Rajesh Jain

Scott Brinker: “The vision for AI agents is the ability for a human to give them higher-level goals — “help turn leads from my website into open opportunities for sales” — and have them iteratively and autonomously do their own internal cycle of ask, answer, take action, repeat to achieve that goal. They can figure out on their own which responses to a web form should go into which nurturing campaign and which ones require a salesperson to be notified immediately. They can sync up all the right data across all the right systems. This isn’t far-off science fiction. This is already starting to happen today, with AI agents demonstrated in workflow automation tools. The technology is advancing quickly, and I expect that in a year from now, AI agents will be proliferating across the martech stack.”

Ambi Parameswaran: “Content marketing has gained traction among marketers over the last decade. Companies have been told they need to move beyond creating single ads or campaigns, and running them for extended periods. Consumers’ attention spans are narrowing; their field of vision is changing all the time with a variety of media clamouring for their attention. The customer’s decision journey is becoming more complex, requiring brands to create a constant stream of content to engage with their audience.”

Razeen Sally: “General rules of conduct are simple, transparent, nondiscriminatory, and negative: they tell actors what not to do, but otherwise leave them free to do as they wish. They are generally proscriptive, not prescriptive.” [via CafeHayek]

WaPo: “The Sims isn’t like other video games. Instead of inviting players to explore faraway fantasy lands or fight in imagined battlefields, the world of The Sims hews closer to reality. Through avatars called “Sims,” players build homes, have careers, form relationships and try on gender identities — all while meeting their basic needs, like sleep and hunger. Over 24 years, the game has evolved to include four main editions and dozens of expansion packs. Its latest edition has 88 million users, according to developer Maxis. There are even plans for a movie based on the cozy-quirky game.”

James Hartley: “If you care about poverty, then you should focus on encouraging positive views about high levels of wealth. A country with people who think positively about the wealthy is more likely to implement market reforms which will make it easier for people to generate wealth. As a nation gets wealthier, poverty will decline. After all, as Zitelmann notes, “it is not primarily the strong who need the market economy, because they will somehow manage in any system; it is the weak and the poor, whose only chance to improve their living conditions is in a free-market economy.””

WSJ: “Materials scientists have had limited success making composites affordable and accessible for decades, or possibly millennia—technically, they were invented by the Mesopotamians. The labor-intensive nature of their manufacturing has made them expensive, which has limited their application to a handful of areas where their advantages outweigh their costs, such as the aerospace industry. Now, thanks to new manufacturing techniques that can churn out composite parts quickly and cheaply, all of that is changing, and the results could be both profound and exciting…Shifting substantial portions of what we make and use from steel and plastic to composites—which are amalgamations of a variety of fibers, embedded in a variety of plastics—could bring new kinds of transportation, more terrifying weapons of war, and lighter and more durable smartphones, wearables and other consumer electronics. All of that is possible because composites, while they have their challenges, are often able to perform just as well as high-strength metal parts, but with a fraction of the weight. Composites are the reason modern jetliners are so fuel-efficient, and the entire wind-power industry would be impossible without enormous turbine blades made from composites.”

David Cahn: “A huge amount of economic value is going to be created by AI. Company builders focused on delivering value to end users will be rewarded handsomely. We are living through what has the potential to be a generation-defining technology wave. Companies like Nvidia deserve enormous credit for the role they’ve played in enabling this transition, and are likely to play a critical role in the ecosystem for a long time to come. Speculative frenzies are part of technology, and so they are not something to be afraid of. Those who remain level-headed through this moment have the chance to build extremely important companies. But we need to make sure not to believe in the delusion that has now spread from Silicon Valley to the rest of the country, and indeed the world. That delusion says that we’re all going to get rich quick, because AGI is coming tomorrow, and we all need to stockpile the only valuable resource, which is GPUs. In reality, the road ahead is going to be a long one. It will have ups and downs. But almost certainly it will be worthwhile.”

Ashu Garg: “The rise of generative AI has only increased the value of enterprise data. Previously, AI models could only handle highly structured text data. But now, unstructured data—images, PDFs, audio files, and more—is also fair game. According to MIT, this unstructured data accounts for a staggering 80-90% of all enterprise data. This “frontier data”—expert knowledge, workflow logs, multimedia assets, and so on—represents far more granular and domain-specific information than what’s publicly available on the internet. To put this in perspective, JPMorgan reportedly has 150 petabytes of data: a whopping 150 times the size of the dataset used to train GPT-4. The challenge for enterprises lies in figuring out how to organize, process, and marshal this data to build AI solutions. In doing so, they must weigh the benefits of training their own AI models against the risks of sharing their IP with outside providers, who have shown to be less than scrupulous with their data sourcing practices.”

Pratik Bhadra: “One channel that remains a consistent powerhouse is email. With an average return on investment (ROI) of $36 for every dollar spent as of 2020, it has one of the highest ROIs compared to other marketing channels. Moreover, it is estimated that 30% of total revenue for many North American brands will come from email in 2024. Email’s true strength lies in delivering highly targeted messages. You can craft personalized email experiences by segmenting your audience, using dynamic content, leveraging customer data for personalized recommendations and implementing automated triggers for timely, relevant messages. To get the most out of this strategy, I recommend including A/B testing and responsive design, ensuring your emails have clear CTAs, and maintaining engaging, value-driven content to foster loyalty and drive conversions.”

Karl Rove: “Some people today describe America as a third-world dystopian hellhole. That’s a slur. Though a flawed people, we’re also deeply compassionate and generous. We’ve built the world’s most innovative, prosperous economy. We cherish liberty and the rule of law. In this century, we’re the bulwark against tyranny in the world; in the last one, we rescued civilization at enormous cost. In return, we didn’t seek reparations, only enough land to bury our dead. The world knows it. Go anywhere and people understand the American dream. It means the opportunity to work hard, think big, live in liberty, and be part of a great and grand story. Sure, we have challenges, but still people around the globe want to invest, study and live here more than any other place on the planet. We’re a light of freedom and hope. If we forget that, we surrender an important part of what it means to be an American.”

Mint: “Meetings are essential for decision-making, aligning a team and fostering collaboration. However, to be effective, group meetings need to be well-structured. This includes having a clear agenda, defined objectives and ensuring the right people are in attendance. Avoiding unnecessary presentations and focusing on dialogue and decision-making can make them productive. But even before getting to ‘how best to run a meeting,’ we think it is important to answer two key questions. The first is whether there should be a meeting at all, or can the objective be met through an empowered individual (with inputs from others) or even in a group setting via email? This is even more relevant for recurring meetings, which start off with the right intention but then inertia takes over. The second is clarity on the desired objective of the meeting—is it to generate ideas, challenge solutions, take decisions, seek alignment or communicate with a broader group? Meetings can be set for any of these, but there needs to be clarity on what outcome is expected.”

NYTimes on UK exit polls: “Earlier exit polls sought to assemble a representative sample of voting places at each election, using the vote totals in the sample to predict shares for each party elsewhere. The new-style poll still looks for a representative sample, but it also returns, as far as possible, to the same polling places each time. Now, instead of focusing on the totals, the researchers can make direct comparisons and examine how the vote has changed. Using statistical models, they then project how the changes they find will play out in districts across the country, based on further analysis of the demographics and the previous election results in each area. The focus on the same locations is the critical thing, according to Jouni Kuha, a professor of social statistics at the London School of Economics who has worked on the exit-polling team since 2010. “There’s less noise in the data when you look at the changes than if you were trying to estimate the shares themselves,” he said in a telephone interview.”

FT: “In the past, new tech eras — such as the rise of client-server computing in the 1990s and cloud computing the following decade — have brought new waves of start-up software companies to the fore. New companies, their products and business models designed from the ground up to fit a new computing paradigm start with a big advantage. The first wave of these “AI native” software companies has often looked like little more than “wrappers” around the large language models, adding only a veneer of industry-specific expertise as they offer businesses ways to adopt generative AI. But they are all working hard to gain a foothold from where they can start to build out more compelling services. According to Salesforce’s Benioff, the incumbents will be hard to unseat. Companies such as his have become the repositories of their customers’ most important data, he says, giving them a big advantage when it comes to training the AI models that businesses will find truly useful.”

Ashu Garg: “Before writing their first line of code, Mohit [Aron] advises founders to pressure-test their ideas by articulating, in writing, exactly why their startup will succeed. This “hypothesis document” should include four sections: Elevator pitch: A concise, compelling description of your product that motivates potential customers to learn more. Minimum viable product (MVP): A crisp definition of the very first version of your product. Why it will work: A detailed explanation of why your product will sell and succeed in the market against competitors. This section should demonstrate a deep understanding of your target customers, their pain points, and how your product delivers unique value compared to existing solutions. “Why nots” and rebuttals: An honest assessment of the reasons a skeptic might give for why your startup will fail, along with strong counterarguments for each.”

NYTimes: “In many Asian economies over the last half-century, the rise of manufacturing has been a powerful force of upward mobility. Incomes rose, poverty lessened and working opportunities opened. Women were at the center of this transformation. In Vietnam, where a factory boom has been especially momentous, more than 68 percent of women and girls over 15 are working for some form of pay, according to data compiled by the World Bank. In China, the rate is 63 percent; in Thailand, 59 percent; and in Indonesia, 53 percent. Yet in India, less than 33 percent of women are engaged in paid work in jobs counted in official surveys…As multinational brands shift factory production from China, Indian women — long shut out of the work force — could be prime beneficiaries.”

WaPo: “The best leaders today need to be smarter about a wider range of topics than before. The years of the pandemic, geopolitical unrest, supply chain disruptions and partisan polarization have made clear how events seemingly far removed from a leader’s day-to-day portfolio can wreak outsize havoc on any organization. “They need to be lifelong learners,” Olson says, “not just stuck in whatever paradigm that they’re already in. Leaders now need to be able to adapt and to pivot. Sophisticated boards are looking for people who don’t only have the résumé qualifications, but also a level of EQ and intellect to be successful in an ever-changing world.””

Randy Barnett: “What libertarianism also needs is a theory of the second best. Libertarianism needs to be better accommodated to a nonideal world—aka, the real world—of competing nations. A libertarian approach to nationalism, for example, would take seriously the competition among differing forms of government that are better and worse from a libertarian perspective. It explains exactly why one should be proud to be an American based on the ideals for which it stands.”

NYTimes: “Like a globe-spanning tornado that touches down with little predictability, deep economic anxieties are leaving a trail of political turmoil and violence across poor and rich countries alike…The causes, context and conditions underlying these disruptions vary widely from country to country. But a common thread is clear: rising inequality, diminished purchasing power and growing anxiety that the next generation will be worse off than this one. The result is that citizens in many countries who face a grim economic outlook have lost faith in the ability of their governments to cope — and are striking back. The backlash has often targeted liberal democracy and democratic capitalism, with populist movements springing up on both the left and right. “An economic malaise and a political malaise are feeding each other,” said Nouriel Roubini, an economist at New York University.”

Andrej Karpathy: “We’re entering a new computing paradigm with large language models acting like CPUs, using tokens instead of bytes, and having a context window instead of RAM. This is the Large Language Model OS (LMOS).” [via Haider]

Business Standard: “The talent shortage or skills gap has been a persistent issue in the industry. A marathon general election and extreme heat have only exacerbated the problem. The shortage of skilled labour appears to have hit India’s engineering and capital goods firms the hardest. Industry executives attribute the shortage to a mix of India’s growing order book and increasing demand, while other factors impact the supply end. An executive who does not wish to be named says: “Not all labour is skilled, and those we skill, we tend to lose to markets like West Asia due to better pay. Preference for an air-conditioned work environment is another factor impacting labour supply for engineering firms.”” A possible solution from Niranjan Rajadhyaksha.

CNN: “Governments owe an unprecedented $91 trillion, an amount almost equal to the size of the global economy and one that will ultimately exact a heavy toll on their populations. Debt burdens have grown so large — in part because of the cost of the pandemic — that they now pose a growing threat to living standards even in rich economies, including the United States. Yet, in a year of elections around the world, politicians are largely ignoring the problem, unwilling to level with voters about the tax increases and spending cuts needed to tackle the deluge of borrowing. In some cases, they’re even making profligate promises that could at the very least jack up inflation again and could even trigger a new financial crisis.”

FT: “No economic model would have predicted stocks would be at all-time highs and credit spreads would be very narrow after the Federal Reserve raised its benchmark interest rate by 5.25 percentage points since early 2022. Yet, that is exactly what has happened. The Fed seems ready to declare victory in its fight against inflation, but the outperformance of highly speculative investments suggests that even such a sharp increase in interest rates hasn’t been a big enough mop to soak up the excess liquidity sloshing around the financial markets.”