MxMIndia

Tag: ChatGPT

  • On-Device Edge AI – The B2C AI Business Waiting to Happen

    On-Device Edge AI – The B2C AI Business Waiting to Happen

    Image generated with prompts to Meta on WhatsApp

     

    Ashoke AgarrwalAs the ChatGPT excitement fades away, the capital markets are beginning to wonder whether the LLM gold rush is a bust.

    Over the past two years, Big Tech – Google, Meta and Facebook – have sunk hundreds of billions of dollars each in training LLM models and continue to burn hundreds of millions more in inference computing every week as hundreds of thousands of users freeload (or pay pennies) to flood the model with queries that are mostly borne out of curiosity or laziness with not real economic, quality or productivity value add. Further, hundreds of angels and VCs have pumped billions into thousands of AI-driven or AI-adjacent start-ups.

    Although trillions of dollars have been invested in the LLM ecosystem, the business and economic case has yet to emerge.

    In the B2B segment, corporations are busy building machine learning (ML) models that sit atop their proprietary datasets and whatever other data they can access. The ML models (the line between ML and AI) are, in essence, semantic until the day AGI emerges. Predictive pattern building based on complex, structured data and signals will be at the heart of these models. These models will access available LLMs but at the periphery to absorb unstructured data and speed up documentation.

    In the academic and professional world of science and technology research, deep-learning-based ML/AI is an increasing reality. For example, AlphaGo is at the core of research into discovering and synthesising new proteins that will drive the cutting edge of genetics and drug discovery.

    By contrast, the economic case for AI in the B2C arena still needs to be clarified.

    The trillions being spent on creating LLM models and inference testing them by offering them free (or nearly free) to millions of consumers can be likened to the early days of optical-fibre-based bandwidth building, much before the emergence of the deluge of mobile Internet, video-sharing, and streaming. In the final years of the nineties and the early oughts, many wrote off the vast investments in the optical fibre network as white elephants.

    History proved otherwise.

    Device-based Edge AI will create an economically viable future for AI in the B2C arena. This future will be predicated on the investments being made today in LLMs, which have an exponentially increasing number of parameters, increasingly customised hardware and software, and a wide variety of specialist AI agents sitting atop increasingly capable LLMs. Breakthroughs in design will decrease the cost of specialist LLM cloud farms and their environmental impact through greater energy efficiency and better green energy solutions.

    The contours of the device-based Edge AI that will drive the emergence of a viable B2C market for AIs are beginning to emerge.

    Samsung and Google have launched smartphones that are touted to incorporate device-based AI. A slew of laptop brands are also touting AI credentials. However, by the use cases these brands tout, they are marketing gimmicks that harm instead of heralding the B2C AI era.

    Apple’s Intelligence could be the actual start of the device-based Edge AI (EAI) B2C era.

    The launch event of the iPhone 16 mentioned the phone’s AI capability but did not present any use cases. In all the usual slickness of the launch, what went almost unnoticed is that while the hardware and probably the operational software were on the phone, Apple Intelligence would be ready for the consumer to use only a few months down the lines. The reasons could be Apple’s philosophy of not putting out anything half-baked and even regulatory approval.

    Reading between the lines, Apple Intelligence (AI) is the first AI engine focused on deciphering the individual, unlike the written/spoken word, visuals, and video at large that the LLMs are focused on.

    Smartphones are rich repositories of an individual’s lifestyle, interests, attitudes, and behaviour–a finer-grained repository permanently etched. Further variables like smartwatches and fitness rings will continue to add vital data to this repository. With the individual’s permission, the on-device AI can capture more information from conversations, laptops, office computers, and the increasingly innovative IoT devices at home.

    A smartphone-based Edge AI can then be the counterpart of the LLM – the Deep Personal Model (DPM) that is continuously trained to predict and anticipate. An individual needs to interact with her and the world to meet them. For example, if an individual is preparing for an educational test, the DPM could decipher her areas of weakness, alert her to them and provide specific inputs to overcome them. It could create a section of the DPM, her avatar as her professional – an architect, a journalist, a management consultant. This professional avatar could handle her professional communications and routine tasks.

    Another use case is for the DPM to detect signs in her vitals and situational stress and correspond with her doctor’s professional DPM avatar to get remedial recommendations.

    The DPM could take over the essential consumer functions of anticipating and ordering products within set limits and in interactions with market-facing AIs that allow her to access all relevant market knowledge.

    Of course, the consumer will be in complete control of the DPM regarding what personal data it can access and what functions it can perform for the consumer. She would also have the option to turn off and turn on the DPM. She decides based on her perception of access and utility trade-offs.

    The DPM will be charged as a service, much like Apple, at various subscription levels. A few years into the emergence of device-based DPMs, the device could come free with a subscription to a DPM, making the DPM market the largest B2C category in the world.

    The crucial aspect of a DPM’s success is the assurance of privacy and control for the individual. That’s why the DPM must reside on the device, not the cloud. Equally important will be trust in the brand offering the DPM. Apple with its brand positioning on privacy and its track record on that aspect has a leadership advantage in that area

     

    PS: I first wrote about a concept called “Concierge Intelligence” in my first MxMIndia column published on Jan 6th 2022; thirty-two short months later, the idea of what I now call DPM seems to be around the corner.

  • Yes! OpenAI’s Sora could revolutionise marketing content creation

    Yes! OpenAI’s Sora could revolutionise marketing content creation

    By Omar H. Fares

    OpenAI’s new generative Sora tool has sparked lively technology discussions over the past week, generating both enthusiasm and concern among fans and critics.

    Sora is a text-to-video model that significantly advances the integration of deep learning, natural language processing and computer vision to transform textual prompts into detailed and coherent life-like video content.

    In contrast to previous text-to-video technologies, like Meta’s Make-A-Video, Sora is able to overcome limitations related to the type of visual data it can interpret, video length and resolution.

    From what OpenAI has demonstrated, Sora can generate videos of various lengths, from short clips to full-minute narratives, and in high definition, accommodating a wide range of creative needs.

    Although no official release date has been announced, Sora will likely be available to the public in the coming months, judging by OpenAI’s typical pattern of public releases. For now, it’s only available to experts and a few artists and filmmakers.

    How Sora works

    At the heart of Sora’s innovation is a technique that transforms visual data into a format it can easily understand and manipulate, similar to how words are broken down into tokens for AI processing by text-based applications.

    This process involves compressing video data into a more manageable form and breaking it down into patches or segments. These segments act like building blocks that Sora can rearrange to create new videos.

    Sora uses a combination of deep learning, natural language processing and computer vision to achieve its capabilities.

    Deep learning helps it understand and generate complex patterns in data, natural language processing interprets text prompts to create videos, and computer vision allows it to understand and generate visual content accurately.

    By employing a diffusion model — a type of model that’s particularly good at generating high-quality images and videos — Sora can take noisy, incomplete data and transform it into clear, coherent video content.

    Sora’s approach differs from CGI character creation, which requires extensive manual effort, and from traditional deepfake technologies, which often lack ethical safeguards, by offering a scalable and adaptable method for generating video content based on textual input.

    What does this mean for businesses?

    One of the most noteworthy aspects of Sora is its flexibility, as it supports various video formats and sizes, enhances framing and composition for a professional finish, and accepts text, images or videos as prompts for animating images or extending videos.

    The emergence of Sora presents key opportunities for businesses across different sectors. In the near future, there are two key areas that may have significant applications.

    The first area is in marketing and advertising. Just as ChatGPT has become a marketing and content creation tool, we can expect businesses to use Sora for similar reasons.

    With the public release of Sora, brands and companies will be able to create highly engaging and visually appealing video content for marketing campaigns, social media and advertisements.

    The ability to generate custom videos based on textual prompts will allow for greater creativity and personalisation, possibly helping brands stand out in a crowded market.

    The second area Sora could impact is training and education. Companies could use Sora to develop educational and training videos that are tailored to specific topics or scenarios. This could enhance the learning experience for employees and customers, making complex information more accessible and engaging.

    Other sectors, such as e-commerce, also hold promising potential for the future application of Sora. Retailers could create dynamic product demonstrations that effectively showcase products in a more engaging and interactive manner.

    This would be especially beneficial for companies that want to highlight specific aspects of products that might not be easily conveyed through static images or text, or for advertising products that require a detailed explanation.

    Sora could also significantly reduce the uncertainty associated with online shopping by facilitating virtual try-on experiences, allowing customers to visualize how a product, such as clothing or accessories, would look on them without the need for a physical fitting. This, in turn, could result in a better return on investment.

    What are the key challenges ahead?

    While there are key opportunities ahead, OpenAI, regulators and users need to carefully consider key factors that could pose challenges, including copyright issues, ethical concerns and the consequences of increased digital noise.

    With Sora’s ability to generate lifelike video content, there’s a risk of inadvertently creating videos that infringe on existing copyrights. OpenAI has already been sued several times over copyright infringement and intellectual property issues.

    OpenAI hasn’t disclosed where the data used to train Sora is from, but it did tell the New York Times it was training the system using videos that were publicly available and licensed from copyright holders.

    The technology also raises ethical questions, particularly around the creation of deepfake videos or misleading content.

    Establishing guidelines and safeguards to prevent misuse will be essential for maintaining trust in the technology. In a post on its website, OpenAI stated it was working with experts to test the model before releasing it to the public.

    As more businesses and individuals gain access to Sora, there’s a potential for an increase in low-quality or irrelevant video content, leading to increased “digital noise” that could overwhelm users. Finding ways to filter and curate content will become increasingly important for businesses looking to maintain their edge.

    Last, but certainly not least, is the question of how Sora will impact the job market for content creators. While Sora does have the potential to automate certain aspects of video production, like ChatGPT, it’s unlikely to replace human creativity and insight anytime soon.

    Instead, Sora could serve as a tool that enhances the capabilities of content creators, allowing them to produce higher-quality content more efficiently. As with any technological advancement, the key will be for professionals to adapt and find ways to integrate Sora into their workflows, leveraging its strengths to complement their own skills and creativity.The Conversation

     

    Omar H. Fares is Lecturer in the Ted Rogers School of Retail Management, Toronto Metropolitan University. This article is republished from The Conversation under a Creative Commons license. Read the original article.

  • As AI surges, tough times for news biz
    Representative photograph. Source: Wikimedia Commons

    As AI surges, tough times for news biz

    By Nic Newman

    News organisations are bracing for serious disruptions as a result of the increasing influence of artificial intelligence (AI) – both on the way that they work and the way their audiences consume news. As part of our latest journalism trends report, my colleagues and I at the Reuters Institute for the Study of Journalism found that less than half (47%) of 314 editors, CEOs and other digital leaders from more than 50 countries say they are confident about journalism’s prospects in 2024.

    The report details a tough period for the news industry over several years. A decline in online advertising, slowing growth in subscriber numbers and rapidly declining referrals from social media have fed into dramatic falls in revenue.

    Industry data shows that Facebook referrals alone fell by 48% in the past year, and many fear that search traffic will be next. Google and Microsoft, among other tech giants, are expected to roll out AI-driven, chat-based interfaces that have been trained on publisher content – mostly, or so the publisher of the New York Times alleges, without their permission.

    But it is not just internet search. We are also seeing a proliferation of conversational AI assistants built into computers, mobile phones and even cars that will change the way we discover and consume content of all types. Queries about the news are increasingly answered directly by the AI interface. Links to sources of the news on publisher websites, meanwhile, disappear into the background. As a result, far fewer audience eyeballs will find their way to each publisher’s site.

    Against that background, it is not surprising to find that some publishers such as AP and Axel Springer have already done deals with AI companies. The New York Times, meanwhile, is taking legal action over what it says was the unauthorised use of published work to train AI technologies.

    Many publishers hope that this time round, the outcome will benefit publishers of original and high-quality news and information. “There is an opportunity for the industry to work with AI players to design a symbiotic ecosystem and that’s an opportunity we must not squander,” says the chief operating officer of a leading UK news provider, who wishes to remain anonymous.

    Most publishers in our survey, however are not optimistic that this new phase of negotiations will work out well. More than one-third (35%) of respondents felt that only a few big media companies would benefit, while around half (48%) predicted that ultimately there would be little money available for any publisher.

     

    Publishers are not confident about funding from big AI companies

    Industry concerns are not just about money. More than two-thirds (70%) of respondents think that widespread availability of generative AI could reduce trust in the news. “The explosion of crap content definitely has the potential to shake the trust,” says Christoph Zimmer, chief product officer at German news company Der Spiegel.

    Zimmer highlights concerns about the use of deep fakes and other synthetic media, even as he hopes that the widespread availability of such second-rate content could also “allow [trusted] news media to differentiate ourselves more clearly”.

    Trying to adapt

    While the risks around business models, platforms and trust need to be managed, publishers know there are also significant opportunities to make their newsrooms more efficient. In our survey, we found the majority of publishers (56%) are focusing on back-end automation this year – using AI to help with copyediting, metadata creation and translation – with the next most common AI-related aim being identifying better ways to recommend content (37%).

    “The most compelling user case for AI in newsrooms is in the automation of routine tasks,” argues Ed Roussel, head of digital at The Times and Sunday Times. “We do not believe that AI is a substitute for reporting stories, which will continue to be done by journalists.”

     

    Which newsroom uses of AI will be most important in 2024?

    This focus on back-end automation is partly because news executives recognise the reputational risks in using AI for content. But that won’t stop others pushing ahead. Nordic publishers are routinely adding AI written summaries to their stories, while one German newspaper uses an AI robot to write 5% of its articles, albeit with human oversight.

    NewsGPT is the world’s first 24-hour TV news station created entirely by AI, and Channel1.ai, due to launch this year, promises a personalised news channel that can speak in any language.

    Rapid developments in AI are disrupting many industries, not just journalism, but news executives know they can’t just bury their heads in the sand. Rather than using AI to create volume, forward-thinking news organisations should be looking to build unique content and experiences that can’t be easily replicated by AI – think curating live news, deep analysis, and human experiences that build connection between audiences and the news provider.

    But they’ll also need to use AI technologies to make their businesses more efficient, as well as more relevant for audiences, in an era when many are turning away from the news.

    The impact of AI on the provision of online content in general is harder to predict. Much will depend on emerging public attitudes to the technology, but also on how responsibly the platforms that share this content behave. Equally important is the outcome of the legal cases around intellectual property, which could open up – or severely restrict – the way news content can be used for training AI models without proper compensation.

    We’re still at the early stages of the AI revolution but this is a year in which many of the rules and approaches are likely to be set. Against that background, journalists and news organisations need to proactively rethink their role and purpose with some urgency.The Conversation

     

    Nic Newman is Senior Research Associate, Reuters Institute for the Study of Journalism, University of Oxford. This article is republished from The Conversation under a Creative Commons license. Read the original article.

  • The New York Times’ lawsuit against OpenAI could have major implications for the development of machine intelligence, writes Mike Cook in The Conversation

    Will the NY Times lawsuit against ChatGPT’s owners impact the future of AI?

     

     

    By Mike Cook

     

    In 1954, the Guardian’s science correspondent reported on “electronic brains”, which had a form of memory that could let them retrieve information, like airline seat allocations, in a matter of seconds.

     

    Nowadays the idea of computers storing information is so commonplace that we don’t even think about what words like “memory” really mean. Back in the 1950s, however, this language was new to most people, and the idea of an “electronic brain” was heavy with possibility.

     

    In 2024, your microwave has more computing power than anything that was called a brain in the 1950s, but the world of artificial intelligence is posing fresh challenges for language – and lawyers. Last month, the New York Times newspaper filed a lawsuit against OpenAI and Microsoft, the owners of popular AI-based text-generation tool ChatGPT, over their alleged use of the Times’ articles in the data they use to train (improve) and test their systems.

     

    They claim that OpenAI has infringed copyright by using their journalism as part of the process of creating ChatGPT. In doing so, the lawsuit claims, they have created a competing product that threatens their business. OpenAI’s response so far has been very cautious, but a key tenet outlined in a statement released by the company is that their use of online data falls under the principle known as “fair use”. This is because, OpenAI argues, they transform the work into something new in the process – the text generated by ChatGPT.

     

    At the crux of this issue is the question of data use. What data do companies like OpenAI have a right to use, and what do concepts like “transform” really mean in these contexts? Questions like this, surrounding the data we train AI systems, or models, like ChatGPT on, remain a fierce academic battleground. The law often lags behind the behaviour of industry.

     

    If you’ve used AI to answer emails or summarise work for you, you might see ChatGPT as an end justifying the means. However, it perhaps should worry us if the only way to achieve that is by exempting specific corporate entities from laws that apply to everyone else.

     

    Not only could that change the nature of debate around copyright lawsuits like this one, but it has the potential to change the way societies structure their legal system.

     

    Fundamental questions

    Cases like this can throw up thorny questions about the future of legal systems, but they can also question the future of AI models themselves. The New York Times believes that ChatGPT threatens the long-term existence of the newspaper. On this point, OpenAI says in its statement that it is collaborating with news organisations to provide novel opportunities in journalism. It says the company’s goals are to “support a healthy news ecosystem” and to “be a good partner”.

    Even if we believe that AI systems are a necessary part of the future for our society, it seems like a bad idea to destroy the sources of data that they were originally trained on. This is a concern shared by creative endeavours like the New York Times, authors like George R.R. Martin, and also the online encyclopedia Wikipedia.

    Advocates of large-scale data collection – like that used to power Large Language Models (LLMs), the technology underlying AI chatbots such as ChatGPT – argue that AI systems “transform” the data they train on by “learning” from their datasets and then creating something new.

    Effectively, what they mean is that researchers provide data written by people and ask these systems to guess the next words in the sentence, as they would when dealing with a real question from a user. By hiding and then revealing these answers, researchers can provide a binary “yes” or “no” answer that helps push AI systems towards accurate predictions. It’s for this reason that LLMs need vast reams of written texts.

    If we were to copy the articles from the New York Times’ website and charge people for access, most people would agree this would be “systematic theft on a mass scale” (as the newspaper’s lawsuit puts it). But improving the accuracy of an AI by using data to guide it, as shown above, is more complicated than this.

    Firms like OpenAI do not store their training data and so argue that the articles from the New York Times fed into the dataset are not actually being reused. A counter-argument to this defence of AI, though, is that there is evidence that systems such as ChatGPT can “leak” verbatim excerpts from their training data. OpenAI says this is a “rare bug”.

    However, it suggests that these systems do store and memorise some of the data they are trained on – unintentionally – and can regurgitate it verbatim when prompted in specific ways. This would bypass any paywalls a for-profit publication may put in place to protect its intellectual property.

     

    Language use

    But what is likely to have a longer term impact on the way we approach legislation in cases such as these is our use of language. Most AI researchers will tell you that the word “learning” is a very weighty and inaccurate word to use to describe what AI is actually doing.

    The question must be asked whether the law in its current form is sufficient to protect and support people as society experiences a massive shift into the AI age. Whether something builds on an existing copyrighted piece of work in a manner different from the original is referred to as “transformative use” and is a defence used by OpenAI.

    However, these laws were designed to encourage people to remix, recombine and experiment with work already released into the outside world. The same laws were not really designed to protect multi-billion-dollar technology products that work at a speed and scale many orders of magnitude greater than any human writer could aspire to.

    The problems with many of the defences of large-scale data collection and usage is that they rely on strange uses of the English language. We say that AI “learns”, that it “understands”, that it can “think”. However, these are analogies, not precise technical language.

    Just like in 1954, when people looked at the modern equivalent of a broken calculator and called it a “brain”, we’re using old language to grapple with completely new concepts. No matter what we call it, systems like ChatGPT do not work like our brains, and AI systems don’t play the same role in society that people play.

    Just as we had to develop new words and a new common understanding of technology to make sense of computers in the 1950s, we may need to develop new language and new laws to help protect our society in the 2020s.The Conversation

     

    Mike Cook is Senior Lecturer, Department of Informatics, King’s College London. This article is republished from The Conversation under a Creative Commons license. Read the original article.

     

  • As ChatGPT turns 1, the AI chatbot’s success says as much about humans as technology, writes Tim Gorichanaz

    On ChatGPT’s first anniv, rejoice?

     

     

    By Tim Gorichanaz

     

    ChatGPT was launched on Nov. 30, 2022, ushering in what many have called artificial intelligence’s breakout year. Within days of its release, ChatGPT went viral. Screenshots of conversations snowballed across social media, and the use of ChatGPT skyrocketed to an extent that seems to have surprised even its maker, OpenAI. By January, ChatGPT was seeing 13 million unique visitors each day, setting a record for the fastest-growing user base of a consumer application.

     

    Throughout this breakout year, ChatGPT has revealed the power of a good interface and the perils of hype, and it has sown the seeds of a new set of human behaviors. As a researcher who studies technology and human information behaviour, I find that ChatGPT’s influence in society comes as much from how people view and use it as the technology itself.

     

    Generative AI systems like ChatGPT are becoming pervasive. Since ChatGPT’s release, some mention of AI has seemed obligatory in presentations, conversations and articles. Today, OpenAI claims 100 million people use ChatGPT every week.

     

    Besides people interacting with ChatGPT at home, employees at all levels up to the C-suite in businesses are using the AI chatbot. In tech, generative AI is being called the biggest platform since the iPhone, which debuted in 2007. All the major players are making AI bets, and venture funding in AI startups is booming.

     

    Along the way, ChatGPT has raised numerous concerns, such as its implications for disinformation, fraud, intellectual property issues and discrimination. In my world of higher education, much of the discussion has surrounded cheating, which has become a focus of my own research this year.

     

    Lessons from ChatGPT’s first year

    The success of ChatGPT speaks foremost to the power of a good interface. AI has already been part of countless everyday products for well over a decade, from Spotify and Netflix to Facebook and Google Maps. The first version of GPT, the AI model that powers ChatGPT, dates back to 2018. And even OpenAI’s other products, such as DALL-E, did not make the waves that ChatGPT did immediately upon its release. It was the chat-based interface that set off AI’s breakout year.

     

    There is something uniquely beguiling about chat. Humans are endowed with language, and conversation is a primary way people interact with each other and infer intelligence. A chat-based interface is a natural mode for interaction and a way for people to experience the “intelligence” of an AI system. The phenomenal success of ChatGPT shows again that user interfaces drive widespread adoption of technology, from the Macintosh to web browsers and the iPhone. Design makes the difference.

     

    At the same time, one of the technology’s principal strengths – generating convincing language – makes it well suited for producing false or misleading information. ChatGPT and other generative AI systems make it easier for criminals and propagandists to prey on human vulnerabilities. The potential of the technology to boost fraud and misinformation is one of the key rationales for regulating AI.

     

    Amid the real promises and perils of generative AI, the technology has also provided another case study in the power of hype. This year has brought no shortage of articles on how AI is going to transform every aspect of society and how the proliferation of the technology is inevitable.

     

    ChatGPT is not the first technology to be hyped as “the next big thing,” but it is perhaps unique in simultaneously being hyped as an existential risk. Numerous tech titans and even some AI researchers have warned about the risk of superintelligent AI systems emerging and wiping out humanity, though I believe that these fears are far-fetched.

     

    The media environment favors hype, and the current venture funding climate further fuels AI hype in particular. Playing to people’s hopes and fears is a recipe for anxiety with none of the ingredients for wise decision making.

     

    What the future may hold

    The AI floodgates opened in 2023, but the next year may bring a slowdown. AI development is likely to meet technical limitations and encounter infrastructural hurdles such as chip manufacturing and server capacity. Simultaneously, AI regulation is likely to be on the way.

     

    This slowdown should give space for norms in human behavior to form, both in terms of etiquette, as in when and where using ChatGPT is socially acceptable, and effectiveness, like when and where ChatGPT is most useful.

     

    ChatGPT and other generative AI systems will settle into people’s workflows, allowing workers to accomplish some tasks faster and with fewer errors. In the same way that people learned “to google” for information, humans will need to learn new practices for working with generative AI tools.

     

    But the outlook for 2024 isn’t completely rosy. It is shaping up to be a historic year for elections around the world, and AI-generated content will almost certainly be used to influence public opinion and stoke division. Meta may have banned the use of generative AI in political advertising, but this isn’t likely to stop ChatGPT and similar tools from being used to create and spread false or misleading content.

     

    Political misinformation spread across social media in 2016 as well as in 2020, and it is virtually certain that generative AI will be used to continue those efforts in 2024. Even outside social media, conversations with ChatGPT and similar products can be sources of misinformation on their own.

     

    As a result, another lesson that everyone – users of ChatGPT or not – will have to learn in the blockbuster technology’s second year is to be vigilant when it comes to digital media of all kinds.The Conversation

     

    Tim Gorichanaz is Assistant Teaching Professor of Information Science, Drexel University. This article is republished from The Conversation under a Creative Commons license. Read the original article.

     

  • With 78% feeling confident about using AI tools

    LinkedIn tables new research on AI acceptance by marketers

    By Our Staff

     

    New research from LinkedIn reveals marketers in India are ready to embrace AI with 78% feeling confident about using AI tools.

     

    The study reveals that the majority (83%) of marketers in India believe AI will significantly change the way they work in the next year, and nearly half (47%) hope it will help them to be more productive. The research also found that 93% believe AI will support their work and help create space for teams to think innovatively.

     

    AI will free up considerable time for marketers to build impactful creative campaigns

    As companies look to stay top of mind and leverage creativity to build memorability among audiences, AI will enable marketers to spend less time trying to find potential buyers, and more time on higher value work such as engaging with customers. Marketers plan to use AI for day-to-day tasks, such as summarising lengthy articles and videos (88%), creating first drafts of written content and presentations (82%), and helping them problem solve (83%).

     

    In India, 68% of marketers are using the technology today, with nearly half (45%) experimenting with tools such as ChatGPT. LinkedIn’s latest ‘B2B Marketing Benchmark’ report also finds that 87% of B2B marketing leaders in India plan to increase their use of generative AI in the next year.

     

    Said Ashutosh Gupta, Country Manager at LinkedIn India: “AI tools can work as great supporters for B2B CMOs by taking on operational tasks and creating room for marketers to focus on building strong customer relationships. Amid competing priorities and limited resources, AI empowers marketers to excel in strategic work, deepen customer connections, and create memorable campaigns that drive immediate action and fuel long-term business growth.”

     

  • The resultant hype around ChatGPT has kickstarted the age of Artificial Intelligence, writes Ashoke Agarrwal

    ML, LLM, Graphs & Market Modelling

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalNine months after the launch of ChatGPT, the hype has died down and the real work of building upon the burgeoning availability of Large Language Models (LLMs), of which ChatGPt is but one example, has begun.

     

    The interest of businesses in the concept of Big Data rose exponentially in 2012. Many expected a paradigm shift in consumer marketing based on nifty analytical systems driven by Big Data. Much was expected in data-driven decision-making, personalisation and customisation, targeted advertising, sharper segmentation, predictive analytics and real-time insights. In 2015, in its report titled ‘Big Data, Analytics and the Future of Marketing and Sales’,  McKinsey laid out the expectations.

     

    In 2023, the future is different from what McKinsey expected. The paradigm certainly shifted for Google and Meta, who cornered the advertising market based on a humongous amount of real-time Big data and state-of-the-art analytical engines.

     

    Change also happened for brands that marketed and sold products and services to B2C and B2B markets. However, the difference had little to do with their use of Big Data and advanced analytical systems. It was in the emergence of the digital universe as a product, go-to-market and communication platform.

     

    Dig a little, and you will find that the thesis that brands under-exploited the opportunity that Big Data presented to them mainly because they used legacy databases and ERP systems from the likes of SAP, Oracle and Salesforces to collect and store their Big Data. As a result, while many created special teams to mine, warehouse and analyse Big Data, most crucial business, marketing and sales decisions continued to be based on traditional business analysis and market research.

     

    Meanwhile, Google and Meta (then Facebook) invested in an analytical system that eschewed the rigidity of the traditional IT-age relational databases – essentially tables with rigid rows and columns. In a seminal decision that presaged the age of AI, they decided to populate their databases in graphs – a network of nodes with many properties with multiple links to other nodes, with each link specifying a kind of relationship with a property of the originating node and a property of the linking node.

     

    Such a database structure allowed for:

    :: Fast and more varied analysis

    :: More immediate additions and reconfiguration of the database as conditions change

    :: Better situational analysis and insight discovery through “what-if” analysis that changed node and link configurations

     

    Based on their ever-expanding, ever-enriched graphs and the use of Machine Learning (ML) driven near-real-time analysis, Google and Meta created a mighty advertising service with the confidence to offer brands a pay-per-click service. As a result, brands willy-nilly outsourced the harnessing of the real opportunity of the digital and Big Data age to Google, Meta and other digital ad exchanges that sprang up.

     

    It is no surprise that Google and Facebook are among the most advanced AI players today, including in the field of LLMs with Google’s Bard and Facebook’s Llama. The essential process that powers LLMs is that they parse large storehouses of text into triples of subjects, objects and predicates and then model them into graphs with the nodes consisting of subjects and objects and the links signifying relationships in the form of predicates.

     

    As Google’s and Meta’s LLMs improved power, it turbocharged their graph databases, allowing them to automate the process of incorporating unstructured into their graphs. Perhaps left to themselves, Google and Meta would not have exposed their LLMs to the public as they have done so now but kept it themselves as a background technology powering customer-facing applications. Instead, OpenAI and ChatGPT forced their hand.

     

    The resultant hype around ChatGPT has kickstarted the age of AI, with the world at large now seriously scrambling to incorporate AI into businesses, Governments, schools, hospitals and wars. Publications like The Economist and others have started ranking Fortune 500 companies based on the potential competitive advantages/disadvantages that AI can deliver to them!

     

    How will businesses in general and marketers in particular respond to the new horizons of AI?

     

    The powers of MI, Graph Theory and Advanced Modelling will create a new platform that will change how businesses, if not entire societies, are run. Just as the arrival of digital media changed economies at the core, Graphs with Big Data inputs from structured and unstructured sources (processed through LLMs) will create dynamic market models that will change how businesses are structured, with business and marketing strategy being almost wholly automated with human inputs needed only at the highest meta-strategy level. The shift will be paradigmatic enough for the world to label the resultant business order as the Nth Industrial Revolution, a sub-set of the First AI Revolution that will redefine human society.

     

    The question is whether individual businesses will seize this opportunity, invest and build proprietary dynamic models that will run their companies, or will they, once again, as they did with the digital revolution, outsource it to the next Google or Meta?

     

    The stakes this time are higher. Not only will the businesses themselves be more beholden to those who own and run the models, but in the process, society will create AI-driven behemoths that will be the first step to the dysfunctional system that those who fear AI imagine.

     

    Therefore, it is incumbent on business leaders and thinkers to pay close attention to this evolving opportunity and invest all that is needed to harness it before it becomes an insurmountable challenge.

     

  • ChatGPT and Threads reflect the challenges of fast tech adoption, write Omar Fares and Seung Hwan in The Conversation

    Engagement drops for ChatGPT & Threads, with reason

    Representative graphic. It doesn’t give the exact drop in engagement of ChatGPT and Threads

     

    By Omar H. Fares and Seung Hwan (Mark) Lee

     

    ChatGPT recently experienced a decline in user engagement for the first time since its launch in November 2022. From May to June, engagement dropped 9.7 per cent, with the largest decline — 10.3 per cent — occurring in the United States.

    Meanwhile, Meta’s Threads platform experienced a significant drop in user numbers, going from more than 49 million users on July 7 to 23.6 million active users by July 14. In the same time frame, the average time users in the U.S. spent on the app dropped from a peak of 21 minutes in early July to just above six minutes.

    In the tech world, companies are always racing to be the first ones to introduce new innovations, aiming for the “first mover’s advantage.” This refers to a firm’s ability to get a head start over competitors by being the first to enter a new product category or market.

    However, being a trailblazer doesn’t guarantee an easy ride. While there are perceived benefits, there are also a plethora of challenges that arise.

    A news story about what the drop in Meta Threads engagement means for the social media app.

    The recent declines of Threads and ChatGPT attest to this reality, demonstrating that rapid and widespread acceptance doesn’t necessarily lead to long-term success.

    There are a few reasons why a fast adoption isn’t necessarily the key to success including unsustainable growth, inadequate scaling infrastructure and a lack of user retention strategies.

     

    Unsustainable growth

    The idea of unsustainable growth stems from a platform’s inability to uphold or maintain the quality of the user experience while scaling up at a rapid pace.

    This is where the real challenge lies: being able to effectively scale up a product or service. It is precisely at this junction that the concept of unsustainable growth intersects with the Gartner Hype Cycle.

    The Gartner Hype Cycle is a model that shows the stages of emerging technology adoption: from the initial hype and inflated expectations, through disillusionment and skepticism, to practical and mainstream productivity.

    A line graph illustrating that Threads and ChatGPT both had a period of significant hype and inflated expectations, followed by a drop in user interest.
    A graph illustrating how ChatGPT and Threads fit into the Gartner Hype Cycle.
    (Omar H. Fares and Seung Hwan Lee), Author provided

     

    In the context of unsustainable growth, products like ChatGPT and Threads appear to have reached the stage known as “peak of inflated expectations,” where the publicity of a new product generates over-enthusiasm and unrealistic expectations. During this stage, users rapidly adopt the product due to its novelty and the hype surrounding it.

    However, this stage often leads to the “trough of disillusionment.” During this stage, the product fails to meet users’ unrealistic expectations, causing a decline in their interest.

    It indicates the product’s growth may have outpaced its ability to provide an excellent user experience. Without enhancing the product based on user feedback, declining user engagement will ensue.

    This rise and fall underscores the challenge of achieving sustainable growth in the face of rapid adoption. The initial hype often attracts a massive influx of users, but without a clear, scalable strategy for maintaining quality and engagement, platforms can quickly lose their appeal.

     

    Inadequate scaling infrastructure

    When a platform’s user base expands at a rapid pace, the question of whether that platform’s infrastructure can scale to the demands of its users becomes critical.

    The sudden influx of users that accompanies a successful product launch can be a double-edged sword; it brings a wealth of opportunities for data collection, user feedback and revenue, but also tests the scalability of the platform’s infrastructure.

    If the underlying technology, support services or operational strategies are not built to scale, the product might suffer from slow loading times, frequent crashes or a lack of timely customer support — all of which are detrimental to the user experience and a product’s long-term success.

    For instance, OpenAI, the company behind ChatGPT, had to limit ChatGPT-4 users to 25 messages every three hours due to infrastructure constraints — even for those with a paid membership. While this helps manage the infrastructure load, it presents a challenge from the user’s perspective.

    Users who were accustomed to unlimited interactions with ChatGPT-3 now find themselves paying for a service with limitations. This may inadvertently dampen user engagement and drive some users away, underscoring the delicate balance between managing infrastructure and maintaining user satisfaction.

     

    Lack of user retention strategies

    One reason why tech businesses struggle to retain users is because they don’t prioritize user-centered design. By failing to incorporate user feedback in product development, businesses can end up offering a product that doesn’t meet user needs.

    In addition, businesses must provide effective support for users. Insufficient or unclear onboarding may leave users feeling lost and overwhelmed, leading them to abandon the product. In the case of ChatGPT, OpenAI provides a basic explanation of platform usage, but users are primarily responsible for exploring it themselves.

    Users experiment with prompts without a clear understanding of how to generate impactful responses, resulting in uncertainty and frustration. This lack of guidance may contribute to lower engagement rates, as observed in the recent decline.

    Lastly, increasing concerns about security threats and privacy have raised questions about how new technologies are protecting their users. The conflict between the need for more personalized experiences and privacy can give rise to a phenomenon called the personalization-privacy paradox.

    As individuals grow increasingly uneasy about how their personal information is stored, the lack of proper regulations can lead to a decline in the use of personalised services or technologies.

    While rapid user adoption is a promising start, it doesn’t guarantee long-term success. Striking the right balance between growth and infrastructure scalability, adopting a user-centric approach, maintaining user trust and investing in continuous innovation are the cornerstones for enduring success in the competitive tech landscape.The Conversation

     

    Omar H. Fares is Lecturer in the Ted Rogers School of Retail Management, Toronto Metropolitan University and Seung Hwan (Mark) Lee is Professor and Associate Dean of Engagement & Inclusion, Ted Rogers School of Management, Toronto Metropolitan University. This article is republished from The Conversation under a Creative Commons licence.  Read the original article.

     

  • 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.

     

  • The rush to find good use cases for Generative AI is spawning a new class of start-ups, writes Ashoke Agarrwal

    Will 2025 be the year of the arrival of Concierge Intelligence?

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalSince OpenAI launched ChatGPT in November 2022, many have heralded (and some) feared the arrival of the age of Artificial Intelligence (AI)?

     

    The rush to find good use cases for Generative AI is spawning a new class of start-ups and keeping Angels and VCs busy.

     

    I have always thought the Information Age was a way-stop on the road to the Age of AI. I have also surmised that the Age of AI will amplify the gains and ills of the Information Age. However, being an eternal optimist, I have always focused on the good technology can do.

     

    In February 2021, in the gloom of the Covid lockdown, when the world had barely an inkling of what Generative AI was, I imagined a use case of AI I called Concierge Intelligence and published a blog post about it.

     

    Here are some excerpts from the post:

    “I believe one of the critical directions Artificial Intelligence will develop over the next decade is what I call “Concierge Intelligence”.

    Concierge Intelligence will go a long way towards fulfilling the initial promise of the digital age.”

     

    “The era of Concierge Intelligence will avoid the concerns raised by the age of marketing to bots like Alexa or Sirir that I wrote about in my post of April 25th 2018, titled “Marketing to Bots: The Coming Paradigm Shift?” 

     

    Concierge Intelligence will instead be the emergence of AI with an agency. The kind of agency that I wrote about in my post dated June 14th 2019, titled “Machine Intelligence to Machine Curiosity – The Route to Machine Creativity”, as also in my post dated December 19th 2019, titled “Should AI Have Agency.”

     

    The individual will buy his Concierge Intelligence (CI) – a software application -from the market and load on onto all the devices she uses. I believe CI will be the next big thing in consumer marketing. CI will get to work to learn the consumer’s interests and preferences. The individual will set the scope and depth of this learning. I can imagine the emergence of a new form of Yoga – CI Yoga! CI Yoga trainers will coach the individual on how to refine their CI settings for maximum well-being.

     

    CI will mediate between the world and the individual. It will map your learning patterns and maximize the speed and efficacy of your learning. It will continuously keep a tab on the individual’s inherent talents and emergent capabilities and connect her with opportunities to use these talents and abilities, in the process not just maximizing her earnings but increasing her sense of self-worth. It will perceive the individual’s relationship and leisure needs and help her meet them. One of the minor duties of CI will be as the gatekeeper to brands and services that seek to message and sell to the individual. While the CI will have powerful capabilities, it will be under the total command of the individual. She can change its functionalities whenever she wants and even switch it off if she so desires, much like today’s smartphones.

     

    Over the next decade, CI will become the most widely prevalent form of AI. I like to think of a CI as AI with a soul. A form of augmented intelligence that fuses an individual’s psyche, with all its complexity and humanity intact, with AI’s power, speed and reach.”

     

    My concept of CI has so taken hold of me that I even wrote about it in my first column for MxMIndia in January 2022, titled “The Coming Post-Digital World.”

     

    Post ChatGPT, the concept of an individual-owned and operated AI model is in the air. Sources in the VC world now tell me that a couple of start-ups are proposing systems close to the CI concept. While musings in blog posts do not give me any monetisable rights, I am glad that while some of my prognostications target a future too far out to find vindication in my lifetime, the CI concept will, in some measure, come true in the next couple of years. I would bet on Apple to be the company that will lead the world into the age of CI. Its current stance of developing AI systems that reside entirely on the user’s AI device and use user information without transmitting out of the device is a stepping stone to CI systems. Plus, of course, the fact that it is the most resourced company in the world and among the most trusted brands.

     

  • New technologies will always be fascinating but shall always remain the 'tool' of the marketer, writes Avik Chattopadhyay

    Tinker, tailor, marketer, sailor…

     

     

    By Avik Chattopadhyay

     

    Avik ChattopadhyayI attended a very interesting conference of CMOs yesterday. The one subject that took my fancy was that of “marketing in the era of technological disruption”. The panellists were CMOs from different industries, ranging from BFSI to consumer electronics, food and home improvement…from the totally digital to the totally physical consumer spaces. [I hate using the term ‘phygital’ as it sounds derogatory to both the spheres or spaces.] These people were in the thick of things, hemmed in between increasing personalisation and the rising head of AI and ChatGPT. I had some key takeaways from the session which I share here, as I believe these CMOs represent the larger community of marketers who chart the course that corporate India takes in building and nurturing brands and businesses.

     

    The role of the marketer fundamentally remains the same as before. The larger objectives remain the same while the ‘tools’ of the trade have certainly changed and proliferated. Given the rapid digital proliferation, the marketer now has to focus on reducing inefficiencies than ever before.

     

    While data is the ‘new oil’ and the ‘king’, it is easy to be burdened with tons of data without knowing what exactly to do with it. After all, the tasks of how to mine the data are also created by us humans, so anomalies may creep in till the time when AI totally takes over this job and we become mere implementors of orders from the ether. It is crucial for the marketer to draw the line between big data and usable data.

     

    Conversion continues to the biggest challenge for the marketer. While the funnel gets richer by the day, it narrows too soon leading to a rapid fall in % shares from prospect to customer. The marketer has to shift the focus of both the organisation as well as the investors from mere visitors / footfalls / followers to converts / advocates / consumers…basically from the passive base to the active base.

     

    The second biggest challenge is retention. As there is an overwhelming investment in getting customers, the required focus on retaining the existing base gets diluted on occasions. This is why the marketer has to look after the service aspect too, in terms of communication and engagement. We all know how expensive it is to get a new customer vis-à-vis retain one who gets more by word-of-mouth.

     

    The third biggest challenge is measurement. With the proliferation of channels and media, there is also an explosion of measurement systems, with each claiming to be the “right one”. The marketer looks forward to a single measure for all media and channels, and also a simplification of the process. Aspects like sustainability also need to feature in the measure, as it is a corporate regulation now. Both new media like OTT and traditional ones like OOH suffer from credibility issues when it comes to measurement.

     

    The use of jargon seems to bother today’s marketer. He / she wants the language to be simplified. Terms like “omnichannel” and “cohort” have been recklessly used to justify both esoteric strategy as well as on-ground non-performance. While the old guard would grapple with such terminology, the new-age CMOs do not fall for such smokescreens.

     

    The marketers agreed that every organisation has developed into a ‘software firm’ along with the business it conducts. Thankfully, learning tools have become more accessible and intuitive to allow people in marketing and sales to remain updated ‘over the air’. While AI and its tribe will take over the routine tasks of capturing data, processing it and churning out reports, the marketer will need much higher analytical and cognitive skills to use the reports for culling out insights. Will that mean that marketing teams will be down-sized? Remains to be seen. Will that mean that tools like ChatGPT will make the marketer dumb, as Harari fears? Not at all.

     

    As long as the human being continues to consume physical products, the focus on creating immersive sensory physical experiences will keep growing. The marketer has to create the smooth bridge “from the screen to the showroom”. After all, all e-commerce and q-commerce entities survive on delivering physical products from their physical warehouses. The bridge has to be intuitive, seamless and bespoke for each customer over a period of time. That is the final frontier in the career of a marketer.

     

    A new role added is to also keep a tab on competition or vested interests using technology to create deep fakes to damage your image and market. The same technology that holds us in awe, with its ability to insert a person into a video and put words in the mouths that never said them, can become a double-edged sword. We already have cases of deep fakes in advertising created to damage brand reputations.

     

    Finally, technology is not a disruptor but an enabler. It is the means and not the end. The marketer has to have complete control over it rather than become a victim of its whims. New technologies will always be fascinating but shall always remain the ‘tool’ of the marketer. How one uses it decides what one becomes of it.

     

    To draw inspiration from the childhood nursery rhyme,

    “Tinker, tailor, marketer, sailor

    Rich man, poor man, beggar man, thief!”

     

  • 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.