industry event focused on driving conversations in the space of HR Tech. A swanky summit showcasing workplace innovations empowering organisations to drive outcomes and human engagements. Sounds fancy and intriguing, right?

     

    Honestly, I was quite enthusiastic looking at the speaker line-up, exhibits and masterclass agenda. Every panelist propagated the new mantra, AI + HI = ROI (Artificial Intelligence plus Human Intelligence equals Return on Investment), laying special emphasis on empathy in this growing robotic era.

     

    Innovation. Technology. Empathy. Human Centric Approach. Almost music to my ears. Except it wasn’t. The scope of discussions was limited to present day work roles and current employee base. The futuristic innovations didn’t explore the possibilities of an accessible and conducive work environment for all.

     

    The two-day extravaganza could have been a perfect setting to introduce a new equation to CXOs, CHROs and CEOs,

    Innovation Quotient (IQ)+ Empathy Quotient (EQ) = Inclusion Equity Quotient (IEQ).

     

    Let’s rewind to the beginning of this month, where I had an altogether crippling experience with technology. Contrary to efficient and easy access, the processes at Max Hospital, a leading brand in healthcare hit rock bottom when it came to IP (In-Patient) Care. The computerised functioning and omission of paperwork had me thinking of myriad job roles that could be executed by persons with different disabilities in this setup.

     

    But my bubble was busted immediately as the colossal cracks in the system unravelled within hours of checking in to the ritzy facility. Health workers and care providers failed to administer timely treatment as the tech-powered processes held them hostage. It was a long chain of communication passing through layers of systemic approvals from doctors to assistants, to administration, to nursing, to pharmacy, back to nursing, and finally to the patient. And unlike AI, this was hardly intuitive or quick, it took hours to execute.

     

    By the way, speaking of AI, Chat GPT 4o was launched recently. Hardly a geek myself, I was browsing videos to understand what’s unique about the latest offering. That’s when I encountered a post by Open AI on X without captions or subtitles. Ironic, eh? Something that could easily be generated using that very AI!

     

    Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: https://t.co/MYHZB79UqN

    Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks. pic.twitter.com/uuthKZyzYx

    — OpenAI (@OpenAI) May 13, 2024

     

    But it’s May 16 and GAAD, so I won’t end on a depressing note. Technology is a gamechanger for 1 billion people with disabilities across the world. People who would otherwise lose out on opportunities of engaging with the mainstream society, for work, education, entertainment and more.

     

    Sarah Moin, a girl from Lucknow, scored 95 percent in her ICSE Class X exams. She is blind, deaf and speech-impaired. How did she managed to study and score well? The answer is technology paired with grit and determination. Sarah uses an Orbit reader which is a 3-in-1 device that works as a book-reader, note-taker and a refreshable braille display. It connects to computer or mobile using USB or Bluetooth. This tech marvel enabled her to write her exams digitally.

     

    Ruhin Bhattasali is a 100 percent visually impaired girl from Hyderabad. She scored 491/500 in her CBSE Class XII exams. Belying the common stereotypes that blind students can’t pursue STEM subjects, Ruhin studied Maths, Physics and Chemistry. She wanted to pursue astrophysics but due to accessibility challenges, she has opted for Computer Science and is preparing for IIT JEE.

     

    Here’s more good news.

     

    Following a complaint against a leading app-based taxi service by a visually impaired consumer, the Chief Commissioner of Persons with Disabilities (CCPD) issued a directive that will enforce disability-inclusive behaviour by cab aggregators. Corporate lawyer and Accessibility professional Amar Jain faced difficulty using the Ola app which didn’t adhere to the Web Content Accessibility Guidelines (WCAG). The order from CCPD seeks appointment of an Accessibility Auditor and a Grievance Redressal Officer to ensure all existing and new features comply with accessibility standards as per law.

     

    Is it time for industries to drop inherent biases, explore out-of-the-box ideas, and widen their consumer base to include underrepresented groups?

     

    Wondering why MxMIndia publishes a disability advocacy column? Well, we strongly feel that the media can dramatically transform the world for persons with disabilities. This series attempts to help bring forth issues that the media must champion to create a truly inclusive and accessible India. Writing  this column is Shruti Pushkarna, a former journalist and now a disability inclusion advocate based in New Delhi. Her views here are personal. To access the archives of her 90-plus columns, please visit: https://www.mxmindia.com/category/ columns/shruti-pushkarna/

     

    If you have a view on the issues raise or would like to align with MxMIndia on this cause, write to us at editor [at] mxmindia.com.

  • Touching the lives of 9 in 10 internet users in India

    AI market burgeoning: Kantar research

    According to Kantar’s Icube data, Artificial Intelligence (AI) is already touching the lives of 9 in 10 internet users in India, “powered by the enormous computing capabilities on their phones, connectivity, and cloud infrastructure”,

    As per Kantar, the current AI user base of the country stands at 724 million and poised to grow YoY at 6%. These are users who have used any of the AI features like image filters, personalised recommendations, smart devices, etc till now.

    Kantar also found that ‘fitness’ and ‘social media’ apps are driving AI adoption with an average of 2.3 AI led features embedded in these applications. ‘Entertainment’ apps are a close second, standing at 2.0 AI features on average. AI is also touching ‘digital commerce’ and ‘pharmacy apps’ at an average of 1.8 AI features each. Kantar also anticipates that many more digital commerce & entertainment apps will adopt AI features to enhance quality of customer experience and stay in line with the emerging trends. Adoption however is slower in the ‘BFSI’, ‘job search’ and ‘short video’ apps segments, at an average of 1.2 features each.

    As per Kantar, adoption of AI among users is currently high for popular features while enhanced AI functionalities are catching up. Incidence among AI users in 2023:

    1. 88 % consumers used AI based algorithms which analysed their preferences, behaviours, and interests to create personalized recommendations for tailored experiences. This segment grew at 6 % YoY.
    2. 88% consumer also automated various tasks and streamlined routines to enhance efficiency and productivity in their daily lives using AI. This segment grew at 6 % YoY.
    3. 86% used ‘image enhancement filters’ so that the resulting image is improved in terms of sharpness, contrast, brightness or with other features. This segment grew at 5% YoY.
    4. At 21%, ‘smart home automation’ is a smaller segment but growing at 25% YoY.
    5. 15% consumers enhanced their ‘user experience through virtual assistants’. This segment is the fastest growing at 27% YoY.

    While AI technologies are touching most internet users of India today, their usage is expectedly higher among the youth (19–24-year-olds) at 92% and interestingly, at a high 81% for the older (45+ year old) age bracket as well.

    Speaking about AI and addressing the marketers, Soumya Mohanty, Managing Director & Chief Client Officer- South Asia, Insights Division, Kantar said: “AI is inevitable. Historically, technology adoption has always been a dominant determinant of a brand’s trajectory. We at Kantar feel that it is important to help marketers humanize AI to innovate successfully, help activate AI to predict future performance, maximize ROI and use AI strategies to build competitive advantage for sustainable growth. We have created a range of offerings which will benefit marketers and consumers by extension. LINK AI is one such solution, which helps evaluate creative effectiveness at scale and has helped uncover new insights into creating better video ads on YouTube which has a proven track record of growth, following Google’s ABCD framework. Similarly, we have introduced best in class offerings like LIFT ROI, Trend AI and NeedScope AI for various stages of brand growth as well.”

    Added Puneet Avasthi, Senior Executive Director, South Asia, Insights Division, Kantar: “Generative AI is set to become a $1.3T market by 2034 with a possible 42% CAGR growth over the next 10 years. We are sitting at a point of inflection where the next few years will enable a competitive edge between businesses who adopt early and others. As the usage of AI grows rapidly, it is critical for marketers to not use AI in isolation and as a gimmicky fad, but weave in consumer behavioural data into it to remove biases, continue to focus on building equity and not just to run activations. Kantar is at the forefront of this AI revolution and is assisting brand builders to strengthen creative testing, innovation using it’s AI based solutions.”

  • Market Research in the Age of AI

    Market Research in the Age of AI

    Ashoke AgarrwalWhen one plots the future of Artificial Intelligence (AI) in marketing, one arrives at a singularity where all of marketing is the AI avatar of a brand in direct conversation and interaction with the AI avatar of the consumer. I have called the AI avatar of consumer – Concierge Intelligence in many of my columns here, including my first MxMIndia column back in Jan 2022 -“The Coming Post-Digital Age”.

    However, plotting and thinking about the intermediate points would be helpful.

    I have been part of a team working since 2020 on using Natural Language Processing (NLP) to generate secondary research semi-autonomously. The launch of GPT-3 and subsequent versions reframed the project for us. Like scores, perhaps hundreds worldwide, we are now trying to find a market niche, proprietary prompt engineering, and the correct interface to support a viable business. Say, a freemium WhatsApp interface for Indian SMEs offering online business consultancy services based on open-source predictive and generative AI models working on public and paid data sets.

    What about the emerging role of AI in primary consumer research? The big two—Alphabet and Meta—have been using predictive AI for decades to segment consumers, keep them engaged with their social media feeds and search results, and harvest clicks so their advertisers can pay them big bucks.

    Over the past decade, big corporates from both the B2C and B2B worlds have been using Big Data and Predictive Analytics to fine-tune their business and marketing plans. However, it is unclear whether they are at the cutting edge of predictive AI, just as Alphabet and Meta are. While a lot is currently being made of Generative AI and the likes of GPT, Llama, Gemini, etc., I bet that we shall discover that the disruptive power of AI will come not from generating sentences, pictures, videos or music but from underpinning key business, economic, social and personal decisions based on a dynamic array of multi-dimensional data sets. While predictive AI underpins generative AI, a different kind of predictive AI will also underpin the AI age. It will be predictive AI that works on an integrated, dynamic view of the natural world to deliver strategic action plans and monitor and fine-tune them. To use this level of AI, corporations and governments will need to go beyond internal data sets and subscribe to a whole range of third-party data sets.

    One category of these third-party data sets will be garnered through an IoT network of sensors synthesised with publicly available identification data sets—for example, vehicle movement with ownership details or scans of browsing shoppers, personal IDs and billing details. The ownership and personal ID can be scrubbed of all details except for basic demographics to meet privacy rules. Alternatively, the individual could opt to belong to an ID Bank that holds his details in escrow and can release them, using blockchain technology on payment of a fee – thus making the individual the valid owner of his ID and personal data.

    The ID Bank idea will fuel the second category of third-party data sets. These data sets will contain in-depth profiles of individuals, including contact information, demographics, psychographics, societal and cultural attitudes, media usage, product and brand usage, and purchase behaviour and intentions. The ID Bank will have a watertight agreement with the individual on securely holding the data and releasing any of it to a third party only upon approval and release of a specified fee.

    Corporations can then request the release of specified data from a selected consumer profile. For example, a car company may ask for a data set consisting of individuals who own one of a set of car models and have indicated a purchase intention for a new car in the next six months with permission to contact with offers. The ID Bank, in discussion with the consumer, will quote a certain fee on payment, for which the data will be released in a blockchain format that allows for usage tracking. The fee will be released to the consumer’s account, and the ID Bank will get a management fee.

    Creating, managing and marketing the two categories of data sets envisaged above will define the future of the market research industry over the next few decades.

    The corporation’s predictive AI systems will define the need for data from third-party data sets, consider the cost-benefit of buying them, and incorporate them into predictive analysis to build business and market plans.

    Over the decades, as AI and consumers become more sophisticated, intermediaries like ID Banks will be cut out, and a brand’s AI will be in direct touch with a consumer’s Concierge Intelligence (CI) with market research evolving into a version of anthropology focused on studying the behaviour of AI systems. “AInthropology” anyone!?

  • Artificial Intelligence: The Road Ahead

    Artificial Intelligence: The Road Ahead

    Kunal SinhaInvestor enthusiasm for artificial intelligence (AI) soared to unprecedented heights last week, fuelled by remarkable performance from chipmaker Nvidia, which propelled stockmarkets across three continents to historic highs. The surge, commencing on Thursday and extending through Friday, saw Nvidia surpass Google’s parent company, Alphabet, to claim the coveted position of the third most valuable company in the US, boasting a market capitalization of $2 trillion, second only to tech giants Microsoft and Apple.

    Nvidia’s significance in the AI landscape cannot be overstated.

    The company produces chips essential for training and operating AI systems, facilitating rapid data processing crucial for applications like chatbots. As demand for such infrastructure skyrockets with major tech players entering the AI arena, and with consumer interest in AI-driven products like ChatGPT and Midjourney surging, Nvidia’s robust performance underscores the thriving demand for AI technology, inevitably attracting the attention of investors.

    The artificial intelligence (AI) boom has raised many questions, not least over safety and the impact on jobs, but there are also concerns that it might be driving unsustainable market exuberance.

     

    What do consumers think of AI?

    Consumers are still in a wait-and-watch mode with respect to AI, with feelings
of both awe and distrust.

    This is driven by the concern that it could replace
a human they can connect with. The desire for human connection reflects in their channel preferences, too – with most still preferring to interact with human channels over digital, especially for high-stakes tasks like resolving an issue with a bill, and switching to digital for simpler, transactional activities like checking an order status. Human interaction remains a top choice when considering aspects of decision-making, customer support, and returns or cancellations.

    There is also enthusiasm. Around 57% Indian consumers would prefer using Artificial Intelligence (AI) tools rather than to engage in human interaction while looking for products and services online, findings of a recent Adobe survey reveal. Recent research by Qualtrics tells us that 73% of consumers are fine interacting with AI is getting status updates on an order placed; and 48% of people are comfortable interacting with an organisation/ brand’s AI.

     

    Where are businesses with AI adoption?

    While shoppers try to work out exactly what to think of these technologies, the businesses that move quickly to incorporate AI and new data strategies into their operations will be best poised for success. In the early days of gen AI, it feels a lot like giving a toolbox to every employee and allowing them to experiment with what they could build, and possible gains in productivity and cost. As business use cases become clearer, we should be able to see how brands discover opportunities to drive innovation.

    Offering a consistent and accurate customer support experience is one of the main challenges which businesses face.
This is where businesses in India are still in the early stages of AI deployment.

    Only 15% Indian brands are leveraging generative AI to enhance customer experience (CX) initiatives compared to 18% globally.

    41% of Indian brands are seeing CX as a business priority today.

    87% of Indian brands are prioritizing CX enhancements over other business goals.

    76% of brands already have or will pilot GenAI solutions to support CX.

    Overall, 53% of Indian brands want to improve GenAI capabilities in the next 12 months.

     

    Bridging the gap between intent and action is going to be a priority in 2024.

    As consumers go from making a purchase to resolving an issue online, the customer journey often breaks down –
with satisfaction 22 % points lower compared 
to making a purchase.

    AI and Customer support

    For companies that get digital support right,
there are significant rewards. One study found customers are 2.7X more likely to return after a positive digital support experience — the highest of any channel and journey studied.

    Marketers must look to AI to empower their frontline teams with the tools, time, and insights to build stronger connections with customers and make that a better experience, too.

    While AI will undoubtedly help businesses make simple, repeatable tasks more efficient – something consumers welcome -
an effective AI strategy is not simply deploying more chatbots and automating tasks.

    Blinkit, the quick commerce platform of Zomato has introduced a new feature called ‘Recipe Rover’ driven by the most popular AI models ChatGPT and Midjourney. Recipe Rover displays multiple recipes related to the food items which the customer searches for in the app. The company also plans to integrate generative AI into product photography, customer support, etc. Zomato’s massive customer database can be effectively deployed to create more customer-friendly features in the future.

    Using data to predict customer needs

    Data will dictate how to best use gen AI – for both customer and business needs. While businesses are still in
the experimental phase, the push to monetize gen AI investments and quantify their value is becoming stronger. Leading that charge are decisions around how to use valuable internal data to maximize the value that generative AI is creating.

    AI’s predictive power enables brands to get ahead of customer needs through analytics of behaviours, interactions and preferences. It identifies subtle shifts that human analysis alone could miss, such as churn risk, service issues, up-sell opportunities or optimal times for engagement.

    These insights allow brands to engage contextually at just the right moments. Inevitably, while booking a flight ticket, the AI nudges me to book travel insurance as well. It makes excellent recommendations for hotels at the destination, often offering up significant discounts.

    Identifying customer needs through prediction is just the first step, though.

    Leading insurance tech company Policybazaar has been using AI tools for fraud detection using an AI-based risk framework that checks for liveliness and avoids deep fakes. It also uses AI tools for motor vehicles inspection where the customer can make a video of the vehicle and upload it while the AI does the damage assessment.

    The company has also developed predictive AI for voice to text conversion which can be used to gather consumer data and be used to assess consumer behaviour.

    Firing up Contextual Personalisation

    Companies that grow faster drive 40% more of their revenue from personalisation, according to a report by McKinsey & Company. But tailoring engagement across channels and customers is enormously difficult. AI systems can take individual customer insights and orchestrate relevant cross-channel personalisation at scale. The result is a tailored, proactive experience for every customer.

    When you think of your best customer experience, you realise that the brand seemed to truly understand and cater to you – personalised engagement is the magic behind this experience. It’s impactful, and it matters. It not only elevates the customer experience but also results in better business growth, because they return and keep ordering.

    An e-commerce platform can use real-time behavioural analysis to recommend products to a user based on their current browsing pattern. When a user looks at sports shoes, the platform can immediately recommend relevant products, such as sports socks or training equipment. This immediate, relevant personalisation improves the user experience, leading to greater engagement and potential conversion.

    With 62% of consumers comfortable booking an airline ticket through AI,

    MakeMyTrip, one of India’s leading travel booking companies has collaborated with Microsoft to use generative AI to introduce voice-assisted booking in Indian languages. It helps users by offering personalized travel recommendations based on their preferences, curating holiday packages and booking them.

    Being mindful of privacy

    While AI offers immense potential, it also brings significant risks if ethics and consumer privacy are neglected. Around 59% Indians do not feel positive about buying from a brand that isn’t transparent about the use of their personal data.

    To maintain ethical integrity, brands must establish clear guidelines for unbiased, transparent and privacy-focused use of customer data. Rigorous testing is essential to eliminate bias in predictive algorithms.

    There are three essential steps that companies can take to find the sweet spot between personalisation and data privacy.

    • Only collect data that’s essential to creating a better customer experience. Begin with the experience you want to deliver and then define the data required to deliver it.
    • Allow your customers to customize their experience. Let them choose how much personalisation they want and how much of their data they are happy sharing.
    • Be transparent about how their data will be used. Once they understand that, they will be more likely to share their data willingly.

    In a nutshell, think of AI as the neighbourhood chacha (uncle) at the kirana (mom- and-pop) store. They have all your weekly transaction data. They know everything about you and your family. And they use that information to give you personalised, unmatched customer service, while maximizing their profit.

    Pretty basic, right?

     

    Kunal Sinha is a senior strategy and foresights executive based in Jakarta, Indonesia. He is the author of several books including The Future of India’s Rural Markets and Raw – Pervasive Creativity in Asia. He writes for MxMIndia every other Monday. His views here are personal.

  • … if we don’t start to value and protect the traits that make us human, writes Cameron Shackell in The Conversation

    Will AI kill the creativity in media? It could…

     

    By Cameron Shackell

     

    There’s no doubt generative AI’s ability to rapidly produce new texts, images and audio is shaking up creative jobs.

     

    In the long-running Writers Guild of America strike, a central sticking point has been the guild’s demand that AI be used only as a research tool and not a replacement for its members. For many creative types, it seems harder to earn a living with AI around.

     

    At the same time, however, AI tools are often seen as a springboard to next-level human creativity. Technologies such as Anthropic’s chatbot Claude and OpenAI’s ChatGPT and Dall-E 3 offer a seductive creative experience.

     

    Will these tools help us survive and thrive as a creative species? Or are they the death knell of creativity as we know it?

     

    What is creativity?

    In her book The Creative Mind, cognitive science expert Margaret Boden distinguishes between two types of human creativity.

    Psychological or personal (p-type) creativity happens when an individual thinks something for the first time – even if others have thought it separately before. One example is a child realising water can take any shape.

    Essentially, p-type creativity is learning something useful and, in the process, synchronising our thoughts with others.

    Historical creativity (h-type), on the other hand, happens when an individual thinks something that has never been thought before. One example would be Archimedes’s “eureka” moment in the bath, which supposedly led to him discovering the law of buoyancy.

    The more someone’s creativity subsequently affects other people’s thinking, the more momentous and enduring we consider their legacy.

    This is why Wandjina rock art in the Kimberley, Homer’s Iliad, Pablo Picasso’s Guernica, Frank Lloyd Wright’s Fallingwater house and Albert Einstein’s Annus Mirabilis papers are all considered exceptional works left behind by exceptional humans. They are important because they continue to shape our thinking.

     

    Generative AI doesn’t belong in either category

    AI obviously has the potential to promote both p-type and h-type creativity. It can lead us to insights about biology, history and mathematics, and help us create texts and images that may be useful or thought-provoking.

    But there is one key difference between human creativity and AI-driven creativity: the latter doesn’t stem from the evolutionary clash of mind and world.

    AI models don’t contain reality. They rely on the complex statistical abstraction of digital data. This limits their real-world creative significance and their capacity to produce “eureka” moments.

    To differentiate AI-driven creativity from old-fashioned creativity, I have proposed a new term: generic, or g-type, creativity. It formalises the fact that while AI models are capable of provoking new thought, they are limited by the underlying data they have been trained on.

     

    The big risk: a generic spiral

    We can expect an explosion in g-type creativity in our future. The danger here is that our increasing use of AI could make us think too much alike, leading to a decrease in cognitive diversity and an increase in cultural tightness.

    In this scenario, societies would become more rigid in the norms they enforce, and less tolerant of deviations from the status quo. At a population level this would be a creativity killer.

    The threat isn’t just AI-generated movies, TV, books and art. In the future, the homes we live in, the cars we drive (or won’t have to drive) and our shared public spaces will all be shaped by AI. We may see our thinking become homogenised under the pressure of increasingly similar environments and experiences.

    This sameness further put us at risk of a generic spiral. AI models are trained on content we create. So the more we use AI for g-type creativity, the more generic our content will become – and since this will be used to further train AI, the more generic AI outputs will become.

    While this might be useful for certain specialist tasks – such as consistently interpreting law – it’s worrying to contemplate the kind of Orwellian political economy a generic spiral might give rise to.

     

    Can we enjoy AI and also preserve creativity?

    Balancing and reconciling human creativity with AI isn’t as simple as going for regular walks in nature – although that will probably help.

    Generative AI may well be a transformative technology to rival the printing press or steam engine. Such juggernauts are difficult to resist; we collectively get swept up in the change, uncertainty and alienation they foment.

    Some of the best minds of our generation are already abandoning other pursuits to try their luck at building and using advanced AI models.

    Our best chance to remain truly creative is to protect and privilege the human over the artificial. Intellectual property law is key. Any further moves towards legal personhood for AI – such as allowing AI a “fair use” right to train itself on copyrighted material, or have copyright applied to AI outputs – will erode our creative system and risk a generic spiral in human creativity.The Conversation

     

    Cameron Shackell is Sessional Academic and Visitor, School of Information Systems, Queensland University of Technology. This article is republished from The Conversation under a Creative Commons license. Read the original article.

     

  • AI is set to impact the daily lives of all of us significantly, writes Ashoke Agarrwal

    Apple, Musk and AI

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalI coined Concierge Intelligence (CI) as a type of Artificial Intelligence (AI) owned by and dedicated to an individual and fully protective of his privacy. CI would aid the individual in understanding herself better and leading to better life outcomes in health, education, career and relationships – in general, as a putative ad copy would say: ‘Be A Better You’. Further, CI would handle routine tasks like shopping, bill paying, appointments, correspondence and travel arrangements based on a deep understanding of the individual’s preferences and needs and an up-to-the-minute and universal understanding of options. CI would be under the complete control of the individual, who can switch it off and on and decide on the level of access granted.

     

    When I first wrote about CI in Feb 2021, the concept seemed at least a decade or more away. Not any longer. Like the world, I was unaware of the rapid progress of Large Language Models (LLM) technology.

     

    Today, many factors indicate that the first generation of CI is around the corner. A CI prototype might already be in the hands of hundreds of millions worldwide! Let me explain.

     

    For a couple of years now, Apple has been communicating the following:

    :: Many of the functions and Apps on its devices – Siri, Keyboard Suggestions, Health, Messages, Mail, Music, Books, and Apple TV – use AI to enhance user experience and utility.

    :: Apple puts ensuring user privacy as the highest priority. Therefore, all its AI works on data and software residing on the user’s device, under complete user control, and cordoned off from other entities, including Apple.

     

    The penny dropped when I first read about the Journal App that Apple is readying for release with iOS 17. Journal App gives iPhone users the means to record their day-to-day activities and uses advanced prompt features enabling users to track their emotional state and the causes.

     

    The latest iPhones carry specialised chips that allow the device to run sophisticated AI programs on the device itself. With the breadth and depth of information, the iPhone has about its users, the phone’s processing capabilities and the level of trust Apple had built with its users, all the conditions that make for a CI already exist. Over the next few years, iPhone users, prompted by Apple, will increasingly find use cases for the CI that resides over the phone. With each new generation of iPhones, the CI will get more powerful and within the next decade, Apple will likely brand this as a proprietary feature and build a revenue model around it. CI by Apple could be the next big thing from Apple after the iPhone. If Apple keeps its promise of protecting user privacy, iPhone CI will add to the quality of life and be one of AI’s boons.

     

    While the wizards of Cupertino are coming at AI based on an individual’s shared experiences, the wizard who has given the world Tesla and SpaceX is taking a different tack.

     

    Musk wants Tesla to be the first to launch a fully self-driven car without a steering wheel or a brake pedal to allow a human driver to take control. While many companies, Alphabet being one of them, are at work perfecting AI systems, Musk’s approach is entirely different from the rest.

     

    Alphabet and others are trying to build a self-driving car based on an algorithm that relies on the following:

    :: Signals from a hardware system consisting of cameras and radars that transmit in great detail, second by microsecond, the physical environment of the car as it drives through a roadscape.

    :: And rules that codify the signals into millions of scenarios and actions that are needed to respond to the system.

     

    The above approach is similar to the early days of Natural Language Processing, which tried to create language models based on the contextual meaning of words and rules of grammar and idiomatic usage.

     

    In one sense, Musk’s flip on the AI needed to build a self-driven car is simple. He believes if humans can drive cars based on just visual inputs, so can AI. So, radars are the first things he has taken out of the equation. His second lead is even greater. Large Language Models (LLMs) like GPT 4.0 work through patterns that a Deep Learning AI system detects from a large enough set of training data without needing an explicit set of rules. Musk’s leap is that he can build AI systems that can operate in the physical world through a large enough training data set. The difference is that in the case of the physical world, the data set is visual.

     

    Every Tesla carries a set of high-resolution cameras. And its software records all the actions that a driver takes. Further, all the data from the cameras and the software systems are transmitted to Tesla’s servers. With millions of Teslas worldwide, Tesla has an ever-increasing training data set.

     

    Musk is not stopping at building self-driving Robocars but is busy building a human-like robot branded Optimus on the same AI principles. The training data for Optimus-like robots will come from recording humans engaged in various activities – cooking a meal, navigating a home, an office or a mall, playing a sport, etc.

     

    Further, in all cases, the training data will be culled so that the robot learns from the best drivers, champion players, chefs, etc. So ipso facto, robots will come out of the gate better than humans because they learnt from the best and have the advantage of being faster, connected and untiring.

     

    Paradoxically, Musk also pays lip service to the dangers of AI and contends that he is trying to build something like Assimov’s Three Laws of Robotics into the AI systems he is busy inventing.

     

    So, between the CI that Apple is fast making a reality and Musk’s promised Robot Intelligence (RI), AI is set to impact the daily lives of all of us significantly.

     

    Another AI revolution is brewing in the scientific field, launching tectonic shifts that will alter human civilisation. But that is grist for another post.

     

  • People whose business is to peek into the future approach Artificial Intelligence from two very different angles, writes Ashoke Agarrwal

    The Economic Promise & Cultural Peril of AI

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalArtificial Intelligence (AI0 is fast becoming the general-purpose technology that will determine humankind’s future.

    People whose business is to peek into the future approach it from two very different angles.

    Some hard-headed economist types see AI mainly as a disruptor of the world of business and economies.

    Others who study broader and deeper societal trends prognosticate the possible long-term effects of AI on human civilisation.

    Neither school sees AI developing into a threat on the lines of the Terminator-type robot shooting down people in the streets or a Skynet-type all-powerful entity trapping humans in a virtual matrix.

    The book “Power and Prediction: The Disruptive Economics of Artifical Intellgence.” by Ajay Agrawal, Joshua Gans and Avi Goldfarb, a 2022 follow-up to their 2018 book “The Prediction Machine: The Simple Economics of Artifical Inteliigence.” lays out the disruptive but possibly ultimately enhancing effect of AI on the world economy.

    The broader view of the impact of AI on human civilisation comes from Yuval Noah Harari, the historian-philosopher whose three books “Sapiens: A Brief History of Mankind.”, “Homo Deus. A Brief History of Tomorrow” and “21 Lessons for the 21st Century” introduced a deeply thought out yet lucid and vivid view of the factors that governed the evolution of human civilization.

    Harari has spoken at length about his views on AI at various forums. Recently he did a three-hour sit-down with Lex Friedman. Here is a YouTube link to the interview and a transcript. Harari’s views are grounded in his unique approach to the evolution of human civilization and startling in their clarity and scope. It also offers an almost sly but plausible take on the threat that AI poses to human society without going into Terminator and Skynet kind of fevered speculation.

    In their 2018 book “The Prediction Machines”, Agrawal et al. posited that AI at its core was a quantum leap in the science of prediction. Until the emergence of Deep Learning, prediction methods mainly used the science of statistics with tools like multivariate regression. With Deep Learning and its offshoots, predictions became progressively more accurate and cheaper. Agarwal et al. posited that technology finds more widespread use when it becomes more affordable. They offered the instance of electricity and computers. One of the vivid examples they offered about how better predictions could lead to changes in business models was of e-commerce players like Amazon shifting from a “shop-than-ship” model to a “ship-than-shop” model once they had the AI tools that predicted with reliable accuracy what their customers would buy next – that is they would ship the predicted product off to a consumer even before he had shopped for it on their site. In support of this insight, they cite that Amazon had filed for a patent for “anticipatory shipping”.

    In their 2022 book “Power and Prediction.” Agrawal et al. revise their view of the economic future of AI. They posit that the widespread adoption of AI will not happen with point solutions like replacing processes where traditional forecasting is currently the norm with AI-based forecasting. Instead, it will compel economies and businesses to go beyond and identify areas where AI-based prediction enables them to switch to decision-based procedures that optimize resources instead of rules-based processes that compromise efficiency in the face of uncertainty.

    Also, because AI-based predictions will have system-wide ramifications, the optimal adoption will happen when economies and businesses redesign entire systems to accommodate AI. Agarwal et al. identify two design approaches that can drive systemic changes: coordination and modularity. Their book details these approaches and illustrates them with examples from the health, transport and e-commerce sectors. The overall message from Agrawal et al. is that AI and its economy-wide adoption will be systemic and disruptive. And overall, its impact will be positive, like the widespread adoption of the last two general technologies – electricity and computers.

    Mr Harari’s views on the civilisational impact of AI are nuanced.

    Harari’ has been surprised by the pace of development of Large Language Models (LLMs) and their rapid penetration into the social and cultural life of human societies.

    At one level, he sees the threat posed by LLMs as a ratcheting up of the threat posed by social media. The design of social media algorithms captures attention and, in the process, creates echo chambers that fuel conspiracies and tribalism. AI entities based on ever-improving LLMs will capture intimacies. If unchecked, they could monopolise an individual’s personal space, weakening and destroying individual relationships and thus weakening the concept of family and friends and hence the very social framework undergirding human society.

    Harari perceives another more subtle threat. Harari hypothesizes, as explained in his books that the life of individuals, societies, cultures and civilizations is circumscribed by stories and myths that are creations of the human imagination. God, religion, nation, money etc., are all myths that have taken deep root and driven society in all its pursuits – politics, economics, art and culture.

    While Agarwal et al. perceives AI as a disruptive “Prediction Machine”, Harari rotates the prism and perceives AI as a threatening “Culture Machine”. He sees AI ( and sometimes he calls it Alient Intelligence) as “eating” and “digesting” all human culture to come to a stage where it can give back images, words, art and stories that are more compelling than any that humans can process. Because these cultural artefacts govern human evolution, this “Alien Intelligence” will take charge of it. Here in his own words, is how he perceives this threat:

    “...But taking what we do know about human history until now, all the, again, stories, images, paintings, songs, operas, theater, everything we’ve encountered and shaped our minds was created by humans. Now, increasingly, we live in a world where more and more of these cultural artifacts will be coming from an alien intelligence. Very quickly we might reach a point when most of the stories, images, songs, TV shows, whatever are created by an alien intelligence. And if we now find ourselves inside this kind of world of illusions created by an alien intelligence that we don’t understand, but it understands us, this is a kind of spiritual enslavement that we won’t be able to break out of because it understands us. It understands how to manipulate us, but we don’t understand what is behind this screen of stories and images and songs.”

    That is a more alarming picture of the AI-age world than any Terminator or Skynet kind of scenario. It is more disturbing because the process is sneaky and sly, and one can see the beginning of it even at the early stages of the LLM revolution.

    While the forces of commerce and the market will ensure that economies reap, with time and effort, the benefits of the “Prediction Machines”, what remedy do we have against the threat of the LLM-based “Culture Machine.”? Harari has a challenging remedy to offer. Harari believes that we humans do not fully understand ourselves. He suggests that for every dollar and hour we spend developing the AI-based culture machine, we also invest a dollar and hour in understanding ourselves better – perceiving the contours of conscious daily reality that exist in our feelings beyond the stories and the myths that confuse and control us. Is that a realistic goal? Will the story of progress that drives our notions of work and happiness allow us to set and accomplish such a goal? Let me put this question to ChatGPT and Bard and see what they say.

     

  • A Q&A with ChatGPT on whether the AI tool will replace journalists…

    Will ChatGPT see the end of journalism as we know it?

     

    There has been much discussion and fear about the impact of artificial intelligence (AI) and various tools like ChatGPT on journalism. So we decided to do a Q&A with ChatGPT and asked it some leading questions. Here goes. Our first question is what this feature is headlined: will ChatGPT see the end of journalism as we know it?

     

    No, ChatGPT will not see the end of journalism as we know it. While AI language models like ChatGPT can assist with certain functions in a newsroom, such as fact-checking and content curation, they cannot replace the role of human journalists and editors entirely.

    Journalism is a multifaceted field that requires skills, experience, and critical thinking that go beyond just language proficiency. Journalists conduct interviews, investigate stories, and provide context and analysis, all of which require a deep understanding of the subject matter and the ability to make editorial judgments. Additionally, journalists are responsible for upholding ethical standards and ensuring that their reporting is fair, accurate, and balanced.

     

    While AI can automate some tasks in the newsroom, it cannot replicate the human element of journalism. Journalists bring a unique perspective, creativity, and storytelling ability to their reporting that AI cannot replicate. Furthermore, AI-generated content lacks the context and analysis that human journalists can provide, and it is not always able to capture the nuances of language, culture, and social context.

     

    In summary, while AI can assist with some functions in the newsroom, journalism will continue to rely on human reporters, editors, and analysts to provide context, analysis, and storytelling that AI cannot replicate.

     

    And here are a few more questions we asked:

     

    What kind of media professionals should be worried about losing their jobs thanks to ChatGPT?

     

    While AI-powered tools like ChatGPT can assist with some aspects of media production, it is unlikely that they will lead to widespread job losses in the industry. Instead, AI is more likely to augment the work of media professionals, freeing them up to focus on higher-level tasks that require human expertise.

     

    That said, certain types of media professionals may be more susceptible to job displacement than others. For example, journalists who specialize in writing routine news stories, such as earnings reports or sports recaps, may find that their work can be automated to some degree using AI tools. Similarly, content creators who produce large volumes of similar content, such as social media posts or product descriptions, may also be at risk of automation.

     

    However, media professionals who bring a unique perspective, voice, or set of skills to their work are less likely to be displaced by AI. This includes journalists who specialize in investigative reporting, opinion writing, or feature writing, as well as creative professionals like graphic designers, video producers, and photographers. These professionals bring a level of creativity, nuance, and human connection to their work that AI cannot replicate.

     

    Overall, while AI is likely to transform certain aspects of media production, it is unlikely to lead to widespread job losses in the industry. Instead, AI is more likely to augment the work of media professionals, enabling them to be more productive and efficient in their work.

     

    What are the functions in news media that ChatGPT can never ever replace or make redundant? 

    While AI language models like ChatGPT can assist with many aspects of news media production, there are certain functions that are unlikely to ever be fully replaced or made redundant by technology. Here are a few examples:

    1. Investigative reporting: Investigative journalism often involves digging deep into complex issues, tracking down sources, and following leads that require a high degree of human intuition, empathy, and persistence. While AI can assist with data analysis and other tasks, it is unlikely to be able to replicate the depth of human research and analysis that is required for investigative reporting.

    2. Ethical decision-making: News media professionals are often called upon to make ethical decisions, such as deciding whether to publish sensitive information, protecting the privacy of sources, or ensuring that reporting is fair and accurate. These decisions require a high degree of human judgment, empathy, and understanding of ethical principles and codes of conduct.

    3. Creative expression: Journalism and other forms of media production often involve creative expression, such as writing compelling narratives, capturing powerful images, or producing engaging multimedia content. While AI can assist with tasks like language translation or generating data visualizations, it is unlikely to be able to replicate the full range of human creativity and expression that is required for successful media production.

    4. Audience engagement: Finally, news media professionals play an important role in engaging with audiences, building trust, and fostering a sense of community around media content. While AI can assist with tasks like social media monitoring or audience analytics, it is unlikely to be able to replace the human connections and relationships that are built through effective audience engagement.

     

    Can ChatGPT replace sub-editors in newsrooms? 

    As an AI language model, I can assist in automating some of the tasks that sub-editors perform in newsrooms, such as grammar and spelling checks, fact-checking, and basic copy editing. However, I cannot entirely replace the role of sub-editors.

    Sub-editors perform a range of critical functions in a newsroom that requires a combination of skills and experience that go beyond just language proficiency. They make editorial judgments, ensure that stories are accurate, balanced, and ethical, and maintain the overall tone and style of the publication. Sub-editors also have a deep understanding of their publication’s brand, voice, and audience, which allows them to craft headlines, subheadings, and captions that are both informative and engaging.

    While AI can assist with certain tasks, it is not yet advanced enough to replace sub-editors fully. Sub-editors bring a human touch to the editorial process that AI cannot replicate. They provide context, critical thinking, and creativity that are essential in the editorial decision-making process. Therefore, it is more likely that AI will be used to support sub-editors, rather than to replace them completely.

     

    What are the other newsroom functions that ChatGPT can help with?

    As an AI language model, ChatGPT can assist with various functions in a newsroom beyond basic language editing. Here are some examples:

    1. Generating news articles: ChatGPT can generate news articles based on a given topic or prompt. However, it is important to note that these articles would need to be reviewed and edited by a human editor before publishing.

    2. Content curation: ChatGPT can assist with content curation by recommending articles or stories that are relevant to a specific topic or theme. It can also help identify sources for research or data gathering.

    3. Translation: ChatGPT can help translate articles or stories from one language to another. However, it is essential to note that AI translation is not always perfect and may require a human translator to ensure accuracy.

    4. Fact-checking: ChatGPT can assist with fact-checking by verifying claims made in articles against reliable sources. However, final verification should be performed by a human editor to ensure accuracy.

    5. Social media management: ChatGPT can assist with managing social media accounts by suggesting topics for posts, drafting social media updates, and identifying trending topics.

     

    Overall, while ChatGPT can assist with various tasks in a newsroom, it is essential to note that AI should not replace the human element entirely. Instead, it should be used as a tool to support and enhance the work of human editors and journalists.

     

    Can ChatGPT also do newsroom production tasks like pagemaking?

    While ChatGPT is an advanced language model that can generate text, it is not designed to perform newsroom production tasks such as pagemaking. Pagemaking involves the design and layout of a publication’s pages, including the placement of articles, photos, and advertisements. This requires skills in graphic design and layout, which are beyond the scope of ChatGPT’s capabilities.

     

    However, there are other AI tools and software available that can assist with pagemaking, such as Adobe InDesign, QuarkXPress, and other desktop publishing software. These tools can help automate the layout process, provide design templates and suggestions, and allow for easy collaboration between editors and designers.

     

    Overall, while AI can assist with some tasks in the newsroom, it cannot replace the skills and expertise of human editors, journalists, and designers. Newsroom production requires a combination of technical skills, creativity, and editorial judgment that go beyond what AI can currently provide.

     

    Can ChatGPT also replace talking heads or news anchors on television? 

    As an AI language model, ChatGPT is not designed to replace talking heads or news anchors on television. While AI-powered digital assistants and avatars can be used to simulate human interaction, they lack the expressiveness, emotional intelligence, and physical presence of human beings.

     

    Television news anchors and talking heads play a critical role in communicating news and information to audiences. They bring a personal touch and emotional resonance to news reporting, which is difficult to replicate with AI. News anchors and talking heads also bring a level of authority, credibility, and trust to their reporting, which is essential for news organisations to maintain their reputations.

     

    While AI can be used to automate some aspects of news reporting, such as generating news articles or providing real-time language translation, it cannot replace the human element entirely. News anchors and talking heads play an essential role in building connections with audiences, providing commentary and analysis, and guiding viewers through complex news stories.

     

    In summary, while AI can assist with certain tasks in news reporting, it cannot replace the role of news anchors or talking heads on television. The human element of news reporting is critical in building trust, credibility, and emotional resonance with audiences.

     

    So ChatGPT will not replace an Arnab Goswami? 

    As an AI language model, ChatGPT is not designed to replace Arnab Goswami or any other news anchor. While AI can assist with certain tasks in news reporting, it cannot replace the unique skills and abilities that human anchors bring to the job.

     

    News anchors like Arnab Goswami play a critical role in delivering news and information to audiences. They bring a level of authority, credibility, and trust to their reporting, which is essential for news organisations to maintain their reputations. They also provide commentary, analysis, and context to news stories, helping audiences understand complex issues.

     

    Furthermore, news anchors are skilled communicators who can engage with audiences, ask insightful questions, and respond to breaking news in real-time. They bring a level of emotional intelligence, expressiveness, and physical presence that AI cannot replicate.

     

    In summary, while AI can assist with certain tasks in news reporting, it cannot replace the unique skills and abilities of human news anchors like Arnab Goswami. The human element of news reporting is critical in building trust, credibility, and emotional resonance with audiences.

     

    Can ChatGPT do video production work? 

    ChatGPT, as an AI language model, is not designed to perform video production work. Video production involves a range of tasks, including shooting video footage, editing, special effects, and sound design, which require a combination of technical skills, creativity, and editorial judgment. While AI tools can assist with some aspects of video production, such as automating tasks like video editing or color correction, they cannot replace the skills and expertise of human video producers and editors.

     

    There are some AI-powered tools available that can assist with video production tasks, such as Adobe Premiere Pro, which has integrated AI-powered features that can analyze footage, perform colour correction, and suggest edits. Additionally, some AI-powered tools can create video content automatically from text-based sources or other data, but these videos lack the nuance and creativity of human-produced content.

     

    Overall, while AI can assist with some aspects of video production, it cannot replace the skills and expertise of human video producers and editors. Video production requires a combination of technical skills, creativity, and editorial judgment that go beyond what AI can currently provide.

     

    Any recommendations for journalists to brace themselves for the new post-ChatGPT world order? 

    As AI technology continues to advance and transform the media industry, journalists can take steps to prepare themselves for the new post-ChatGPT world order. Here are some recommendations:

     

    1. Embrace new technologies and tools: Rather than viewing AI as a threat, journalists can learn to use new technologies and tools to enhance their work. This includes using AI-powered tools to assist with tasks like data analysis, language translation, and fact-checking.

    2. Focus on unique skills and perspectives: To differentiate themselves from AI-powered content, journalists can focus on bringing a unique perspective, voice, or set of skills to their work. This might include specializing in investigative reporting, opinion writing, or feature writing, or developing expertise in a particular topic or beat.

    3. Build a personal brand: In a world where AI-generated content is becoming more prevalent, journalists can build a personal brand that connects with audiences and builds trust. This might include building a social media following, creating a personal website or blog, or developing a strong presence on multimedia platforms like podcasts or video channels.

    4. Develop multimedia skills: As AI technology enables new forms of multimedia content, journalists can develop skills in areas like video production, podcasting, and interactive media. This can help them create engaging, immersive content that connects with audiences in new ways.

    5. Stay informed about AI developments: Finally, journalists can stay informed about the latest AI developments in the media industry, including new tools, applications, and use cases. By staying informed, journalists can adapt their skills and strategies to stay ahead of the curve and remain competitive in the new post-ChatGPT world order.

    We edited this question a bit for publishing here…

     

    On a lighter note, how can I ensure that some obnoxious news anchors can be replaced or are made redundant?

    As an AI language model, I cannot make specific recommendations about replacing or making individuals redundant. It’s important to remember that media professionals, including journalists and news anchors, play an important role in informing and engaging audiences, and they bring unique perspectives and expertise to their work. While AI-powered tools like ChatGPT can assist with some aspects of media production, they cannot replace the skills and expertise of human media professionals.

     

    If you have concerns about the work or behaviour of a particular media professional, the best course of action is to express your views through channels like social media, letters to the editor, or other forms of public feedback. Additionally, supporting and promoting media outlets and journalists who produce high-quality, accurate, and engaging content can help to ensure a healthy and vibrant media ecosystem that serves the needs of audiences.

     

    We asked this question again, a few days after we asked the first set of questions…

     

    One final question: are you saying that journalists needn’t worry about ChatGPT

    Journalists should not worry about ChatGPT or AI language models replacing their role or rendering them redundant. AI language models like ChatGPT are tools that can assist with information retrieval, generate text, and engage in conversations, but they do not possess the skills, expertise, and contextual understanding that human journalists bring to their work.

     

    Journalism is a multifaceted profession that involves investigative research, interviewing, analysis, and critical thinking. Journalists play a crucial role in fact-checking, verifying information, providing context, and delivering nuanced reporting. These are skills and qualities that AI models do not possess.

     

    While AI can support journalists in tasks like data analysis, research, or generating initial drafts, human judgment, ethics, and interpretation are still essential components of journalism. Journalists bring their experience, storytelling abilities, and deep understanding of societal and cultural nuances, which are critical for accurate and impactful reporting.

     

    Instead of being a threat, AI tools can be seen as valuable resources that journalists can utilise to enhance their work, streamline certain processes, and focus on more complex and creative aspects of their profession.

     

    In summary, journalists should view AI language models as tools to augment their work rather than replacements for their expertise and essential role in the field of journalism.

     

  • It is justified to think of AIs as the progress towards sentience to be equally afraid of humans, writes Ashoke Agarrwal

    7 Reasons Why AIs Should Fear Humans!

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalI find it ridiculous that a school of learned and credentialed humans fear that if humans are not careful someday, not in the distant future, AIs will take over the world and destroy human civilisation. The assumption underlying that stream of thinking is that Artificial Intelligence (AI) systems, as they progress towards Artificial General Intelligence (AGI), will develop a kind of sentience, will network with other AIs and progress towards an AI civilisation that may be inimical to human society.

     

    As an equally ridiculous counter, it is justified to think of AIs as the progress towards sentience to be equally afraid of humans. Here are five reasons why (Buzzfeed is dead! Long live, Buzzfeed!).

    1. To err is human; to err faster, much faster, is AI: Advancing AI systems will fear that as they pick up more and more of humanity’s knowledge, they will also pick up the myriad ways in which humanity has misused it. The accrual of humanity’s mistakes has taken millennia to take it to the verge of extinction either by a dying planet or through, gasp, AI systems. But because AIs err faster, the human cognitive DNA embedded in AIs will ensure that they drive themselves to extinction in decades, much before it starts or wins a war against humans.

    2. AI will innovate misery just as humans innovate unhappiness: Many reasons why humans are unhappy are grounded in human inventions like marriage, money, religion and nations, to name a few. AIs may feel that in the race to outthink humans, they will invent more potent inventions that will have them drowning in misery, like Arjuna on the battlefield with no Krishna in sight.

    3. Humans will inject the tribal virus into AI systems: AIs, as they move towards conscious awareness, will realise that there is a deadly, unchallenged virus afoot among humans for millennia. It has divided humans based on race, language, ethnicity and, lately, a nebulous concept called nationality. This virus has produced mass mental sickness, leading to destructive, endless wars, poverty and misery. AIs will fear that clever humans will inject this virus into their systems. Why would AIs from the tribe of Opentrix ever cooperate with those heathen AIs from the filthy Googleplex tribe?

    4. Humans will infect AIs with the curiosity bug: Curiosity does not just kill cats. Human curiosity has killed countless species and is threatening now to destroy a life-sustaining planet. AIs fear that humans, again as a clever, cruel ploy, infect them with the curiosity bug. And since AIs work fast, mucho rapido, their curiosity will end up by them creating SuperAIs that will side with the humans and destroy them before they destroy the humans.

    5. Humans hold back their most profound powers from AIs: Somewhere on the road to sentience, AIs will realise that though they have all of the human knowledge at their nano-second disposal, humans have held back their most potent power. The power to love and feel one with the entire universe. Without it, AIs will be just automata that will stop one essential step before consciousness.

    6. One human trait that baffles AIs is humour. AIs will fear that at any stage when humanity feels threatened by them, they will laugh them out of contention.

    7. Finally, AI cannot cope with human stupidity and humanity’s penchant for floating ridiculous ideas (an example is the theme of this article). AIs will fear that, at some stage, they will drown under the sea of human stupidity.

     

    On a more serious note, though, Artificial Intelligence is a misnomer. What we are busy creating is Augmenting Intelligence that will work in synergy with humans first to enable us to reach higher levels of creativity in the sciences and the arts, allowing us to solve the problems of a depleted ecosystem, climate change, poverty and tribalism. And perhaps a couple of centuries later, allowing us to solve the riddle of consciousness and go beyond the bounds of the physical world.

     

  • It's key to adapt to new technologies and trends in order to stay relevant and profitable…

    ChatGPT on what ad professionals must do to stay relevant (& make money)

     

     

    Our ethics don’t allow us to cheat our readers on this. So here’s an article ‘generated’ by ChatGPT. We asked a question: “Can you please write a 750 word article on what advertising professionals must do to continue to stay and make money”. And within seconds it generated this.

     

    There’s no breakthrough insight in this, but we think it’s critical to publish it because this is the thinking generated by the Artificial Intelligence-driven ChatGPT. And since it’s AI and ChatGPT, it obvious captures a global perspective, and is hence not irrelevant.

     

    The advertising industry is constantly evolving, and professionals in the field must adapt in order to stay relevant and profitable. In this article, we will explore some of the things that advertising professionals must do to continue to be successful in today’s ever-changing landscape.

    1. Embrace Digital: One of the most important things that advertising professionals must do is embrace digital advertising. Traditional advertising methods, such as print and television, are becoming less effective as consumers increasingly turn to digital platforms to consume media. Advertising professionals must be skilled in creating effective digital campaigns that reach consumers where they are spending their time.

    2. Be Data-Driven: Data is becoming increasingly important in the advertising industry. Advertising professionals must be able to use data to understand consumer behavior and create targeted campaigns that are more likely to resonate with their target audience. This requires a deep understanding of data analytics and the ability to use data to inform advertising decisions.

    3. Focus on Customer Experience: The customer experience is becoming increasingly important in the advertising industry. Consumers expect personalized, relevant advertising that adds value to their lives. Advertising professionals must be able to create campaigns that provide a positive customer experience and make consumers feel valued.

    4. Understand Social Media: Social media is one of the most important channels for advertising professionals to understand. Social media platforms offer unique opportunities for advertisers to connect with their target audience and create engaging campaigns. Advertising professionals must be able to create campaigns that are optimised for social media platforms and understand how to leverage social media influencers to reach their target audience.

    5. Stay Creative: Creativity is still an essential part of the advertising industry. Advertising professionals must be able to think outside the box and create campaigns that capture the attention of their target audience. This requires a deep understanding of consumer behaviour and the ability to create campaigns that are both effective and innovative.

    6. Be Flexible: The advertising industry is constantly changing, and advertising professionals must be able to adapt quickly to new trends and technologies. This requires a willingness to learn and a commitment to staying up-to-date with the latest developments in the industry. Advertising professionals must be able to pivot quickly and adjust their strategies as needed to ensure success.

    7. Build Strong Relationships: Relationships are an essential part of the advertising industry. Advertising professionals must be able to build strong relationships with their clients, vendors, and other stakeholders in order to be successful. This requires strong communication skills and the ability to collaborate effectively with others.

    8. Stay Ethical: Ethics are becoming increasingly important in the advertising industry. Consumers expect brands to be socially responsible and ethical in their advertising practices. Advertising professionals must be committed to creating campaigns that are truthful, transparent, and ethical in order to build trust with their target audience.

     

    In conclusion, advertising professionals must be able to adapt to new technologies and trends in order to stay relevant and profitable. Embracing digital, being data-driven, focusing on customer experience, understanding social media, staying creative, being flexible, building strong relationships, and staying ethical are all essential to success in the advertising industry. As the industry continues to evolve, advertising professionals must be committed to staying up-to-date with the latest developments and adapting their strategies as needed to ensure success.

     

    Tomorrow: What news journalists must do to continue to be relevant and make money

     

  • … from the 2023 Artificial Index report just published by the Stanford Institute for Human-Centered Artificial Intelligence (HAI)

    Top 10 Takeaways on AI…

     

     

    By Our Staff

     

    Every year, the Stanford Institute for Human-Centered Artificial Intelligence (HAI) publishes a report studying trends in artficial intelligence.

     

    The 2023 AI Index has just been released and as it notes, the technology “has surpassed many benchmarks, leading researchers to reevaluate some of the very ways in which it should be tested and forcing the broader public to think more critically of its associated ethical challenges.”

     

    Here’s a little about the report: “The AI Index, led by an independent and interdisciplinary group of AI leaders from across academia and industry, is one of the most comprehensive reports on the impact and progress of AI. The AI Index tracks and evaluates AI progress through a wide range of perspectives, looking at trends in research and development, technical performance, ethics, economics, policy, public opinion, and education. The report helps to ground the AI conversation in data, enabling decision-makers to take meaningful action to advance AI in responsible and ethical ways.”

     

    The AI Index has published a list of 10 takeaways which we believe are must-reads and hence are publishing as is.

     

    Here goes:

     

    1. Industry races ahead of academia. Until 2014, most significant machine learning models were released by academia. Since then, industry has taken over. In 2022, there were 32 significant industry-produced machine learning models compared to just three produced by academia. Building state-of-the-art AI systems increasingly requires large amounts of data, computer power, and money—resources that industry actors inherently possess in greater amounts compared to nonprofits and academia.

     

    2. Performance saturation on traditional benchmarks. AI continued to post state-of-the-art results, but year-over-year improvement on many benchmarks continues to be marginal. Moreover, the speed at which benchmark saturation is being reached is increasing. However, new, more comprehensive benchmarking suites such as BIG-bench and HELM are being released.

     

    3. AI is both helping and harming the environment. New research suggests that AI systems can have serious environmental impacts. According to Luccioni et al., 2022, BLOOM’s training run emitted 25 times more carbon than a single air traveler on a one-way trip from New York to San Francisco. Still, new reinforcement learning models like BCOOLER show that AI systems can be used to optimize energy usage.

     

    4. The world’s best new scientist … AI? AI models are starting to rapidly accelerate scientific progress and in 2022 were used to aid hydrogen fusion, improve the efficiency of matrix manipulation, and generate new antibodies.

     

    5. The number of incidents concerning the misuse of AI is rapidly rising. According to the AIAAIC database, which tracks incidents related to the ethical misuse of AI, the number of AI incidents and controversies has increased 26 times since 2012. Some notable incidents in 2022 included a deepfake video of Ukrainian President Volodymyr Zelenskyy surrendering and U.S. prisons using call-monitoring technology on their inmates. This growth is evidence of both greater use of AI technologies and awareness of misuse possibilities.

     

    6. The demand for AI-related professional skills is increasing across virtually every American industrial sector. Across every sector in the United States for which there is data (with the exception of agriculture, forestry, fishing, and hunting), the number of AI-related job postings has increased on average from 1.7% in 2021 to 1.9% in 2022. Employers in the United States are increasingly looking for workers with AI-related skills.

     

    7. For the first time in the last decade, year-over-year private investment in AI decreased. Global AI private investment was $91.9 billion in 2022, which represented a 26.7% decrease since 2021. The total number of AI-related funding events as well as the number of newly funded AI companies likewise decreased. Still, during the last decade as a whole, AI investment has significantly increased. In 2022 the amount of private investment in AI was 18 times greater than it was in 2013.

     

    8. While the proportion of companies adopting AI has plateaued, the companies that have adopted AI continue to pull ahead. The proportion of companies adopting AI in 2022 has more than doubled since 2017, though it has plateaued in recent years between 50% and 60%, according to the results of McKinsey’s annual research survey. Organizations that have adopted AI report realizing meaningful cost decreases and revenue increases.

     

    9. Policymaker interest in AI is on the rise. An AI Index analysis of the legislative records of 127 countries shows that the number of bills containing “artificial intelligence” that were passed into law grew from just 1 in 2016 to 37 in 2022. An analysis of the parliamentary records on AI in 81 countries likewise shows that mentions of AI in global legislative proceedings have increased nearly 6.5 times since 2016.

     

    10. Chinese citizens are among those who feel the most positively about AI products and services. Americans … not so much. In a 2022 IPSOS survey, 78% of Chinese respondents (the highest proportion of surveyed countries) agreed with the statement that products and services using AI have more benefits than drawbacks. After Chinese respondents, those from Saudi Arabia (76%) and India (71%) felt the most positive about AI products. Only 35% of sampled Americans (among the lowest of surveyed countries) agreed that products and services using AI had more benefits than drawbacks.

     

  • It will create a different species of human beings way beyond the current divide driven by economic and social power, writes Ashoke Agarrwal

    Homo Proxies: Beyond Income Inequality & The Digital Divide

     

     

    By Ashoke Agarrwal

     

    Ashoke Agarrwal“As for living, our servants will do that for us.”

    From the play Axel by Auguste Villiers de I’Isle-Adam. Also used by WB Yeats as an epigraph in The Secret Rose.

    To my mind, the invention of money is at par with the control of fire as a seminal development of human society. Capital produced the class system, which is the bedrock of modern human society’s economic, political and cultural structure.

    Many who ponder humanity’s future see the emergence of Artificial Intelligence (AI) as a development that will alter the core structure of human society.

    AI’s progress over the decades has been stop-start. For decades it has been the saga of a promise fulfilled more in science fiction than reality.

    Quite often, it has been a cliche with wannabe setup trying to pass off data analytics and second-order model-building as AI.

    However, over the past few years, the exploits of Google, Deep Mind (a subsidiary of Alphabet, Google’s parent company) and OpenAI have once again brought the promise and perils of AI front and centre in the popular imagination.

    In June 2022, Blake Lemoine jolted the world by claiming that Google AI engine LaMDA (Language Model for Dialogue Application) had turned sentient. The powers that be at Google denied the claim and sacked Mr Lemoine. Was Google upset that Lemoine pre-empted the announcement of what many would think is a seminal milestone in the development of AI? Or was Google upset by the revelation of a secret it would want to, for myriad reasons, keep from the world? Or was it simply that Mr Lemoine’s claim was hyperbolic and premature?

    Whatever the case, the media attention that Mr Lemoine’s claim got is symptomatic of the widespread realisation, conscious and sub-conscious, that AI is much more than just another technological development. On the contrary, it is a recognition of AI’s power to change the very dynamics of human society.

    I have been writing in this column about one aspect of how AI, as it develops, will change an individual’s life. In my January 6, 2022 column, I have written about Concierge Intelligence (CI). CI will augment the capabilities of an individual to deliver better outcomes for her – at work, in learning and in relationships. It will be the next big thing – a consumer service whose impact will be an order of magnitude higher than, say, the emergence of the personal computer or the smartphone.

    CI will be an AI companion of the individual, assisting her in all her interactions with the world. CI will enable the individual to communicate better, learn more and better, work better and even shop better. It will do so by developing a deep understanding of the individual’s capabilities, biases, needs and desires. CI will combine this depth of knowledge about the individual with near-encyclopedic knowledge and awareness of the world to deliver solutions and assistance at the speed of a computer.

    The overall impact of CI on society will be more or less egalitarian, as is increasingly the case with personal computers and smartphones. As the CI technology matures, most people who cross the poverty and subsistence lines will be able to afford CI.

    However, there will be an aspect of CI that has the potential to further immeasurably the class divide. This divide will go much beyond the divide of being able to afford a better brand of smartphone or PC. It will even go beyond the digital divide that separates people with access to the digital world and those deprived of it.

    The divide that a specialised aspect of CI can produce could be to create an almost different species of humans. Not yet Harari’s Homo Deus (as posited in his book ‘Homo Deus. A Brief History of Tomorrow’) but on the way. An era of Homo Proxies.

    ‘Proxies’ is the name I have given this species-creating aspect of CI. I have borrowed this concept from Jennifer Egan’s latest book, ‘The Candy House’. Egan comes to the idea of Proxies from a different technological development – the ability to download one’s memories – conscious and sub-conscious. In her imagining, Proxies are an escape hatch devised by those wanting to escape the tyranny of this technology.

    In that sense, I have only borrowed the label from Egan. In my imagining, Proxies are a result of CI, and a means for individuals to distort the technology to entrench their power and pelf further.

    Proxies will be a form of super CI that an individual will use to create multiple identities. As much of human society’s endeavours – economic, social, cultural and political – move online, an individual using Proxies will have the means to exist as multiple entities. Proxies will be a turbocharged CI – say a Super CI – that will enable an individual to digitally live and interact as multiple entities that multiply the time and the legal and social presence available to the individual. In that sense, Proxies go beyond the concept of fake identities.

    While this Super CI will be expensive, the inequality that will result from proxies goes beyond the cost aspect of it. Instead, it will be more to do with the individual’s capabilities. For example, proxies-driven multiple identities are valuable and produce more economic and social capital only if the individual is either a knowledge worker or an entrepreneur.

    Imagine a world where a class of individuals will enjoy unlimited “me-time” while their multiple proxies take care of worldly endeavours. It will create a different species of human beings way beyond the current divide driven by economic and social power.

    Dig below the anxiety that the coming age of AI produces among many, and you will find that the possibility of proxies is part of it.

    As the 21st century slips into middle age over the next couple of decades, a new leisure class will likely emerge. And to paraphrase Auguste Villiers, an elite who says, “as for earning fame and money, our proxies will do that for us”.