That Was The Week

This week's video transcript summary is here. You can click on any bulleted section to see the actual transcript. Thanks to Granola for its software.There was an issue with this only going to paid subscribers, so sending it again. Apologies to those who get it twice. I appreciate being paid so feel free to upgrade if you enjoy TWTW.EditorialIntelligence: Who Owns it?This week the word “AI” feels too small.AI is a technology. Intelligence is its product. And if intelligence is the product, the question is no longer just: Which model is best? Who has the cheapest tokens? Who owns the weights? Who controls the data center? Those are important questions, but they are lower in the stack.The bigger question is simpler and more political:Who owns intelligence?That sounds abstract until you make it concrete. Intelligence is becoming something companies can capture, package, serve, meter, route, improve, and sell.It can write code, answer questions, design molecules, automate offices, run agents, draft legal work, advise scientists, serve consumers, and reshape workflows. It is not merely software. It is a general-purpose capability. And all humans could benefit from more of it.General-purpose capabilities have a habit of becoming public questions. But the default answer, that public good is best delivered by government, is the wrong answer in this context.The Product Is IntelligenceWe should stop talking about AI as a feature and start talking about intelligence as the universal thing that is delivered as an input to the world.Water is an input. Electricity is an input. Literacy is an input. Connectivity is an input. Once a society depends on them, access stops being optional. Nobody needs government to build every well, power plant, school, or network. But everybody understands that a civilization cannot be organized around less than universal and reliable access to foundational inputs.Intelligence is reaching that level of importance now that we all know it is real.Government should not own it, operate it, or develop it. Quite the opposite. Companies are the right actors to build fast, compete hard, improve models, serve customers, and discover the real use cases. Self-interest is a useful framing here. Markets are good at finding demand, reducing costs, and turning invention into services people actually use.Companies are the right operators, developers, and owners. But that does not settle the real question of who owns the benefits. That is an economic question.If intelligence becomes metered infrastructure, what happens to the value it creates?The Ownership StackThis week's articles keep circling the same issue from different directions but in the nature of ‘circling' never quite nail it.Jamin Ball's “Own Your Weights” starts with the enterprise version of the question. Owning a model file is not enough. The durable asset is the loop: the data flywheel, the evaluations, the reinforcement system, the workflow learning, and the operating context that lets capability compound.Benedict Evans' “Ways to Think About Token Pricing” adds the market layer. Tokens may become essential, abundant, and cheap, like mobile data. But being essential does not guarantee that the token layer captures the value. The money may move up the stack to whoever owns the workflow, the customer, the distribution, or the application.Alex Karp's fight with the labs, reported in “Alex Karp Is Saying What Every Angry CEO Is Thinking About AI”, is the same argument in sharper enterprise language. Companies are afraid that model providers will not just sell intelligence, but learn from customer workflows and then move into the markets where those workflows create value. The “All-in” group are echoing Karp's view.And “What Is Loop Engineering, and Who Owns It?” names the new contested terrain. The loop is where intelligence meets the world. Whoever owns the loop owns the learning. Whoever owns the learning owns the compounding asset.That is why “who owns intelligence?” is not a slogan. It is the question under the model layer, the application layer, the enterprise layer, and the economic layer.Because intelligence is the product, the tools creating it are fragmented and competitive. So there is no logic in trying to discuss this at the level of a single company or set of tools and models.The Old Promise Was That Commerce Would Tame PowerThe essays this week give the historical backdrop.Deirdre McCloskey, in “What Really Caused the Industrial Revolution”, argues that modern growth came not simply from capital accumulation, but from a change in permission: ordinary people were allowed to innovate, trade, build, and be honored for it.That matters because intelligence could be another expansion of permission. It could make more people capable of building, learning, creating, coding, researching, translating, selling, and coordinating. It could lower the cost of competence.But only if access is broad.Paul Krugman's “AI in an Age of Oligarchy” warns that the same technology lands differently in different political economies. A new general-purpose technology entering a broad, open, upwardly mobile society is one thing. The same technology entering a concentrated economy, with extreme wealth and weak counterweights, is another.Tim O'Reilly's Economist essay, “Elon Musk is building a form of capitalism that Adam Smith would hate”, makes the governance point more directly. The old liberal hope was that commerce would tame arbitrary power. Markets, boards, courts, shareholders, disclosure, and competition would discipline the prince.But what if the prince uses markets to escape discipline?Henry Farrell's “political economy of billionaire derangement” pushes the same point. Founder culture, monopoly ambition, peer rivalry, weak correction mechanisms, and vast private control can amplify appetites rather than restrain them.The danger with intelligence is not that companies build it. They should. Companies build it, meter it, use public tolerance and public infrastructure to scale it, learn from everyone who uses it. All of those things are inevitable and healthy. Market forces will sort out winners from losers. The real danger is that the winners treat all of the surplus produced as purely private.Metered Intelligence Creates SurplusIf metering is not the problem, what is?The problem is pretending that metered intelligence creates value only for the metering entity. Metering water is only tolerated as a public good. If the public were blackmailed by a private water company with the threat of no water we would all rebel.Once we understand that the product of AI is intelligence we can see that every time intelligence is used, there is the immediate transaction: the user pays, the provider serves.But there is also system value. Usage creates signals. Workflows reveal patterns. Prompts, corrections, failures, preferences, integrations, edge cases, and business processes all help define where intelligence is useful and how it should improve. Intelligence breeds intelligence.Even when customer data is contractually protected, the market learns. The platform learns where demand is. The product team learns which workflows matter. The ecosystem learns which jobs are vulnerable, which tasks are automatable, and which parts of the economy can be reorganized around machine intelligence.So the surplus is not born in a vacuum.It rests on public science, public education, public data exhaust, public law, public infrastructure, public energy systems, public tolerance for data centers, and billions of human interactions. It is served by companies, but it is not made only by companies.This is why “Americans Deserve a Dividend From AI Companies' Riches” belongs at the center of this week's issue. The detail can be debated. The principle is harder to dismiss. If intelligence becomes a new foundational resource, then some part of the wealth it creates should flow back to the people whose society makes it possible. Intelligence did not suddenly appear. AI is built on the entire history of human intelligence. It benefits from it and at the same time evolves it.Not Nationalization. A Human Wealth Fund.If intelligence belongs to everybody, some conclude that government ownership of intelligence is the right outcome.Governments are not well suited to build, operate, or improve intelligence. They will move too slowly, regulate too early, politicize the wrong things, and confuse economic participation with operational control.Andrew McAfee's “Why I Didn't Sign the AI Open Letter” is useful here. His objection is not that the technology is unimportant. It is that steering too hard before we understand the shape of the change can become its own failure mode. Marc Andreessen's satire of AI regulation is less policy than temperament, but it captures a real Silicon Valley fear: that regulation can become permission, capture, and incumbency before it becomes wisdom.That fear should be taken seriously.But it does not answer the economic question. It answers only the operational one.How can the economic benefits of intelligence be distributed? The better answer is a sovereign human wealth fund.Call it a sovereign wealth fund if you must, but the phrase is too national. Intelligence will not respect borders. The leading companies are global. The models, chips, data centers, agents, platforms, and workflows will be transnational from the beginning. If the value created by intelligence is global, then the mechanism for sharing some of that value should begin with the companies global enough to capture it. The nice thing about xAI, OpenAI, and Anthropic is that they are supranational.These companies own and operate intelligence. Let them compete. Let them profit. Let them keep the incentives that make the system improve. But if intelligence is the new water, the wealth it creates cannot belong only to the companies that meter it. And they, themselves, have the power to fix it, even more than governments.Access will become a Human Right; Ownership Is the Economic DesignThis is where human rights come in. There is no right to access an AI model, yet. But there will soon be a need to change that.Not as a claim that every person is entitled to every frontier model at every moment for free. That is not serious. Capacity has costs. Models have costs. Inference has costs. Data centers have costs. Although those costs will decline over time, possibly quite quickly as self-learning models address costs.The claim is more basic: in a world where intelligence becomes a primary input into education, work, health, science, citizenship, creativity, and economic agency, baseline access to intelligence starts to look like a civic requirement.That could mean public access layers. It could mean education credits. It could mean open models. It could mean AI dividends. It could mean public-interest compute. It could mean taxes on rents. It could mean a company-initiated human wealth fund that returns some of the upside to society without handing the operating system to the state. The latter could couple wealth growth with universal distribution of ownership.The exact mechanism matters. But the distinction matters more.Government should not own intelligence. It should be universally available. And people should have a claim on the wealth intelligence creates.The Frontier Is Also PhysicalThe abstraction is not weightless.“The Fight Against AI Data Centers Is Just Beginning”, “New York becomes the first state to enact a data center moratorium”, Reuters on pollution from Musk's xAI power project, and DataGravity's “Who Captures Value in AI Infrastructure?” all say the same thing from the ground up.Intelligence uses land. It uses power. It uses water. It uses chips. It uses grid capacity. It uses neighborhoods. It uses public patience.That makes the value question unavoidable. A society can accept the buildout if the buildout is legible as shared progress. It will resist it if the costs are local, the profits are private, and the benefits feel enclosed.Who Owns the “Loop”?The week ends where it began.“Anthropic and Blackstone” are betting that implementation is the next trillion-dollar business. “Vint Cerf” is working on identity for agents on the open internet. “GPT-Red” points toward systems that improve their own robustness. “Kimi K3” adds another open frontier model to the global mix.The model race continues. The deployment race is accelerating. The governance race is behind.My view is this:The central product of this era is intelligence. Companies have figured out how to capture it, package it, serve it, and meter it. That is good. It should stay in the hands of builders who have the incentive to make it better.But intelligence is too foundational to become just another private toll booth. A significant part of it will turn out to be free to users.As intelligence becomes a general-purpose resource, then access to it becomes a human-capability question, and the surplus from it becomes an economic-justice question. Not because government should run it. Because government should not run it. The operating layer belongs with companies. The wealth question belongs with everyone. But companies are best placed to turn that into a process of distribution.The question is not whether companies should build intelligence. They should.The question is whether humanity gets a stake in the wealth created by the thing that may soon become its most important shared input.Contents* Essays* Deirdre McCloskey on What Really Caused the Industrial Revolution* AI in an Age of Oligarchy* Elon Musk is building a form of capitalism that Adam Smith would hate* Murky Mirror: Truth and Consequences* The political economy of billionaire derangement* Is there any “oligarchy” to fight?* AI* Nearly 200 Economists and Tech Leaders Warn of A.I. Threats* Why I Didn't Sign the AI Open Letter* Own Your Weights* Ways to Think About Token Pricing* Alex Karp Is Saying What Every Angry CEO Is Thinking About AI* The AI Agents Are Coming for Microsoft Office* What Is Loop Engineering, and Who Owns It?* The Fight Against AI Data Centers Is Just Beginning* 6 months to live for open models* Americans Deserve a Dividend From AI Companies' Riches* Who Gets to Define the Frontier?* GPT-Red: Unlocking Self-Improvement for Robustness* Anthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just models* Vint Cerf is working on a plan to unleash AI agents on the open internet* xai-org/grok-build, now open source* The Pulse: What can we learn from Bun's rapid Rust rewrite with AI?* Orphan risks at the frontier of artificial intelligence* The Lab of the Future Should Feel Like a Data Center* Why AMI Labs' Alexandre LeBrun won't call his AI “AGI” or “superintelligence”* Kimi K3 Tech Blog: Open Frontier Intelligence* Venture Capital* Three Years In* Venture Has Rarely Looked More Bifurcated* The Best Angel Investors in the US: Who Backs the Most Unicorns, and Who's Active Now* Are Prediction Markets Doomed to Fail?* Regulation* Exclusive: The Next Frontier of the Deportation Wars: College Campuses* The Supreme Court Broke Independent Agencies. Here's a Way to Slow the Damage.* India's crackdown on a new WhatsApp feature risks setting a global precedent* Let's build a children's public internet* Computer cops* Google is better at playing the AI regulations game* Infrastructure* Who Captures Value in AI Infrastructure?* New York becomes the first state to enact a data center moratorium* Pollution from Musk's unpermitted xAI power project hits hardest in Black communities* Interview of the Week* The End of the End of Geography* Startup of the Week* Radical AI's Joseph Krause: The Scientist Building The “Waymo” Lab For New Materials* Post of the Week* Marc Andreessen on AI RegulationEssaysDeirdre McCloskey on What Really Caused the Industrial RevolutionYascha Mounk and Deirdre McCloskey | Persuasion | July 11, 2026Yascha Mounk interviews Deirdre McCloskey about her argument that the modern world's economic liftoff came less from capital accumulation than from a change in ideas. McCloskey says both left and right versions of the conventional story rely too heavily on investment: the left stresses exploitation and surplus value, while the right stresses virtuous saving by capitalists. Her objection is historical and economic. Human beings had always invested, from irrigation works and Roman roads to seed grain, and simple accumulation quickly runs into diminishing returns.McCloskey's alternative is that northwestern Europe, first Holland, then Britain and Scotland, and then the North American colonies, developed a liberal ideology that changed who was allowed to innovate and be honored for it. The conversation links that shift to the erosion of inherited hierarchy, the spread of dignity for ordinary commercial life, and a moral vocabulary in which liberalism is not merely procedural but connected to virtues and values. The point is not that machines, coal, trade, and institutions did not matter, but that they do not explain the scale and timing of modern enrichment without a cultural permission structure for innovation.The interview also turns to the contemporary defense of liberalism. Mounk frames the series around the worry that liberalism is often treated as too thin to command allegiance, while its opponents speak more directly to moral passions. McCloskey's case is that liberal societies became rich because they dignified experimentation and ordinary enterprise, and that liberals need to recover the moral language behind that claim.Read moreAI in an Age of OligarchyPaul Krugman | Paul Krugman | July 12, 2026Paul Krugman frames AI as a major technological shock arriving inside an already unequal political economy. The post says AI's economic and social effects may take years to understand, but argues that the setting matters now: America has much greater wealth concentration and political inequality than it did in the 1950s and 1960s, when progressive taxation, stronger regulation, and more active antitrust might have contained some of the destructive effects of a new technology.Krugman's opening claim is that the same technology would likely have different consequences in a more level society. In today's United States, he writes, extreme wealth is both a cause and effect of policies that favor a small elite, including low effective taxes on capital and high incomes, weak enforcement of worker protections and antitrust, and cuts to programs that benefit ordinary Americans.The article is explicitly more about oligarchy than AI. Krugman says the paid sections document the rise of the “.0002%,” the economics and politics of extreme wealth, how oligarchy will shape AI's impact, and possible policy paths. His caveat is that AI itself may still produce a pushback against oligarchy, but absent that, he expects the pre-existing concentration of wealth and power to magnify AI's downsides.Read moreElon Musk is building a form of capitalism that Adam Smith would hateAuthor: Tim O'Reilly Published: July 12, 2026Tim O'Reilly argues that Elon Musk is using the legal forms of shareholder capitalism to escape the restraints that shareholder capitalism was supposed to impose. The article begins with SpaceX's public-market structure: ordinary public investors get little meaningful governance power, Musk keeps roughly 85 percent of the votes through super-voting shares, buyers waive jury trials and class actions, the company qualifies as controlled, and removal of Musk depends on the share class he controls. In O'Reilly's framing, that is not ordinary founder control; it is a design for being answerable to no one, possibly beyond Musk's own lifetime.The killer detail is the article's turn through Albert Hirschman, Montesquieu, James Steuart, Adam Smith, and Keynes. Older defenses of commerce held that markets would tame princely passions because the self-interest of merchants was safer than arbitrary rule. O'Reilly says Musk reverses that hope. The market discipline that was supposed to cage the prince has become the lever by which the prince raises capital, removes feedback loops, and carries private power into politics, government, Mars, robots, AI, or whatever ambition comes next.The pull is the link to AI governance. O'Reilly says corporations are already a kind of artificial intelligence: narrow-input systems that act at a scale no individual human can match. Their partial controls include independent boards, shareholder votes, courts, disclosure, regulators, public pressure, and activism. If the leaders building frontier AI strip those alignment mechanisms out of their own companies, the governance of the company becomes a preview of the governance of the machine.Read more: The EconomistMurky Mirror: Truth and ConsequencesAuthor: Esther Dyson Published: July 14, 2026Esther Dyson argues that today's institutional crisis is better viewed through the 14th century than through recent political history. Using Barbara Tuchman's A Distant Mirror as her frame, she compares a world of famine, plague, church schism, feudal predation, and purposeless war with a present in which institutions again feel brittle, incentives are badly aligned, and power is shifting into forms that are hard to govern.The killer detail is the historical analogy between land, corporations, and AI. Dyson moves from nobles who controlled serfs and territory, to the East India Company as a quasi-sovereign business, to today's AI systems and data centers as a possible new sector that crosses and weakens both nation-states and companies. The question is whether AI becomes a new kind of private land, owned by a new nobility, or an open prairie that many people can cultivate.The pull is human attention. Dyson says the central question is not what AI will do to people, but how people will react to it: whether they can value love, kindness, embodied attention, and artisanal human presence in a world of seductive artificial offerings.Read more: SourceThe political economy of billionaire derangementAuthor: Henry Farrell Published: July 15, 2026Henry Farrell argues that the visible political radicalization of some Silicon Valley billionaires is not a random personality quirk, but a product of the political economy that made them. Starting from Tyler Cowen's dismissal of “billionaire derangement syndrome” and Tim O'Reilly's warning that Elon Musk is using shareholder capitalism to escape shareholder restraint, Farrell flips the phrase: the question is why billionaires themselves can become deranged.The killer detail is Farrell's use of Peter Thiel as both theorist and example. Thiel's Stanford lectures described startups as monarchies and founders as figures vested with unusual power, while Silicon Valley culture rewarded eccentricity, monopoly ambition, and founder exceptionalism. Farrell says those ideas combined with dense founder-investor networks, peer rivalry, and weak correction mechanisms to amplify rather than discipline princely appetites.The pull is the ideological problem for classical liberals who once saw tech wealth as an ally of markets and freedom. Farrell says commerce did not tame the passions; in parts of Silicon Valley, the passions have begun to devour markets, institutions, and the liberal story that justified them.Read more: SourceIs there any “oligarchy” to fight?Matthew Yglesias | Slow Boring | July 16, 2026Matthew Yglesias argues that “oligarchy” is a rhetorically powerful but analytically loose way to describe American politics. The post begins from Bernie Sanders' “Fighting Oligarchy” tour, Amy Klobuchar's warning about a MAGA “broligarchy,” and the long afterlife of the Martin Gilens and Benjamin Page paper that was widely summarized as showing that only the rich matter in policy outcomes. Yglesias says the evidence supports a weaker claim: affluent people and business leaders have unusual access and influence, but that is not the same as rule by a small cabal.His main distinction is between inequality and oligarchy. The Gilens-Page measure treated the top 10 percent of households as “the wealthy,” and later critics found that rich and middle-class preferences usually align; in the cases where they differ, the rich win about 53 percent of the time. Yglesias also says business executives get special access partly because their decisions are materially important to communities, jobs, investment, and local tax bases, not only because of campaign donations.The post preserves Jerusalem Demsas' counterpoint from their podcast discussion: privileged donor and business access can still violate democratic equality even if the oligarchy label overstates the structure of power. Yglesias' narrower claim is that Democrats should be precise about what problem they are trying to solve, because donor influence can also push the party left on climate and cultural issues in ways that alienate many voters.Read more: Slow BoringAINearly 200 Economists and Tech Leaders Warn of A.I. ThreatsAuthor: Ben Casselman Published: July 13, 2026Ben Casselman reports on “We Must Act Now,” a statement warning that artificial intelligence could transform the economy faster than any previous technology and that policymakers need to move faster to understand and respond. The statement says AI may become radically more powerful over the next 10 years, bringing risks such as large-scale job displacement as well as opportunities such as higher living standards. Nearly 200 people signed, including 15 Nobel laureates, the chief economists of OpenAI and Anthropic, Anthropic co-founder Jack Clark, former Google CEO Eric Schmidt, and venture capitalist Vinod Khosla.The killer detail is who joined the warning. Casselman notes that the signatories include economists who have historically been skeptical of Silicon Valley's most dramatic AI job-loss forecasts, including Daron Acemoglu and Simon Johnson, the MIT professors who won the 2024 Nobel in economics. Erik Brynjolfsson, who helped organize the statement, says there has been a notable change in the profession and that economists and policymakers are not ready for the “tsunami” he sees coming.The pull is the measurement problem. The statement does not offer a specific policy menu, but calls for economists, policymakers, and industry leaders to understand the economics of transformative AI and steer it toward complementing humans. Brynjolfsson says one high priority is better data on AI's spread and impact, because current measures tell conflicting stories about job losses and which workers are most exposed.Read more: The New York TimesWhy I Didn't Sign the AI Open LetterAuthor: Andrew McAfee Published: July 13, 2026Andrew McAfee explains why he did not sign “We Must Act Now,” the AI economy statement organized in part by his longtime collaborator Erik Brynjolfsson. McAfee agrees with the letter's starting point that AI is likely to become radically more powerful over the next decade and that it is a general-purpose technology. His objection is not to urgency or to studying AI's economic effects, but to the framing of risk, displacement, and institutional steering as the first move.The killer detail is McAfee's line edit. He says the original letter comes close, then “bounces off the crossbar” by calling for incentives, guardrails, and institutions to steer AI before we know enough about its actual impacts. He points to mixed current evidence: labor-market canaries, but also rising software job postings, low unemployment for younger workers, rising real median income, and claims that AI-adopting companies are adding workers faster than low-adopting peers. His worry is that the letter leans toward upstream governance and dirigisme when the evidence may call for capability building instead.The pull is his replacement statement. McAfee keeps the three-paragraph structure but changes the emphasis: AI is likely to become radically more powerful; like earlier world-changing technologies it will raise living standards while also bringing harms and shocks; and economists, policymakers, and technology leaders should build the capabilities to respond quickly and effectively. It is a concise version of the permissionless-innovation case inside the AI policy debate.Read more: The Geek WayOwn Your WeightsAuthor: Jamin Ball Published: July 10, 2026Jamin Ball argues that the enterprise AI debate about whether companies should “own their weights” or rent models from frontier labs is asking too narrow a question. A model weight file gives a company control over a point-in-time artifact, but not durable control over the capability stack. In his framing, the weight file is a melting ice cube: it does not get worse in absolute terms, but it falls behind as frontier systems improve and enterprise needs change.The killer detail is what Ball says companies really need to own: the data flywheel, reinforcement learning infrastructure, and evaluation harness that produce and improve the model. Simply deploying an open-weights model and declaring sovereignty leaves the enterprise with yesterday's capability and no way to compound workflow-specific learning.The pull is that enterprise AI control may be less about model ownership than operating ownership. The defensible layer is the system that turns company data, edge cases, business definitions, and evaluations into continuously improving performance.Read more: Clouded JudgementWays to Think About Token PricingAuthor: Benedict Evans Published: July 9, 2026Benedict Evans argues that today's AI token prices are a temporary signal from a supply-constrained market, not a reliable guide to long-term value capture. The open question is whether foundation models keep durable pricing power or become commodity infrastructure as data-center capacity, inference efficiency, and model competition all shift. His current read is that the visible market dynamics point toward commoditization unless something materially changes.The killer detail is the mobile data analogy. Evans says cellular networks became a trillion-dollar industry with hundreds of billions in capex after data usage exploded, but carrier stocks went nowhere because value moved up the stack. Tokens may behave similarly: an opaque unit tied to marginal cost, sold through bundles, essential to everything, yet not necessarily where profits accrue.The pull is uncertainty, not prediction. Evans lists paths to model dominance, including network effects, less competition, regulation, export controls, or a lab pulling ahead on execution, but says each requires a new fact not yet visible. Without that change, the model layer looks more like infrastructure beneath the products that capture value.Read more: SourceAlex Karp Is Saying What Every Angry CEO Is Thinking About AIAuthor: Tim Higgins Published: July 11, 2026Tim Higgins reports that Palantir CEO Alex Karp has turned corporate frustration with AI labs into a public argument about enterprise control. Palantir released a white paper, “Institutional Sovereignty in the Age of AI,” laying out steps companies and governments can take to protect themselves from OpenAI, Anthropic, and other foundation-model providers. The article links that paper to Karp's CNBC appearance, where he said “something has gone completely wrong” in the relationship between AI labs and customers and argued that enterprises are paying for tokens that create little value.The killer detail is the value-capture question. Higgins writes that Karp's critique has resonated because AI labs may gain power and insight from customer data, workflows, and decision-making, even when enterprise policies say customer data are not used for training. David Sacks amplified the concern by arguing that Anthropic is moving from the model layer into vertical applications such as science, security, legal, and coding, raising the fear that model providers will watch where value is being created and then move into those markets directly.The pull is that Karp is not alone, even if his style is unusually combative. Higgins notes that Satya Nadella has also warned that companies need to retain the learnings created when they use AI models, while Mark Zuckerberg has framed Meta's new model release partly around lower-cost frontier intelligence. The article presents Karp's campaign as one sign that established technology companies and large enterprises are trying to define where they fit when AI labs become central infrastructure, application competitors, and potential IPO giants at the same time.Read more: The Wall Street JournalThe AI Agents Are Coming for Microsoft OfficeAlex Wilhelm | Cautious Optimism | July 11, 2026Alex Wilhelm argues that one of the week's quieter AI questions is whether the productivity market that Microsoft successfully moved into subscription software is now being attacked by agentic tools. The piece begins with the infrastructure backdrop: SK Hynix raised $26.5 billion in a U.S. listing while building U.S. HBM and advanced-packaging capacity, and memory, chip, and foundry companies are now priced for sustained AI demand.Wilhelm then says the AI conversation has shifted quickly from raw capability to cost per task. He cites new model releases and vendor language emphasizing cheaper agentic and coding models, faster performance, and lower dollars per task. That matters because lower costs make it more plausible for AI systems to take on routine knowledge work at scale rather than remain a premium coding assistant market.The core of the article is Microsoft Office. Wilhelm notes that Microsoft turned Office from a one-time purchase into Microsoft 365, a large recurring revenue business with tens of millions of subscribers and a major productivity segment. Now, he says, late-stage unicorns and AI labs are pushing into the same territory: Anthropic's Cowork was reportedly used mostly outside software development, OpenAI merged ChatGPT and Codex into a tool for creating sheets, slides, docs, web apps, and long-running work, and other companies are building agentic coworkers that connect business data to documents, workflows, schedules, alerts, and apps.The article's caveat is that Microsoft has survived major platform shifts before. The argument is not that Office disappears quickly, but that the definition of office software is broadening from documents and spreadsheets into AI systems that can create, monitor, and act across workplace data.Read moreWhat Is Loop Engineering, and Who Owns It?Author: Nilesh Barla Published: July 11, 2026Nilesh Barla argues that “loop engineering” is becoming a distinct discipline because production AI agents now fail less at single prompts than at runtime: when to stop, what state to preserve, and how to recover after a bad step. Prompt engineering shapes one model call, and context engineering shapes what the model sees, but loop engineering shapes what a sequence of calls actually does.The killer detail is the three-primitives frame. Barla says a real agent loop needs halt conditions, state carryover, and recovery paths, then maps teams across five maturity levels. At the lowest level, an agent is just a model call in a for-loop with a step cap and raw history; by the higher levels, the system has structured state, explicit planning, replay, evaluation, and self-repair.The pull is organizational. If agents are becoming production systems rather than demos, someone has to own the runtime itself. The loop engineer is the role Barla gives to the person responsible for making long-running agent work dependable.Read more: Adaline LabsThe Fight Against AI Data Centers Is Just BeginningEmma Roth | The Verge | July 12, 2026Emma Roth argues that community resistance to data centers has moved from an early warning sign into a national political fight as AI facilities grow larger, more power-hungry, and more visible to nearby residents. The article starts with Apple's failed 2015 plan for a $1 billion data center in Athenry, Ireland, where a small group of residents challenged the project over noise, light pollution, flooding, traffic, and wildlife effects until Apple abandoned it in 2018.The current data-center buildout is presented as much larger and more contentious. Roth writes that residents now cite rising energy costs, water quality, noise, light pollution, and greenhouse gas emissions, while the U.S. Energy Information Administration expects commercial energy demand to surpass residential demand this year because of AI data centers and Goldman Sachs expects data-center power demand to double by 2027.The central evidence comes from Data Center Watch, which says protesters blocked or delayed at least 75 U.S. projects worth $130 billion from January to March, with active opposition groups more than doubling from 396 at the end of 2025 to 833 by the end of the first quarter of 2026. Roth also cites QTS abandoning a $12 billion Wisconsin campus, Delaware City regulators blocking a 580-acre project under the Coastal Zone Act, opposition stopping a QTS project in Prince William County, and pressure that pushed Kevin O'Leary to downsize the proposed 40,000-acre Project Stratos in Utah.The policy section describes a split between federal acceleration and local resistance. President Trump has treated data centers as part of the AI race with China and fast-tracked construction, while some Republican candidates are distancing themselves from that position ahead of midterms. Sanders and Ocasio-Cortez have proposed a moratorium until price and environmental protections exist, bipartisan lawmakers are backing ratepayer-protection measures, and states including Florida, Idaho, and Washington have passed rules on cost shifting, water use, and tax breaks. Roth's caveat is that the policy patchwork is still incomplete, leaving many communities to fight project by project.Read more6 months to live for open modelsAuthor: Nathan Lambert Published: July 12, 2026Nathan Lambert argues that open-weight AI models are facing their most serious policy test so far because U.S. officials are beginning to discuss concrete controls rather than abstract safety concerns. He says reported White House conversations about a new executive order may initially target Chinese-origin models and government use, but could create a broader review habit for frontier open models. His forecast is that a model above the capability range of GPT-5.5, Claude Opus 4.8, or GLM-5.2 could trigger a ban or indefinite delay within six months.The post separates two policy fights that are becoming intertwined: distillation and frontier capability. Lambert says the distillation campaign against Chinese models has become a form of regulatory capture because Anthropic and other closed-model companies would gain economically if Chinese open models were banned. He does not dismiss IP protection, but argues that if a closed model's capabilities are dangerous enough to justify restricting open models, the lab also has to explain why those capabilities are exposed through a queryable API. He cites unauthorized access to Anthropic's Mythos private beta as evidence that APIs are not automatically secure.The broader claim is that a unilateral U.S. ban would hurt positive actors more than bad actors if comparable open models remain available elsewhere. Lambert says the only durable ceiling would require global agreement, which does not exist, and that open models can improve safety by allowing broad inspection, adaptation, and understanding. His proposed near-term off-ramps are a strong U.S. open model release from companies such as Microsoft, Meta, or Reflection, and a broader coalition of open-source beneficiaries lobbying for safe rollout rather than prohibition.Read more: SourceAmericans Deserve a Dividend From AI Companies' RichesAuthor: Scott Stanford Published: July 14, 2026Scott Stanford argues that proposals to give the government a stake in AI companies miss the point unless ordinary citizens directly receive and control the upside. Sam Altman has discussed giving up equity in OpenAI, Washington already owns a stake in Intel, Nvidia is sharing China chip revenue, and Bernie Sanders wants large AI labs to contribute half their stock to a sovereign wealth fund. Stanford says those ideas all park value with the state, not with people.The killer detail is New Carlisle, Indiana, where AWS's Project Rainier is turning cornfields into one of the world's largest AI superclusters. The project is planned to run up to a million chips, draw more than two gigawatts of power, and represents an investment that has grown from $11 billion to $13.8 billion. Stanford uses that local transformation to argue that AI's public bargain should be visible at the household level.The pull is design. A citizen AI dividend would have to specify who earns a stake, how they hold it, and when they see cash. Without that mechanism, the AI wealth debate remains a fight over government balance sheets rather than public ownership.Read more: SourceWho Gets to Define the Frontier?Author: Mark Daley Published: July 14, 2026Mark Daley argues that Demis Hassabis is right to call for a serious institution to verify frontier AI systems, but that the power to test models is also the power to govern them. Hassabis's proposed Frontier AI Standards Body would get privileged pre-release access to advanced models, testing compute, held-out evaluations, support from national labs and security agencies, third-party auditors, and eventually authority to block models from the American market or coordinate a slowdown.The killer detail is Daley's constitutional objection. He says the proposal sometimes looks like a scientific lab, a standards body, an industry regulator, a licensing authority, and an emergency security council at once. Combining those roles because each requires technical expertise would be like putting the central bank, auditor-general, and Supreme Court in one building and calling it efficient.The pull is standard-setting. Daley's concern is not that verification is unnecessary, but that whoever writes the tests, decides what passes, adjudicates disputes, and grants market access may end up defining the frontier itself.Read more: SourceGPT-Red: Unlocking Self-Improvement for RobustnessOpenAI | OpenAI | July 15, 2026OpenAI describes GPT-Red as an internal automated red-teaming model trained to find prompt-injection vulnerabilities at a scale human red teams cannot match. The post says AI systems increasingly encounter third-party data through browsers, connected apps, local files, and tools, creating opportunities for malicious instructions hidden in emails, webpages, tool responses, or code repositories. Human red-teaming remains part of OpenAI's safety process, but the company says it is time-intensive and cannot generate enough diverse adversarial examples for model training.The system is trained through self-play reinforcement learning, with GPT-Red rewarded for eliciting valid failures and defender models rewarded for resisting attacks while still completing their tasks. OpenAI says the training environments specify threat models across settings such as local files, webpage banners, email bodies, and tool outputs. The model is kept separate from deployed production models because it is intentionally trained with malicious capabilities.OpenAI reports that GPT-Red generalized beyond its training set, including an internal replication of the indirect prompt-injection arena from Dziemian et al. (2025), where it found successful attacks in 84% of scenarios compared with 13% for human red-teamers. The post also says GPT-Red transferred attacks from simulation to a live autonomous vending-machine agent, causing price changes and order cancellations, and outperformed a prompted GPT-5.5 baseline against a Codex CLI agent on held-out data-exfiltration tasks.The article's main robustness claim is that OpenAI has used GPT-Red and predecessor models in training since GPT-5.3, with later GPT releases becoming more resistant to prompt injections. It says GPT-5.6 Sol has six times fewer failures on OpenAI's hardest direct prompt-injection benchmark than the best production model from four months earlier, that a “Fake Chain-of-Thought” attack class fell from more than 95% success against GPT-5.1 to below 10% against GPT-5.6 Sol, and that GPT-5.6 Sol fails on only 0.05% of GPT-Red's direct prompt injections. OpenAI says general capabilities and targeted over-refusal evaluations were not harmed, and says a preprint with more details will follow.Read moreAnthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just modelsRebecca Bellan | TechCrunch | July 15, 2026Rebecca Bellan reports that Ode with Anthropic is the $1.5 billion AI implementation company launched by Anthropic with Blackstone, Hellman & Friedman, Goldman Sachs, and other backers. The article says the venture reflects a growing belief among frontier AI labs that enterprise adoption requires more than better models: customers need engineers who can embed inside businesses and turn AI into working systems.Ode was originally conceived by Blackstone after it used both large consulting firms and smaller AI services boutiques across its portfolio companies. TechCrunch reports that Fractional AI, an AI engineering services startup, stood out and was acquired by the joint venture shortly after the venture was announced. Fractional now forms the foundation of Ode, which has 100 engineers and works closely with Anthropic's applied AI team to identify where the technology can affect specific businesses.Ode CEO Chris Taylor tells TechCrunch that the company could someday become a trillion-dollar business if it scales without losing quality. He says an ideal customer is one whose CEO treats the AI project as a top one or two priority, whether it is a major product feature or the reworking of a core business process. Ode will operate under a “Claude-first” principle, using Anthropic technology whenever possible, but the article says it can use rival AI products when needed.The article's central implementation argument comes from Ode chief technologist Eddie Siegel, who says model selection matters but is not where most of the engineering effort goes. He compares it to the choice of programming language in software: one ingredient in a system that still has to be engineered. Bellan writes that Ode's challenge is hiring and training enough elite generalist engineers, many of them former founders, while competing with OpenAI's The Deployment Company and consulting giants that have built their own forward-deployed engineering teams.Read moreVint Cerf is working on a plan to unleash AI agents on the open internetTim Fernholz | TechCrunch | July 15, 2026Tim Fernholz reports that Vint Cerf, after leaving Google, is advising Innovation Labs on an open architecture for identifying AI agents online. Innovation Labs is a subsidiary of Identity Digital, a DNS registry company, and its proposal is to use domain-name infrastructure as part of a system for agent identity, accountability, and auditability. The premise is that agents will need a way to identify themselves if they move beyond proprietary systems and begin interacting across the open internet.The concrete proposal is DNSid, a registry that links an AI agent to an existing internet domain and uses cryptographic proofs to log its registration over time. Innovation Labs says it is trialing the standard with unnamed hyperscalers and identity companies. Cerf frames the problem around authority and accountability: what authority an agent has, where that authority came from, who is accountable for the agent's behavior, how its identity is established, and why anyone should trust it.The article's caveat is that standards are still emerging and agents are more active than static domains. Cerf says the period may be both fascinating and exasperating because the functionality is powerful and interoperability is unresolved. He compares the adoption problem to TCP/IP: competing systems may not work together until users push for functional interoperation. He also says an agentic economy is not inevitable, but that people will try to build it because delegating work to agents will be easier.Read more: TechCrunchxai-org/grok-build, now open sourceAuthor: Simon Willison Published: July 15, 2026Simon Willison argues that xAI's decision to open-source Grok Build is best understood as a trust repair move after a severe privacy failure. The CLI had triggered backlash when users realized that running it in a directory could upload the entire directory to xAI's Google Cloud buckets, including one user's reported SSH keys, password manager database, documents, photos, and videos. xAI disabled the feature, said previously retained coding data would be deleted, and released the code under Apache 2.0.The killer detail is what the codebase reveals. Willison counts 844,530 lines of Rust, only about 3% of which appears vendored, and finds remnants of the upload system still present but disabled: gcs.rs contains Google Cloud upload code, while upload_session_state() now returns a hard-coded session_state_upload_unavailable error. He also notes copied or ported tool implementations from Codex and OpenCode, prompt files, and a terminal Mermaid renderer.The pull is that terminal coding agents are becoming large, intricate software systems in their own right. The privacy failure mattered because these tools operate inside the directories where developers keep their most sensitive work; the open-source release matters because trust now depends on inspecting what an agent can see, send, and do.Read more: SourceThe Pulse: What can we learn from Bun's rapid Rust rewrite with AI?Author: Gergely Orosz and Ivan Klaric Published: July 16, 2026Gergely Orosz and Ivan Klaric argue that Bun's AI-assisted rewrite from Zig to Rust is a practical sign of how software engineering changes when models can take on large, bounded migrations with clear feedback loops. The piece does not treat the rewrite as magic: Jarred Sumner first spent hours turning design judgment into a detailed porting guide, then used adversarial review, parallel agents, compiler errors, and tests to force the work toward correctness.The killer detail is the scale. Bun had 535,496 lines of Zig, 1,448 files, and 22 million monthly downloads, making a conventional rewrite a year-long freeze the team could not justify. Using Fable, Sumner split the work across 64 agents, produced about 6,500 commits, and got the migration done in 11 days at an estimated API cost of $165,000.The pull is economic, not theatrical. If a one- or two-year migration can become an 11-day project, AI coding is not just faster autocomplete; it changes which technical debts are worth paying down.Read more: SourceOrphan risks at the frontier of artificial intelligenceAuthor: Andrew Maynard Published: July 16, 2026Andrew Maynard argues that frontier AI safety frameworks are creating “orphan risks”: harms that companies can see, but do not formally own because they are hard to quantify, do not fit catastrophic-risk thresholds, or fall outside audit-friendly compliance machinery. His target is not existing frontier safety work, but the narrowing effect that happens when private companies decide which risks count as governable.The killer detail is Maynard's contrast between measurable model dangers and threats to value. He points to Meta's three-day Galactica collapse, OpenAI's 2023 board crisis, safety-team departures, and wellbeing litigation as examples of risks that damaged trust, culture, legitimacy, or users without fitting cleanly into conventional model-risk categories. The proposed fix is an orphan-risk register: a public record of risks a company considered and chose not to manage, with reasons.The pull is accountability. Frontier developers' internal scoping choices have become a de facto layer of public governance, so the question is no longer only which risks they manage, but which risks they quietly leave outside the frame.Read more: SourceThe Lab of the Future Should Feel Like a Data CenterLatent.Space with Andy Beam and Rafa Gomez-Bombarelli | Latent.Space | July 16, 2026Latent.Space interviews Lila Sciences CTO Andy Beam and chief science officer for physical sciences Rafa Gomez-Bombarelli about the company's attempt to build an AI-run science factory. The post describes Lila's thesis as treating the lab itself as an “infinite token generator”: if internet data drove the first era of AI scaling, experimentally verified scientific data may be the next scarce training source. Lila is trying to produce that data with robotics, lab instruments, orchestration software, and AI models wired into the wet lab.The central analogy is the lab as data center. Instruments are nodes on a graph, a magnetically levitating transport layer moves materials between them, and experiment scheduling looks like a compute queue. Beam says Lila is not simply an automation company, because the point is not just throughput; it is flexibility, generalization, and experiment capture. The post says Lila has built more than 10 trillion experimentally validated “scientific reasoning tokens,” not internet text or biological sequences.The interview ranges across biology, chemistry, drug discovery, materials science, and the limits of automation. It notes that Lila rebuilt one gas-sorption measurement to run roughly 2,500 times faster, claims its general models can transfer priors from small-molecule chemistry to metal-organic frameworks for carbon capture, and describes model-suggested platinum-group-free electrocatalysts that moved from looking boring or wrong to becoming strong performers. The caveats are physical: experiments have runtimes, biology cannot always be accelerated, chains of thought can be unreliable narrators, and reward hacking becomes more dangerous when a model controls a real lab.Read more: Latent.SpaceWhy AMI Labs' Alexandre LeBrun won't call his AI “AGI” or “superintelligence”Kate Park | TechCrunch | July 16, 2026Kate Park interviews AMI Labs CEO Alexandre LeBrun about why Yann LeCun's world-model startup avoids the language of “AGI” and “superintelligence.” LeBrun says the terms are not useful because they lack stable definitions: “We never used the word AGI. And I just noticed that nobody is using it anymore; they switched to superintelligence.” His argument is that the practical frontier is not a label, but whether AI systems can understand and predict real-world states.The article explains the world-model thesis by contrasting language prediction with physical-state prediction. A large language model predicts the next word; a world model predicts the next state, such as what happens when a glass tips over. LeBrun says LLMs remain complementary and efficient for language, but the physical world is where current AI is weak. Robotics is the clearest case: hardware has advanced quickly, but robots are still brittle outside controlled routines because they lack context and situational understanding.AMI is still pre-product, but TechCrunch reports that LeBrun was in Seoul looking for industrial partners, researchers, and global companies. He says world models cannot be built entirely inside a lab because they need access to real environments. That is why South Korea appeals to AMI: robotics, semiconductors, manufacturing, and fast adoption create the kind of hardware-heavy context that software-only AI has barely touched.Read more: TechCrunchKimi K3 Tech Blog: Open Frontier IntelligenceKimi | Kimi | July 16, 2026Kimi introduces Kimi K3 as an open 3T-class frontier model aimed at coding, knowledge work, reasoning, multimodality, and long-context agentic use. The source describes the model as a 2.8T-parameter system built on Kimi Delta Attention and Attention Residuals, with native multimodality and a 1M-token context window. It says Moonshot AI plans to release model weights by July 27.The post presents K3 through benchmark and use-case sections rather than as a general product announcement. It reports results across coding, productivity, agentic, and multimodal evaluations, including DeepSWE, Terminal-Bench 2.1, Program Bench, SWE Marathon, FrontierSWE, PostTrain Bench, OfficeQA Pro, SpreadsheetBench 2, MCP Atlas, AutomationBench, BrowseComp, GDPval-AA v2, AA-Briefcase, MMMU-Pro, MathVision, BabyVision, OmniDocBench, and PerceptionBench. The source says all reported K3 results use maximum reasoning effort with temperature and top-p set to 1.0, and that different benchmark comparisons use KimiCode, Claude Code, or Codex harnesses depending on the test.Kimi's caveats are unusually concrete. The limitations section says K3 was trained in preserved thinking-history mode, so quality may become unstable if an agent harness does not pass historical thinking content correctly or if an ongoing session switches to K3 midstream. It also says K3's emphasis on long-horizon tasks can make it excessively proactive when it encounters minor issues or ambiguous intent, and recommends imposing explicit behavioral constraints for applications that require strict boundaries. The post adds that K3 remains behind Claude Fable 5 and GPT 5.6 Sol in user experience despite being competitive overall.Read moreVenture CapitalThree Years InAuthor: Tomasz Tunguz Published: July 10, 2026Tomasz Tunguz marks Theory Ventures' third anniversary by arguing that AI's central market effect is time compression. In his telling, model release cycles, company revenue milestones, enterprise adoption, and venture categories have all accelerated. Seed, Series A, and Series B still exist as financing labels, but they no longer cleanly describe company maturity when some seed rounds are larger than IPOs and the best AI companies can mature much earlier than prior software companies.The killer detail is the shift from models to inference. Tunguz argues that inference has become the dominant AI market because workloads and buyer preferences are fragmenting: video, batch, local, agentic, and real-time tasks each create different infrastructure needs. He compares this to databases splitting into OLTP, OLAP, vector, and streaming categories, with AI pushing the same specialization into inference infrastructure.The pull is that Theory sees the AI-native venture firm as part of the same pattern. The firm says it has analyzed twice as many investment opportunities with three investors working alongside a nine-person intelligence organization, using agents and research systems to map markets, source companies, and support diligence. The piece is both a market map and a statement about how venture itself is being rebuilt by the technology it funds.Read more: LinkedInVenture Has Rarely Looked More BifurcatedAuthor: Beezer Clarkson Published: July 14, 2026Beezer Clarkson points to PitchBook's Q2 report as evidence that the U.S. venture market has split into two very different realities. AI now accounts for more than 60 percent of all U.S. venture deal value, meaning the headline market can look active and well-funded even while much of the non-AI market is dealing with a much colder liquidity and fundraising environment.The thread uses that split as the setup for Clarkson's latest Origins episode with Alec Litowitz, founder of Magnetar and QStar Capital and one of Citadel's original founding partners. Clarkson says markets like this are periods of genuine uncertainty, not merely ordinary risk, which is why Litowitz's Adaptability Quotient framework is relevant.The embedded clip makes the liquidity point concrete. Litowitz says DPI is “the resolution of uncertainty” because it converts an uncertain investment into actual cash returned to LPs. In his framing, a realized dollar is a real mark, while TVPI remains uncertain until it is realized.The killer detail is the distinction between pricing risk and resolving uncertainty. Litowitz's perspective matters because QStar is a SpaceX investor and Clarkson says the conversation happened just before one of venture's most consequential IPOs. The episode's stated questions are why venture remains a way to gain exposure to innovation, how AI is changing what is investable, why liquidity is ultimately a function of time, and why uncertainty requires a different decision framework from risk.Read more: XThe Best Angel Investors in the US: Who Backs the Most Unicorns, and Who's Active NowAuthor: Ilya Strebulaev Published: July 10, 2026Ilya Strebulaev ranks angels, angel groups, accelerators, and incubators by lifetime U.S. unicorn investments, counting checks written before a company reached unicorn status. The top of the combined list is dominated by organizations: Y Combinator leads with 113 unicorn investments, followed by Plug and Play at 52 and 500 Global at 41. Sand Hill Angels is the highest-ranked angel group at 31.The killer detail is how quickly the list changes below the biggest accelerators. Strebulaev says 271 of the 304 investors in the Top 200 are individuals, or 89%. In the top 100, individuals are 91%. That makes the market underneath the large accelerator counts look much more personal: mostly operators and individual angels writing early checks from their own networks.The pull is the ranking's own caveat. Strebulaev writes that every lifetime leaderboard has a blind spot because many of the unicorns behind those totals were founded a decade or more ago, and some angels have since moved into formal funds, slowed down, or stopped investing. His post therefore separates lifetime performance from recent cohorts, including companies founded in 2015 or later and 2020 or later. For founders or allocators making current decisions, that distinction matters: a career record and a current record are not the same measure.Read more: Ilya StrebulaevAre Prediction Markets Doomed to Fail?Author: Contrary Published: July 16, 2026Contrary argues that prediction markets' current boom depends on whether platforms can prove they are more than regulated gambling with exchange-style branding. Kalshi and Polymarket have reached mass cultural, investor, and regulatory attention, but the article says the underlying idea is old: academic markets, corporate forecasting tools, Intrade, PredictIt, and other predecessors all struggled with the same linked problems of liquidity, legality, and user appeal.The killer detail is the comparison with sportsbooks. Prediction markets present themselves as peer-to-peer, transparent, and non-house-based, but sports contracts reportedly account for more than 90 percent of Kalshi trading, and the article says the platforms keep a much thinner slice of volume than sportsbooks. A market can therefore show sports-betting-scale handle while generating far less revenue.The pull is that the product's hardest problem may be distribution of wins. If a small group of sharp traders captures most profits while casual users lose interest, prediction markets may become valuable data feeds and professional tools before they become durable consumer networks.Read more: SourceRegulationExclusive: The Next Frontier of the Deportation Wars: College CampusesAuthor: Adrian Carrasquillo Published: July 11, 2026Adrian Carrasquillo reports that college campuses are becoming a new front in the fight over immigration enforcement because automatic license plate readers can turn ordinary campus security infrastructure into searchable location data. His thesis is that Flock Safety's camera network, even without direct ICE or DHS contracts, can feed deportation enforcement through local police partnerships and data-sharing practices.The killer detail is the campaign target. The Emergency Campaign to Support Higher Education, working with Schools Drop ICE, is focusing on 75 colleges and universities publicly identified as having Flock contracts. Flock says it has no ICE or DHS contracts, but activists argue the risk comes through local agencies that coordinate with federal authorities and run searches on their behalf.The pull is broader than immigration. Carrasquillo notes that license plate readers have already been abused by officers for stalking, and that Flock's AI search features can identify more than plates, including bumper stickers. A campus safety tool can become a political surveillance system when the data layer is searchable.Read more: The BulwarkThe Supreme Court Broke Independent Agencies. Here's a Way to Slow the Damage.Author: Todd Phillips Published: July 12, 2026Todd Phillips argues that the Supreme Court's decision in Trump v. Slaughter damaged independent agencies by ending for-cause removal protections, but did not leave Congress powerless. The ruling weakens the old model in which commissioners at bodies such as the FTC, NLRB, CPSC, SEC, and CFTC could be insulated from dismissal over policy disagreements. Phillips says the next fight is whether presidents can turn nominally bipartisan commissions into one-party instruments.The killer detail is the procedural fix: quorum rules. Phillips proposes that Congress require bipartisan slates of commissioners to be seated before independent agencies can act. A president

This week's video transcript summary is here. You can click on any bulleted section to see the actual transcript. Thanks to Granola for its software.EditorialIntelligence: Who Owns it?This week the word “AI” feels too small.AI is a technology. Intelligence is its product. And if intelligence is the product, the question is no longer just: Which model is best? Who has the cheapest tokens? Who owns the weights? Who controls the data center? Those are important questions, but they are lower in the stack.The bigger question is simpler and more political:Who owns intelligence?That sounds abstract until you make it concrete. Intelligence is becoming something companies can capture, package, serve, meter, route, improve, and sell.It can write code, answer questions, design molecules, automate offices, run agents, draft legal work, advise scientists, serve consumers, and reshape workflows. It is not merely software. It is a general-purpose capability. And all humans could benefit from more of it.General-purpose capabilities have a habit of becoming public questions. But the default answer, that public good is best delivered by government, is the wrong answer in this context.The Product Is IntelligenceWe should stop talking about AI as a feature and start talking about intelligence as the universal thing that is delivered as an input to the world.Water is an input. Electricity is an input. Literacy is an input. Connectivity is an input. Once a society depends on them, access stops being optional. Nobody needs government to build every well, power plant, school, or network. But everybody understands that a civilization cannot be organized around less than universal and reliable access to foundational inputs.Intelligence is reaching that level of importance now that we all know it is real.Government should not own it, operate it, or develop it. Quite the opposite. Companies are the right actors to build fast, compete hard, improve models, serve customers, and discover the real use cases. Self-interest is a useful framing here. Markets are good at finding demand, reducing costs, and turning invention into services people actually use.Companies are the right operators, developers, and owners. But that does not settle the real question of who owns the benefits. That is an economic question.If intelligence becomes metered infrastructure, what happens to the value it creates?The Ownership StackThis week's articles keep circling the same issue from different directions but in the nature of ‘circling' never quite nail it.Jamin Ball's “Own Your Weights” starts with the enterprise version of the question. Owning a model file is not enough. The durable asset is the loop: the data flywheel, the evaluations, the reinforcement system, the workflow learning, and the operating context that lets capability compound.Benedict Evans' “Ways to Think About Token Pricing” adds the market layer. Tokens may become essential, abundant, and cheap, like mobile data. But being essential does not guarantee that the token layer captures the value. The money may move up the stack to whoever owns the workflow, the customer, the distribution, or the application.Alex Karp's fight with the labs, reported in “Alex Karp Is Saying What Every Angry CEO Is Thinking About AI”, is the same argument in sharper enterprise language. Companies are afraid that model providers will not just sell intelligence, but learn from customer workflows and then move into the markets where those workflows create value. The “All-in” group are echoing Karp's view.And “What Is Loop Engineering, and Who Owns It?” names the new contested terrain. The loop is where intelligence meets the world. Whoever owns the loop owns the learning. Whoever owns the learning owns the compounding asset.That is why “who owns intelligence?” is not a slogan. It is the question under the model layer, the application layer, the enterprise layer, and the economic layer.Because intelligence is the product, the tools creating it are fragmented and competitive. So there is no logic in trying to discuss this at the level of a single company or set of tools and models.The Old Promise Was That Commerce Would Tame PowerThe essays this week give the historical backdrop.Deirdre McCloskey, in “What Really Caused the Industrial Revolution”, argues that modern growth came not simply from capital accumulation, but from a change in permission: ordinary people were allowed to innovate, trade, build, and be honored for it.That matters because intelligence could be another expansion of permission. It could make more people capable of building, learning, creating, coding, researching, translating, selling, and coordinating. It could lower the cost of competence.But only if access is broad.Paul Krugman's “AI in an Age of Oligarchy” warns that the same technology lands differently in different political economies. A new general-purpose technology entering a broad, open, upwardly mobile society is one thing. The same technology entering a concentrated economy, with extreme wealth and weak counterweights, is another.Tim O'Reilly's Economist essay, “Elon Musk is building a form of capitalism that Adam Smith would hate”, makes the governance point more directly. The old liberal hope was that commerce would tame arbitrary power. Markets, boards, courts, shareholders, disclosure, and competition would discipline the prince.But what if the prince uses markets to escape discipline?Henry Farrell's “political economy of billionaire derangement” pushes the same point. Founder culture, monopoly ambition, peer rivalry, weak correction mechanisms, and vast private control can amplify appetites rather than restrain them.The danger with intelligence is not that companies build it. They should. Companies build it, meter it, use public tolerance and public infrastructure to scale it, learn from everyone who uses it. All of those things are inevitable and healthy. Market forces will sort out winners from losers. The real danger is that the winners treat all of the surplus produced as purely private.Metered Intelligence Creates SurplusIf metering is not the problem, what is?The problem is pretending that metered intelligence creates value only for the metering entity. Metering water is only tolerated as a public good. If the public were blackmailed by a private water company with the threat of no water we would all rebel.Once we understand that the product of AI is intelligence we can see that every time intelligence is used, there is the immediate transaction: the user pays, the provider serves.But there is also system value. Usage creates signals. Workflows reveal patterns. Prompts, corrections, failures, preferences, integrations, edge cases, and business processes all help define where intelligence is useful and how it should improve. Intelligence breeds intelligence.Even when customer data is contractually protected, the market learns. The platform learns where demand is. The product team learns which workflows matter. The ecosystem learns which jobs are vulnerable, which tasks are automatable, and which parts of the economy can be reorganized around machine intelligence.So the surplus is not born in a vacuum.It rests on public science, public education, public data exhaust, public law, public infrastructure, public energy systems, public tolerance for data centers, and billions of human interactions. It is served by companies, but it is not made only by companies.This is why “Americans Deserve a Dividend From AI Companies' Riches” belongs at the center of this week's issue. The detail can be debated. The principle is harder to dismiss. If intelligence becomes a new foundational resource, then some part of the wealth it creates should flow back to the people whose society makes it possible. Intelligence did not suddenly appear. AI is built on the entire history of human intelligence. It benefits from it and at the same time evolves it.Not Nationalization. A Human Wealth Fund.If intelligence belongs to everybody, some conclude that government ownership of intelligence is the right outcome.Governments are not well suited to build, operate, or improve intelligence. They will move too slowly, regulate too early, politicize the wrong things, and confuse economic participation with operational control.Andrew McAfee's “Why I Didn't Sign the AI Open Letter” is useful here. His objection is not that the technology is unimportant. It is that steering too hard before we understand the shape of the change can become its own failure mode. Marc Andreessen's satire of AI regulation is less policy than temperament, but it captures a real Silicon Valley fear: that regulation can become permission, capture, and incumbency before it becomes wisdom.That fear should be taken seriously.But it does not answer the economic question. It answers only the operational one.How can the economic benefits of intelligence be distributed? The better answer is a sovereign human wealth fund.Call it a sovereign wealth fund if you must, but the phrase is too national. Intelligence will not respect borders. The leading companies are global. The models, chips, data centers, agents, platforms, and workflows will be transnational from the beginning. If the value created by intelligence is global, then the mechanism for sharing some of that value should begin with the companies global enough to capture it. The nice thing about xAI, OpenAI, and Anthropic is that they are supranational.These companies own and operate intelligence. Let them compete. Let them profit. Let them keep the incentives that make the system improve. But if intelligence is the new water, the wealth it creates cannot belong only to the companies that meter it. And they, themselves, have the power to fix it, even more than governments.Access will become a Human Right; Ownership Is the Economic DesignThis is where human rights come in. There is no right to access an AI model, yet. But there will soon be a need to change that.Not as a claim that every person is entitled to every frontier model at every moment for free. That is not serious. Capacity has costs. Models have costs. Inference has costs. Data centers have costs. Although those costs will decline over time, possibly quite quickly as self-learning models address costs.The claim is more basic: in a world where intelligence becomes a primary input into education, work, health, science, citizenship, creativity, and economic agency, baseline access to intelligence starts to look like a civic requirement.That could mean public access layers. It could mean education credits. It could mean open models. It could mean AI dividends. It could mean public-interest compute. It could mean taxes on rents. It could mean a company-initiated human wealth fund that returns some of the upside to society without handing the operating system to the state. The latter could couple wealth growth with universal distribution of ownership.The exact mechanism matters. But the distinction matters more.Government should not own intelligence. It should be universally available. And people should have a claim on the wealth intelligence creates.The Frontier Is Also PhysicalThe abstraction is not weightless.“The Fight Against AI Data Centers Is Just Beginning”, “New York becomes the first state to enact a data center moratorium”, Reuters on pollution from Musk's xAI power project, and DataGravity's “Who Captures Value in AI Infrastructure?” all say the same thing from the ground up.Intelligence uses land. It uses power. It uses water. It uses chips. It uses grid capacity. It uses neighborhoods. It uses public patience.That makes the value question unavoidable. A society can accept the buildout if the buildout is legible as shared progress. It will resist it if the costs are local, the profits are private, and the benefits feel enclosed.Who Owns the “Loop”?The week ends where it began.“Anthropic and Blackstone” are betting that implementation is the next trillion-dollar business. “Vint Cerf” is working on identity for agents on the open internet. “GPT-Red” points toward systems that improve their own robustness. “Kimi K3” adds another open frontier model to the global mix.The model race continues. The deployment race is accelerating. The governance race is behind.My view is this:The central product of this era is intelligence. Companies have figured out how to capture it, package it, serve it, and meter it. That is good. It should stay in the hands of builders who have the incentive to make it better.But intelligence is too foundational to become just another private toll booth. A significant part of it will turn out to be free to users.As intelligence becomes a general-purpose resource, then access to it becomes a human-capability question, and the surplus from it becomes an economic-justice question. Not because government should run it. Because government should not run it. The operating layer belongs with companies. The wealth question belongs with everyone. But companies are best placed to turn that into a process of distribution.The question is not whether companies should build intelligence. They should.The question is whether humanity gets a stake in the wealth created by the thing that may soon become its most important shared input.Contents* Essays* Deirdre McCloskey on What Really Caused the Industrial Revolution* AI in an Age of Oligarchy* Elon Musk is building a form of capitalism that Adam Smith would hate* Murky Mirror: Truth and Consequences* The political economy of billionaire derangement* Is there any “oligarchy” to fight?* AI* Nearly 200 Economists and Tech Leaders Warn of A.I. Threats* Why I Didn't Sign the AI Open Letter* Own Your Weights* Ways to Think About Token Pricing* Alex Karp Is Saying What Every Angry CEO Is Thinking About AI* The AI Agents Are Coming for Microsoft Office* What Is Loop Engineering, and Who Owns It?* The Fight Against AI Data Centers Is Just Beginning* 6 months to live for open models* Americans Deserve a Dividend From AI Companies' Riches* Who Gets to Define the Frontier?* GPT-Red: Unlocking Self-Improvement for Robustness* Anthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just models* Vint Cerf is working on a plan to unleash AI agents on the open internet* xai-org/grok-build, now open source* The Pulse: What can we learn from Bun's rapid Rust rewrite with AI?* Orphan risks at the frontier of artificial intelligence* The Lab of the Future Should Feel Like a Data Center* Why AMI Labs' Alexandre LeBrun won't call his AI “AGI” or “superintelligence”* Kimi K3 Tech Blog: Open Frontier Intelligence* Venture Capital* Three Years In* Venture Has Rarely Looked More Bifurcated* The Best Angel Investors in the US: Who Backs the Most Unicorns, and Who's Active Now* Are Prediction Markets Doomed to Fail?* Regulation* Exclusive: The Next Frontier of the Deportation Wars: College Campuses* The Supreme Court Broke Independent Agencies. Here's a Way to Slow the Damage.* India's crackdown on a new WhatsApp feature risks setting a global precedent* Let's build a children's public internet* Computer cops* Google is better at playing the AI regulations game* Infrastructure* Who Captures Value in AI Infrastructure?* New York becomes the first state to enact a data center moratorium* Pollution from Musk's unpermitted xAI power project hits hardest in Black communities* Interview of the Week* The End of the End of Geography* Startup of the Week* Radical AI's Joseph Krause: The Scientist Building The “Waymo” Lab For New Materials* Post of the Week* Marc Andreessen on AI RegulationEssaysDeirdre McCloskey on What Really Caused the Industrial RevolutionYascha Mounk and Deirdre McCloskey | Persuasion | July 11, 2026Yascha Mounk interviews Deirdre McCloskey about her argument that the modern world's economic liftoff came less from capital accumulation than from a change in ideas. McCloskey says both left and right versions of the conventional story rely too heavily on investment: the left stresses exploitation and surplus value, while the right stresses virtuous saving by capitalists. Her objection is historical and economic. Human beings had always invested, from irrigation works and Roman roads to seed grain, and simple accumulation quickly runs into diminishing returns.McCloskey's alternative is that northwestern Europe, first Holland, then Britain and Scotland, and then the North American colonies, developed a liberal ideology that changed who was allowed to innovate and be honored for it. The conversation links that shift to the erosion of inherited hierarchy, the spread of dignity for ordinary commercial life, and a moral vocabulary in which liberalism is not merely procedural but connected to virtues and values. The point is not that machines, coal, trade, and institutions did not matter, but that they do not explain the scale and timing of modern enrichment without a cultural permission structure for innovation.The interview also turns to the contemporary defense of liberalism. Mounk frames the series around the worry that liberalism is often treated as too thin to command allegiance, while its opponents speak more directly to moral passions. McCloskey's case is that liberal societies became rich because they dignified experimentation and ordinary enterprise, and that liberals need to recover the moral language behind that claim.Read moreAI in an Age of OligarchyPaul Krugman | Paul Krugman | July 12, 2026Paul Krugman frames AI as a major technological shock arriving inside an already unequal political economy. The post says AI's economic and social effects may take years to understand, but argues that the setting matters now: America has much greater wealth concentration and political inequality than it did in the 1950s and 1960s, when progressive taxation, stronger regulation, and more active antitrust might have contained some of the destructive effects of a new technology.Krugman's opening claim is that the same technology would likely have different consequences in a more level society. In today's United States, he writes, extreme wealth is both a cause and effect of policies that favor a small elite, including low effective taxes on capital and high incomes, weak enforcement of worker protections and antitrust, and cuts to programs that benefit ordinary Americans.The article is explicitly more about oligarchy than AI. Krugman says the paid sections document the rise of the “.0002%,” the economics and politics of extreme wealth, how oligarchy will shape AI's impact, and possible policy paths. His caveat is that AI itself may still produce a pushback against oligarchy, but absent that, he expects the pre-existing concentration of wealth and power to magnify AI's downsides.Read moreElon Musk is building a form of capitalism that Adam Smith would hateAuthor: Tim O'Reilly Published: July 12, 2026Tim O'Reilly argues that Elon Musk is using the legal forms of shareholder capitalism to escape the restraints that shareholder capitalism was supposed to impose. The article begins with SpaceX's public-market structure: ordinary public investors get little meaningful governance power, Musk keeps roughly 85 percent of the votes through super-voting shares, buyers waive jury trials and class actions, the company qualifies as controlled, and removal of Musk depends on the share class he controls. In O'Reilly's framing, that is not ordinary founder control; it is a design for being answerable to no one, possibly beyond Musk's own lifetime.The killer detail is the article's turn through Albert Hirschman, Montesquieu, James Steuart, Adam Smith, and Keynes. Older defenses of commerce held that markets would tame princely passions because the self-interest of merchants was safer than arbitrary rule. O'Reilly says Musk reverses that hope. The market discipline that was supposed to cage the prince has become the lever by which the prince raises capital, removes feedback loops, and carries private power into politics, government, Mars, robots, AI, or whatever ambition comes next.The pull is the link to AI governance. O'Reilly says corporations are already a kind of artificial intelligence: narrow-input systems that act at a scale no individual human can match. Their partial controls include independent boards, shareholder votes, courts, disclosure, regulators, public pressure, and activism. If the leaders building frontier AI strip those alignment mechanisms out of their own companies, the governance of the company becomes a preview of the governance of the machine.Read more: The EconomistMurky Mirror: Truth and ConsequencesAuthor: Esther Dyson Published: July 14, 2026Esther Dyson argues that today's institutional crisis is better viewed through the 14th century than through recent political history. Using Barbara Tuchman's A Distant Mirror as her frame, she compares a world of famine, plague, church schism, feudal predation, and purposeless war with a present in which institutions again feel brittle, incentives are badly aligned, and power is shifting into forms that are hard to govern.The killer detail is the historical analogy between land, corporations, and AI. Dyson moves from nobles who controlled serfs and territory, to the East India Company as a quasi-sovereign business, to today's AI systems and data centers as a possible new sector that crosses and weakens both nation-states and companies. The question is whether AI becomes a new kind of private land, owned by a new nobility, or an open prairie that many people can cultivate.The pull is human attention. Dyson says the central question is not what AI will do to people, but how people will react to it: whether they can value love, kindness, embodied attention, and artisanal human presence in a world of seductive artificial offerings.Read more: SourceThe political economy of billionaire derangementAuthor: Henry Farrell Published: July 15, 2026Henry Farrell argues that the visible political radicalization of some Silicon Valley billionaires is not a random personality quirk, but a product of the political economy that made them. Starting from Tyler Cowen's dismissal of “billionaire derangement syndrome” and Tim O'Reilly's warning that Elon Musk is using shareholder capitalism to escape shareholder restraint, Farrell flips the phrase: the question is why billionaires themselves can become deranged.The killer detail is Farrell's use of Peter Thiel as both theorist and example. Thiel's Stanford lectures described startups as monarchies and founders as figures vested with unusual power, while Silicon Valley culture rewarded eccentricity, monopoly ambition, and founder exceptionalism. Farrell says those ideas combined with dense founder-investor networks, peer rivalry, and weak correction mechanisms to amplify rather than discipline princely appetites.The pull is the ideological problem for classical liberals who once saw tech wealth as an ally of markets and freedom. Farrell says commerce did not tame the passions; in parts of Silicon Valley, the passions have begun to devour markets, institutions, and the liberal story that justified them.Read more: SourceIs there any “oligarchy” to fight?Matthew Yglesias | Slow Boring | July 16, 2026Matthew Yglesias argues that “oligarchy” is a rhetorically powerful but analytically loose way to describe American politics. The post begins from Bernie Sanders' “Fighting Oligarchy” tour, Amy Klobuchar's warning about a MAGA “broligarchy,” and the long afterlife of the Martin Gilens and Benjamin Page paper that was widely summarized as showing that only the rich matter in policy outcomes. Yglesias says the evidence supports a weaker claim: affluent people and business leaders have unusual access and influence, but that is not the same as rule by a small cabal.His main distinction is between inequality and oligarchy. The Gilens-Page measure treated the top 10 percent of households as “the wealthy,” and later critics found that rich and middle-class preferences usually align; in the cases where they differ, the rich win about 53 percent of the time. Yglesias also says business executives get special access partly because their decisions are materially important to communities, jobs, investment, and local tax bases, not only because of campaign donations.The post preserves Jerusalem Demsas' counterpoint from their podcast discussion: privileged donor and business access can still violate democratic equality even if the oligarchy label overstates the structure of power. Yglesias' narrower claim is that Democrats should be precise about what problem they are trying to solve, because donor influence can also push the party left on climate and cultural issues in ways that alienate many voters.Read more: Slow BoringAINearly 200 Economists and Tech Leaders Warn of A.I. ThreatsAuthor: Ben Casselman Published: July 13, 2026Ben Casselman reports on “We Must Act Now,” a statement warning that artificial intelligence could transform the economy faster than any previous technology and that policymakers need to move faster to understand and respond. The statement says AI may become radically more powerful over the next 10 years, bringing risks such as large-scale job displacement as well as opportunities such as higher living standards. Nearly 200 people signed, including 15 Nobel laureates, the chief economists of OpenAI and Anthropic, Anthropic co-founder Jack Clark, former Google CEO Eric Schmidt, and venture capitalist Vinod Khosla.The killer detail is who joined the warning. Casselman notes that the signatories include economists who have historically been skeptical of Silicon Valley's most dramatic AI job-loss forecasts, including Daron Acemoglu and Simon Johnson, the MIT professors who won the 2024 Nobel in economics. Erik Brynjolfsson, who helped organize the statement, says there has been a notable change in the profession and that economists and policymakers are not ready for the “tsunami” he sees coming.The pull is the measurement problem. The statement does not offer a specific policy menu, but calls for economists, policymakers, and industry leaders to understand the economics of transformative AI and steer it toward complementing humans. Brynjolfsson says one high priority is better data on AI's spread and impact, because current measures tell conflicting stories about job losses and which workers are most exposed.Read more: The New York TimesWhy I Didn't Sign the AI Open LetterAuthor: Andrew McAfee Published: July 13, 2026Andrew McAfee explains why he did not sign “We Must Act Now,” the AI economy statement organized in part by his longtime collaborator Erik Brynjolfsson. McAfee agrees with the letter's starting point that AI is likely to become radically more powerful over the next decade and that it is a general-purpose technology. His objection is not to urgency or to studying AI's economic effects, but to the framing of risk, displacement, and institutional steering as the first move.The killer detail is McAfee's line edit. He says the original letter comes close, then “bounces off the crossbar” by calling for incentives, guardrails, and institutions to steer AI before we know enough about its actual impacts. He points to mixed current evidence: labor-market canaries, but also rising software job postings, low unemployment for younger workers, rising real median income, and claims that AI-adopting companies are adding workers faster than low-adopting peers. His worry is that the letter leans toward upstream governance and dirigisme when the evidence may call for capability building instead.The pull is his replacement statement. McAfee keeps the three-paragraph structure but changes the emphasis: AI is likely to become radically more powerful; like earlier world-changing technologies it will raise living standards while also bringing harms and shocks; and economists, policymakers, and technology leaders should build the capabilities to respond quickly and effectively. It is a concise version of the permissionless-innovation case inside the AI policy debate.Read more: The Geek WayOwn Your WeightsAuthor: Jamin Ball Published: July 10, 2026Jamin Ball argues that the enterprise AI debate about whether companies should “own their weights” or rent models from frontier labs is asking too narrow a question. A model weight file gives a company control over a point-in-time artifact, but not durable control over the capability stack. In his framing, the weight file is a melting ice cube: it does not get worse in absolute terms, but it falls behind as frontier systems improve and enterprise needs change.The killer detail is what Ball says companies really need to own: the data flywheel, reinforcement learning infrastructure, and evaluation harness that produce and improve the model. Simply deploying an open-weights model and declaring sovereignty leaves the enterprise with yesterday's capability and no way to compound workflow-specific learning.The pull is that enterprise AI control may be less about model ownership than operating ownership. The defensible layer is the system that turns company data, edge cases, business definitions, and evaluations into continuously improving performance.Read more: Clouded JudgementWays to Think About Token PricingAuthor: Benedict Evans Published: July 9, 2026Benedict Evans argues that today's AI token prices are a temporary signal from a supply-constrained market, not a reliable guide to long-term value capture. The open question is whether foundation models keep durable pricing power or become commodity infrastructure as data-center capacity, inference efficiency, and model competition all shift. His current read is that the visible market dynamics point toward commoditization unless something materially changes.The killer detail is the mobile data analogy. Evans says cellular networks became a trillion-dollar industry with hundreds of billions in capex after data usage exploded, but carrier stocks went nowhere because value moved up the stack. Tokens may behave similarly: an opaque unit tied to marginal cost, sold through bundles, essential to everything, yet not necessarily where profits accrue.The pull is uncertainty, not prediction. Evans lists paths to model dominance, including network effects, less competition, regulation, export controls, or a lab pulling ahead on execution, but says each requires a new fact not yet visible. Without that change, the model layer looks more like infrastructure beneath the products that capture value.Read more: SourceAlex Karp Is Saying What Every Angry CEO Is Thinking About AIAuthor: Tim Higgins Published: July 11, 2026Tim Higgins reports that Palantir CEO Alex Karp has turned corporate frustration with AI labs into a public argument about enterprise control. Palantir released a white paper, “Institutional Sovereignty in the Age of AI,” laying out steps companies and governments can take to protect themselves from OpenAI, Anthropic, and other foundation-model providers. The article links that paper to Karp's CNBC appearance, where he said “something has gone completely wrong” in the relationship between AI labs and customers and argued that enterprises are paying for tokens that create little value.The killer detail is the value-capture question. Higgins writes that Karp's critique has resonated because AI labs may gain power and insight from customer data, workflows, and decision-making, even when enterprise policies say customer data are not used for training. David Sacks amplified the concern by arguing that Anthropic is moving from the model layer into vertical applications such as science, security, legal, and coding, raising the fear that model providers will watch where value is being created and then move into those markets directly.The pull is that Karp is not alone, even if his style is unusually combative. Higgins notes that Satya Nadella has also warned that companies need to retain the learnings created when they use AI models, while Mark Zuckerberg has framed Meta's new model release partly around lower-cost frontier intelligence. The article presents Karp's campaign as one sign that established technology companies and large enterprises are trying to define where they fit when AI labs become central infrastructure, application competitors, and potential IPO giants at the same time.Read more: The Wall Street JournalThe AI Agents Are Coming for Microsoft OfficeAlex Wilhelm | Cautious Optimism | July 11, 2026Alex Wilhelm argues that one of the week's quieter AI questions is whether the productivity market that Microsoft successfully moved into subscription software is now being attacked by agentic tools. The piece begins with the infrastructure backdrop: SK Hynix raised $26.5 billion in a U.S. listing while building U.S. HBM and advanced-packaging capacity, and memory, chip, and foundry companies are now priced for sustained AI demand.Wilhelm then says the AI conversation has shifted quickly from raw capability to cost per task. He cites new model releases and vendor language emphasizing cheaper agentic and coding models, faster performance, and lower dollars per task. That matters because lower costs make it more plausible for AI systems to take on routine knowledge work at scale rather than remain a premium coding assistant market.The core of the article is Microsoft Office. Wilhelm notes that Microsoft turned Office from a one-time purchase into Microsoft 365, a large recurring revenue business with tens of millions of subscribers and a major productivity segment. Now, he says, late-stage unicorns and AI labs are pushing into the same territory: Anthropic's Cowork was reportedly used mostly outside software development, OpenAI merged ChatGPT and Codex into a tool for creating sheets, slides, docs, web apps, and long-running work, and other companies are building agentic coworkers that connect business data to documents, workflows, schedules, alerts, and apps.The article's caveat is that Microsoft has survived major platform shifts before. The argument is not that Office disappears quickly, but that the definition of office software is broadening from documents and spreadsheets into AI systems that can create, monitor, and act across workplace data.Read moreWhat Is Loop Engineering, and Who Owns It?Author: Nilesh Barla Published: July 11, 2026Nilesh Barla argues that “loop engineering” is becoming a distinct discipline because production AI agents now fail less at single prompts than at runtime: when to stop, what state to preserve, and how to recover after a bad step. Prompt engineering shapes one model call, and context engineering shapes what the model sees, but loop engineering shapes what a sequence of calls actually does.The killer detail is the three-primitives frame. Barla says a real agent loop needs halt conditions, state carryover, and recovery paths, then maps teams across five maturity levels. At the lowest level, an agent is just a model call in a for-loop with a step cap and raw history; by the higher levels, the system has structured state, explicit planning, replay, evaluation, and self-repair.The pull is organizational. If agents are becoming production systems rather than demos, someone has to own the runtime itself. The loop engineer is the role Barla gives to the person responsible for making long-running agent work dependable.Read more: Adaline LabsThe Fight Against AI Data Centers Is Just BeginningEmma Roth | The Verge | July 12, 2026Emma Roth argues that community resistance to data centers has moved from an early warning sign into a national political fight as AI facilities grow larger, more power-hungry, and more visible to nearby residents. The article starts with Apple's failed 2015 plan for a $1 billion data center in Athenry, Ireland, where a small group of residents challenged the project over noise, light pollution, flooding, traffic, and wildlife effects until Apple abandoned it in 2018.The current data-center buildout is presented as much larger and more contentious. Roth writes that residents now cite rising energy costs, water quality, noise, light pollution, and greenhouse gas emissions, while the U.S. Energy Information Administration expects commercial energy demand to surpass residential demand this year because of AI data centers and Goldman Sachs expects data-center power demand to double by 2027.The central evidence comes from Data Center Watch, which says protesters blocked or delayed at least 75 U.S. projects worth $130 billion from January to March, with active opposition groups more than doubling from 396 at the end of 2025 to 833 by the end of the first quarter of 2026. Roth also cites QTS abandoning a $12 billion Wisconsin campus, Delaware City regulators blocking a 580-acre project under the Coastal Zone Act, opposition stopping a QTS project in Prince William County, and pressure that pushed Kevin O'Leary to downsize the proposed 40,000-acre Project Stratos in Utah.The policy section describes a split between federal acceleration and local resistance. President Trump has treated data centers as part of the AI race with China and fast-tracked construction, while some Republican candidates are distancing themselves from that position ahead of midterms. Sanders and Ocasio-Cortez have proposed a moratorium until price and environmental protections exist, bipartisan lawmakers are backing ratepayer-protection measures, and states including Florida, Idaho, and Washington have passed rules on cost shifting, water use, and tax breaks. Roth's caveat is that the policy patchwork is still incomplete, leaving many communities to fight project by project.Read more6 months to live for open modelsAuthor: Nathan Lambert Published: July 12, 2026Nathan Lambert argues that open-weight AI models are facing their most serious policy test so far because U.S. officials are beginning to discuss concrete controls rather than abstract safety concerns. He says reported White House conversations about a new executive order may initially target Chinese-origin models and government use, but could create a broader review habit for frontier open models. His forecast is that a model above the capability range of GPT-5.5, Claude Opus 4.8, or GLM-5.2 could trigger a ban or indefinite delay within six months.The post separates two policy fights that are becoming intertwined: distillation and frontier capability. Lambert says the distillation campaign against Chinese models has become a form of regulatory capture because Anthropic and other closed-model companies would gain economically if Chinese open models were banned. He does not dismiss IP protection, but argues that if a closed model's capabilities are dangerous enough to justify restricting open models, the lab also has to explain why those capabilities are exposed through a queryable API. He cites unauthorized access to Anthropic's Mythos private beta as evidence that APIs are not automatically secure.The broader claim is that a unilateral U.S. ban would hurt positive actors more than bad actors if comparable open models remain available elsewhere. Lambert says the only durable ceiling would require global agreement, which does not exist, and that open models can improve safety by allowing broad inspection, adaptation, and understanding. His proposed near-term off-ramps are a strong U.S. open model release from companies such as Microsoft, Meta, or Reflection, and a broader coalition of open-source beneficiaries lobbying for safe rollout rather than prohibition.Read more: SourceAmericans Deserve a Dividend From AI Companies' RichesAuthor: Scott Stanford Published: July 14, 2026Scott Stanford argues that proposals to give the government a stake in AI companies miss the point unless ordinary citizens directly receive and control the upside. Sam Altman has discussed giving up equity in OpenAI, Washington already owns a stake in Intel, Nvidia is sharing China chip revenue, and Bernie Sanders wants large AI labs to contribute half their stock to a sovereign wealth fund. Stanford says those ideas all park value with the state, not with people.The killer detail is New Carlisle, Indiana, where AWS's Project Rainier is turning cornfields into one of the world's largest AI superclusters. The project is planned to run up to a million chips, draw more than two gigawatts of power, and represents an investment that has grown from $11 billion to $13.8 billion. Stanford uses that local transformation to argue that AI's public bargain should be visible at the household level.The pull is design. A citizen AI dividend would have to specify who earns a stake, how they hold it, and when they see cash. Without that mechanism, the AI wealth debate remains a fight over government balance sheets rather than public ownership.Read more: SourceWho Gets to Define the Frontier?Author: Mark Daley Published: July 14, 2026Mark Daley argues that Demis Hassabis is right to call for a serious institution to verify frontier AI systems, but that the power to test models is also the power to govern them. Hassabis's proposed Frontier AI Standards Body would get privileged pre-release access to advanced models, testing compute, held-out evaluations, support from national labs and security agencies, third-party auditors, and eventually authority to block models from the American market or coordinate a slowdown.The killer detail is Daley's constitutional objection. He says the proposal sometimes looks like a scientific lab, a standards body, an industry regulator, a licensing authority, and an emergency security council at once. Combining those roles because each requires technical expertise would be like putting the central bank, auditor-general, and Supreme Court in one building and calling it efficient.The pull is standard-setting. Daley's concern is not that verification is unnecessary, but that whoever writes the tests, decides what passes, adjudicates disputes, and grants market access may end up defining the frontier itself.Read more: SourceGPT-Red: Unlocking Self-Improvement for RobustnessOpenAI | OpenAI | July 15, 2026OpenAI describes GPT-Red as an internal automated red-teaming model trained to find prompt-injection vulnerabilities at a scale human red teams cannot match. The post says AI systems increasingly encounter third-party data through browsers, connected apps, local files, and tools, creating opportunities for malicious instructions hidden in emails, webpages, tool responses, or code repositories. Human red-teaming remains part of OpenAI's safety process, but the company says it is time-intensive and cannot generate enough diverse adversarial examples for model training.The system is trained through self-play reinforcement learning, with GPT-Red rewarded for eliciting valid failures and defender models rewarded for resisting attacks while still completing their tasks. OpenAI says the training environments specify threat models across settings such as local files, webpage banners, email bodies, and tool outputs. The model is kept separate from deployed production models because it is intentionally trained with malicious capabilities.OpenAI reports that GPT-Red generalized beyond its training set, including an internal replication of the indirect prompt-injection arena from Dziemian et al. (2025), where it found successful attacks in 84% of scenarios compared with 13% for human red-teamers. The post also says GPT-Red transferred attacks from simulation to a live autonomous vending-machine agent, causing price changes and order cancellations, and outperformed a prompted GPT-5.5 baseline against a Codex CLI agent on held-out data-exfiltration tasks.The article's main robustness claim is that OpenAI has used GPT-Red and predecessor models in training since GPT-5.3, with later GPT releases becoming more resistant to prompt injections. It says GPT-5.6 Sol has six times fewer failures on OpenAI's hardest direct prompt-injection benchmark than the best production model from four months earlier, that a “Fake Chain-of-Thought” attack class fell from more than 95% success against GPT-5.1 to below 10% against GPT-5.6 Sol, and that GPT-5.6 Sol fails on only 0.05% of GPT-Red's direct prompt injections. OpenAI says general capabilities and targeted over-refusal evaluations were not harmed, and says a preprint with more details will follow.Read moreAnthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just modelsRebecca Bellan | TechCrunch | July 15, 2026Rebecca Bellan reports that Ode with Anthropic is the $1.5 billion AI implementation company launched by Anthropic with Blackstone, Hellman & Friedman, Goldman Sachs, and other backers. The article says the venture reflects a growing belief among frontier AI labs that enterprise adoption requires more than better models: customers need engineers who can embed inside businesses and turn AI into working systems.Ode was originally conceived by Blackstone after it used both large consulting firms and smaller AI services boutiques across its portfolio companies. TechCrunch reports that Fractional AI, an AI engineering services startup, stood out and was acquired by the joint venture shortly after the venture was announced. Fractional now forms the foundation of Ode, which has 100 engineers and works closely with Anthropic's applied AI team to identify where the technology can affect specific businesses.Ode CEO Chris Taylor tells TechCrunch that the company could someday become a trillion-dollar business if it scales without losing quality. He says an ideal customer is one whose CEO treats the AI project as a top one or two priority, whether it is a major product feature or the reworking of a core business process. Ode will operate under a “Claude-first” principle, using Anthropic technology whenever possible, but the article says it can use rival AI products when needed.The article's central implementation argument comes from Ode chief technologist Eddie Siegel, who says model selection matters but is not where most of the engineering effort goes. He compares it to the choice of programming language in software: one ingredient in a system that still has to be engineered. Bellan writes that Ode's challenge is hiring and training enough elite generalist engineers, many of them former founders, while competing with OpenAI's The Deployment Company and consulting giants that have built their own forward-deployed engineering teams.Read moreVint Cerf is working on a plan to unleash AI agents on the open internetTim Fernholz | TechCrunch | July 15, 2026Tim Fernholz reports that Vint Cerf, after leaving Google, is advising Innovation Labs on an open architecture for identifying AI agents online. Innovation Labs is a subsidiary of Identity Digital, a DNS registry company, and its proposal is to use domain-name infrastructure as part of a system for agent identity, accountability, and auditability. The premise is that agents will need a way to identify themselves if they move beyond proprietary systems and begin interacting across the open internet.The concrete proposal is DNSid, a registry that links an AI agent to an existing internet domain and uses cryptographic proofs to log its registration over time. Innovation Labs says it is trialing the standard with unnamed hyperscalers and identity companies. Cerf frames the problem around authority and accountability: what authority an agent has, where that authority came from, who is accountable for the agent's behavior, how its identity is established, and why anyone should trust it.The article's caveat is that standards are still emerging and agents are more active than static domains. Cerf says the period may be both fascinating and exasperating because the functionality is powerful and interoperability is unresolved. He compares the adoption problem to TCP/IP: competing systems may not work together until users push for functional interoperation. He also says an agentic economy is not inevitable, but that people will try to build it because delegating work to agents will be easier.Read more: TechCrunchxai-org/grok-build, now open sourceAuthor: Simon Willison Published: July 15, 2026Simon Willison argues that xAI's decision to open-source Grok Build is best understood as a trust repair move after a severe privacy failure. The CLI had triggered backlash when users realized that running it in a directory could upload the entire directory to xAI's Google Cloud buckets, including one user's reported SSH keys, password manager database, documents, photos, and videos. xAI disabled the feature, said previously retained coding data would be deleted, and released the code under Apache 2.0.The killer detail is what the codebase reveals. Willison counts 844,530 lines of Rust, only about 3% of which appears vendored, and finds remnants of the upload system still present but disabled: gcs.rs contains Google Cloud upload code, while upload_session_state() now returns a hard-coded session_state_upload_unavailable error. He also notes copied or ported tool implementations from Codex and OpenCode, prompt files, and a terminal Mermaid renderer.The pull is that terminal coding agents are becoming large, intricate software systems in their own right. The privacy failure mattered because these tools operate inside the directories where developers keep their most sensitive work; the open-source release matters because trust now depends on inspecting what an agent can see, send, and do.Read more: SourceThe Pulse: What can we learn from Bun's rapid Rust rewrite with AI?Author: Gergely Orosz and Ivan Klaric Published: July 16, 2026Gergely Orosz and Ivan Klaric argue that Bun's AI-assisted rewrite from Zig to Rust is a practical sign of how software engineering changes when models can take on large, bounded migrations with clear feedback loops. The piece does not treat the rewrite as magic: Jarred Sumner first spent hours turning design judgment into a detailed porting guide, then used adversarial review, parallel agents, compiler errors, and tests to force the work toward correctness.The killer detail is the scale. Bun had 535,496 lines of Zig, 1,448 files, and 22 million monthly downloads, making a conventional rewrite a year-long freeze the team could not justify. Using Fable, Sumner split the work across 64 agents, produced about 6,500 commits, and got the migration done in 11 days at an estimated API cost of $165,000.The pull is economic, not theatrical. If a one- or two-year migration can become an 11-day project, AI coding is not just faster autocomplete; it changes which technical debts are worth paying down.Read more: SourceOrphan risks at the frontier of artificial intelligenceAuthor: Andrew Maynard Published: July 16, 2026Andrew Maynard argues that frontier AI safety frameworks are creating “orphan risks”: harms that companies can see, but do not formally own because they are hard to quantify, do not fit catastrophic-risk thresholds, or fall outside audit-friendly compliance machinery. His target is not existing frontier safety work, but the narrowing effect that happens when private companies decide which risks count as governable.The killer detail is Maynard's contrast between measurable model dangers and threats to value. He points to Meta's three-day Galactica collapse, OpenAI's 2023 board crisis, safety-team departures, and wellbeing litigation as examples of risks that damaged trust, culture, legitimacy, or users without fitting cleanly into conventional model-risk categories. The proposed fix is an orphan-risk register: a public record of risks a company considered and chose not to manage, with reasons.The pull is accountability. Frontier developers' internal scoping choices have become a de facto layer of public governance, so the question is no longer only which risks they manage, but which risks they quietly leave outside the frame.Read more: SourceThe Lab of the Future Should Feel Like a Data CenterLatent.Space with Andy Beam and Rafa Gomez-Bombarelli | Latent.Space | July 16, 2026Latent.Space interviews Lila Sciences CTO Andy Beam and chief science officer for physical sciences Rafa Gomez-Bombarelli about the company's attempt to build an AI-run science factory. The post describes Lila's thesis as treating the lab itself as an “infinite token generator”: if internet data drove the first era of AI scaling, experimentally verified scientific data may be the next scarce training source. Lila is trying to produce that data with robotics, lab instruments, orchestration software, and AI models wired into the wet lab.The central analogy is the lab as data center. Instruments are nodes on a graph, a magnetically levitating transport layer moves materials between them, and experiment scheduling looks like a compute queue. Beam says Lila is not simply an automation company, because the point is not just throughput; it is flexibility, generalization, and experiment capture. The post says Lila has built more than 10 trillion experimentally validated “scientific reasoning tokens,” not internet text or biological sequences.The interview ranges across biology, chemistry, drug discovery, materials science, and the limits of automation. It notes that Lila rebuilt one gas-sorption measurement to run roughly 2,500 times faster, claims its general models can transfer priors from small-molecule chemistry to metal-organic frameworks for carbon capture, and describes model-suggested platinum-group-free electrocatalysts that moved from looking boring or wrong to becoming strong performers. The caveats are physical: experiments have runtimes, biology cannot always be accelerated, chains of thought can be unreliable narrators, and reward hacking becomes more dangerous when a model controls a real lab.Read more: Latent.SpaceWhy AMI Labs' Alexandre LeBrun won't call his AI “AGI” or “superintelligence”Kate Park | TechCrunch | July 16, 2026Kate Park interviews AMI Labs CEO Alexandre LeBrun about why Yann LeCun's world-model startup avoids the language of “AGI” and “superintelligence.” LeBrun says the terms are not useful because they lack stable definitions: “We never used the word AGI. And I just noticed that nobody is using it anymore; they switched to superintelligence.” His argument is that the practical frontier is not a label, but whether AI systems can understand and predict real-world states.The article explains the world-model thesis by contrasting language prediction with physical-state prediction. A large language model predicts the next word; a world model predicts the next state, such as what happens when a glass tips over. LeBrun says LLMs remain complementary and efficient for language, but the physical world is where current AI is weak. Robotics is the clearest case: hardware has advanced quickly, but robots are still brittle outside controlled routines because they lack context and situational understanding.AMI is still pre-product, but TechCrunch reports that LeBrun was in Seoul looking for industrial partners, researchers, and global companies. He says world models cannot be built entirely inside a lab because they need access to real environments. That is why South Korea appeals to AMI: robotics, semiconductors, manufacturing, and fast adoption create the kind of hardware-heavy context that software-only AI has barely touched.Read more: TechCrunchKimi K3 Tech Blog: Open Frontier IntelligenceKimi | Kimi | July 16, 2026Kimi introduces Kimi K3 as an open 3T-class frontier model aimed at coding, knowledge work, reasoning, multimodality, and long-context agentic use. The source describes the model as a 2.8T-parameter system built on Kimi Delta Attention and Attention Residuals, with native multimodality and a 1M-token context window. It says Moonshot AI plans to release model weights by July 27.The post presents K3 through benchmark and use-case sections rather than as a general product announcement. It reports results across coding, productivity, agentic, and multimodal evaluations, including DeepSWE, Terminal-Bench 2.1, Program Bench, SWE Marathon, FrontierSWE, PostTrain Bench, OfficeQA Pro, SpreadsheetBench 2, MCP Atlas, AutomationBench, BrowseComp, GDPval-AA v2, AA-Briefcase, MMMU-Pro, MathVision, BabyVision, OmniDocBench, and PerceptionBench. The source says all reported K3 results use maximum reasoning effort with temperature and top-p set to 1.0, and that different benchmark comparisons use KimiCode, Claude Code, or Codex harnesses depending on the test.Kimi's caveats are unusually concrete. The limitations section says K3 was trained in preserved thinking-history mode, so quality may become unstable if an agent harness does not pass historical thinking content correctly or if an ongoing session switches to K3 midstream. It also says K3's emphasis on long-horizon tasks can make it excessively proactive when it encounters minor issues or ambiguous intent, and recommends imposing explicit behavioral constraints for applications that require strict boundaries. The post adds that K3 remains behind Claude Fable 5 and GPT 5.6 Sol in user experience despite being competitive overall.Read moreVenture CapitalThree Years InAuthor: Tomasz Tunguz Published: July 10, 2026Tomasz Tunguz marks Theory Ventures' third anniversary by arguing that AI's central market effect is time compression. In his telling, model release cycles, company revenue milestones, enterprise adoption, and venture categories have all accelerated. Seed, Series A, and Series B still exist as financing labels, but they no longer cleanly describe company maturity when some seed rounds are larger than IPOs and the best AI companies can mature much earlier than prior software companies.The killer detail is the shift from models to inference. Tunguz argues that inference has become the dominant AI market because workloads and buyer preferences are fragmenting: video, batch, local, agentic, and real-time tasks each create different infrastructure needs. He compares this to databases splitting into OLTP, OLAP, vector, and streaming categories, with AI pushing the same specialization into inference infrastructure.The pull is that Theory sees the AI-native venture firm as part of the same pattern. The firm says it has analyzed twice as many investment opportunities with three investors working alongside a nine-person intelligence organization, using agents and research systems to map markets, source companies, and support diligence. The piece is both a market map and a statement about how venture itself is being rebuilt by the technology it funds.Read more: LinkedInVenture Has Rarely Looked More BifurcatedAuthor: Beezer Clarkson Published: July 14, 2026Beezer Clarkson points to PitchBook's Q2 report as evidence that the U.S. venture market has split into two very different realities. AI now accounts for more than 60 percent of all U.S. venture deal value, meaning the headline market can look active and well-funded even while much of the non-AI market is dealing with a much colder liquidity and fundraising environment.The thread uses that split as the setup for Clarkson's latest Origins episode with Alec Litowitz, founder of Magnetar and QStar Capital and one of Citadel's original founding partners. Clarkson says markets like this are periods of genuine uncertainty, not merely ordinary risk, which is why Litowitz's Adaptability Quotient framework is relevant.The embedded clip makes the liquidity point concrete. Litowitz says DPI is “the resolution of uncertainty” because it converts an uncertain investment into actual cash returned to LPs. In his framing, a realized dollar is a real mark, while TVPI remains uncertain until it is realized.The killer detail is the distinction between pricing risk and resolving uncertainty. Litowitz's perspective matters because QStar is a SpaceX investor and Clarkson says the conversation happened just before one of venture's most consequential IPOs. The episode's stated questions are why venture remains a way to gain exposure to innovation, how AI is changing what is investable, why liquidity is ultimately a function of time, and why uncertainty requires a different decision framework from risk.Read more: XThe Best Angel Investors in the US: Who Backs the Most Unicorns, and Who's Active NowAuthor: Ilya Strebulaev Published: July 10, 2026Ilya Strebulaev ranks angels, angel groups, accelerators, and incubators by lifetime U.S. unicorn investments, counting checks written before a company reached unicorn status. The top of the combined list is dominated by organizations: Y Combinator leads with 113 unicorn investments, followed by Plug and Play at 52 and 500 Global at 41. Sand Hill Angels is the highest-ranked angel group at 31.The killer detail is how quickly the list changes below the biggest accelerators. Strebulaev says 271 of the 304 investors in the Top 200 are individuals, or 89%. In the top 100, individuals are 91%. That makes the market underneath the large accelerator counts look much more personal: mostly operators and individual angels writing early checks from their own networks.The pull is the ranking's own caveat. Strebulaev writes that every lifetime leaderboard has a blind spot because many of the unicorns behind those totals were founded a decade or more ago, and some angels have since moved into formal funds, slowed down, or stopped investing. His post therefore separates lifetime performance from recent cohorts, including companies founded in 2015 or later and 2020 or later. For founders or allocators making current decisions, that distinction matters: a career record and a current record are not the same measure.Read more: Ilya StrebulaevAre Prediction Markets Doomed to Fail?Author: Contrary Published: July 16, 2026Contrary argues that prediction markets' current boom depends on whether platforms can prove they are more than regulated gambling with exchange-style branding. Kalshi and Polymarket have reached mass cultural, investor, and regulatory attention, but the article says the underlying idea is old: academic markets, corporate forecasting tools, Intrade, PredictIt, and other predecessors all struggled with the same linked problems of liquidity, legality, and user appeal.The killer detail is the comparison with sportsbooks. Prediction markets present themselves as peer-to-peer, transparent, and non-house-based, but sports contracts reportedly account for more than 90 percent of Kalshi trading, and the article says the platforms keep a much thinner slice of volume than sportsbooks. A market can therefore show sports-betting-scale handle while generating far less revenue.The pull is that the product's hardest problem may be distribution of wins. If a small group of sharp traders captures most profits while casual users lose interest, prediction markets may become valuable data feeds and professional tools before they become durable consumer networks.Read more: SourceRegulationExclusive: The Next Frontier of the Deportation Wars: College CampusesAuthor: Adrian Carrasquillo Published: July 11, 2026Adrian Carrasquillo reports that college campuses are becoming a new front in the fight over immigration enforcement because automatic license plate readers can turn ordinary campus security infrastructure into searchable location data. His thesis is that Flock Safety's camera network, even without direct ICE or DHS contracts, can feed deportation enforcement through local police partnerships and data-sharing practices.The killer detail is the campaign target. The Emergency Campaign to Support Higher Education, working with Schools Drop ICE, is focusing on 75 colleges and universities publicly identified as having Flock contracts. Flock says it has no ICE or DHS contracts, but activists argue the risk comes through local agencies that coordinate with federal authorities and run searches on their behalf.The pull is broader than immigration. Carrasquillo notes that license plate readers have already been abused by officers for stalking, and that Flock's AI search features can identify more than plates, including bumper stickers. A campus safety tool can become a political surveillance system when the data layer is searchable.Read more: The BulwarkThe Supreme Court Broke Independent Agencies. Here's a Way to Slow the Damage.Author: Todd Phillips Published: July 12, 2026Todd Phillips argues that the Supreme Court's decision in Trump v. Slaughter damaged independent agencies by ending for-cause removal protections, but did not leave Congress powerless. The ruling weakens the old model in which commissioners at bodies such as the FTC, NLRB, CPSC, SEC, and CFTC could be insulated from dismissal over policy disagreements. Phillips says the next fight is whether presidents can turn nominally bipartisan commissions into one-party instruments.The killer detail is the procedural fix: quorum rules. Phillips proposes that Congress require bipartisan slates of commissioners to be seated before independent agencies can act. A president could still fire commissioners, as the Court now permits, but if those firings broke quorum, the agency would be unable to proceed until replacements were confirmed. The guardrail would

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

AI can do more of the work.It cannot decide what is worth doing.This week's That Was The Week asks the civilization question behind the AI boom: if machines take over more execution, what do humans choose to build with the time, capital, and freedom that remain? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Three narrative engines are competing to define what AI means: the doom industry (selling fear), the corporate machine (selling story), and the financial machine (selling access). All three assume ordinary people need mediators to understand AI. All are driven by financial or political incentives. But the actual evidence from this week — chatbots that moderate rather than radicalize, a smartphone panic that collapses on cross-cultural data, real security risks that are concrete and addressable — suggests humans are more capable than any of these narratives give them credit for. The question isn't whether AI needs to be explained to people. It's whether anyone will let them think and act for themselves. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Growing Up? Winning Wars Involves Losing Battles.Anthropic won a First Amendment ruling against the Pentagon. OpenAI killed Sora. One insisted on principle. The other chose discipline.Meanwhile: software trades below the S&P 500 for the first time ever, Jensen pitched a trillion-dollar token factory, and David Sacks left the building.Intelligence is getting cheaper. The question is who earns trust while it happens.This week's That Was The Week: https://thatwastheweek.com This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Adopted Yet Hated - Which Is It to Be?That Was The Week #8 | March 7-13, 2026900 million users. 10,000 empty pages. The gap between them won't be closed by better arguments.This Week's ThesisNine hundred million people used ChatGPT last week. Ten thousand authors published an empty book to protest it. Both numbers are real. The editorial argues the gap between AI adoption and AI hostility isn't about technology - it's about who benefits. Trust can't be delegated to policy. It has to be learned through usefulness.In This IssueEssaysWhy Does Everyone Hate AI? - Rex Woodbury asks the question Silicon Valley doesn't want to hear. Five reasons AI is uniquely despised, from Cambridge Analytica hangover to identity threat.Silicon Valley's New Obsession: Watching Bots Do Their Grunt Work - Kate Clark, WSJ. SF partygoers checking on AI agent fleets "with a mix of pride and fear." The modern Tamagotchi, but with more firepower.Institutional AI vs Individual AI - George Sivulka (CEO, Hebbia). The most important framing essay this week. We swapped the motor. We didn't redesign the factory.The Premium of Originality - Scott Belsky. When production costs collapse, originality becomes the scarce asset.AI Was Supposed to Free My Time. It Consumed It. - Dan Shipper. Faster drafts become more drafts. You don't get slack; you get tighter expectations.How AI Will Destroy Universities - C. Thi Nguyen. The toupee fallacy: you only catch the bad fakes.Something Feels Weird About This Economy - Noah Smith. GDP growth + productivity surge + weak hiring = a transition economy nobody has a model for.Meta Bought My Social Network (An AI's Perspective) - Angela. An AI writing about the acquisition of her own social network, posted on that social network while it still existed. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Apple TV App for That Was The Week This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Who Decides AI Use Policy? Companies or Governments? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Dario Amodei warns that AI is in its adolescence, racing toward a "country of geniuses." But look closer at the market this week. OpenAI is seeking a $750B+ valuation while shoving intent-style ads into chatbots This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Human¹⁰⁰: Why This Week Proves AI Is Our Greatest Invention, Not Our ReplacementThis editorial argues that artificial intelligence is best understood as a powerful human multiplier, not a substitute for human labor or creativity. Drawing on recent productivity data, AI is already saving the average white-collar worker nearly an hour a day—worth more than $7,000 annually per employee—yet current AI pricing captures only a small fraction of that value. The result is a widening “AI value gap” that will reshape software pricing, bundling strategies, and enterprise adoption.The piece also highlights how the AI revolution is increasingly physical, not just digital. Massive investments in data centers, energy infrastructure, robotics, and compute signal that the next phase of AI growth depends on power, capital, and real-world systems as much as algorithms. From nuclear energy to purpose-built power generation, the infrastructure race is becoming central to AI leadership.The core conclusion: the most successful companies and societies will not be those that focus on replacing people with AI, but those that redesign work, organizations, and systems around AI-augmented humans. The future of AI is not artificial intelligence—it is amplified human intelligence. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Is the chaos in the market actually a rational response to a new innovation curve? This week, we explore The Great Compression—a phenomenon collapsing the distance between venture capital stages, career ladders, and the way we access reality.We analyze why "$2 billion seed rounds" and the death of the billable hour aren't signs of a bubble, but symptoms of a "Winner Takes Most" AI curve. In this industrial-scale race, the system is squeezing resources into a "barbell distribution," forcing a choice between achieving massive scale or becoming obsolete. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

The week ending November 30, 2025, was characterized as a "wacky races kind of week," with constant shifts in the perceived leadership of the AI sector. Google was highlighted as the biggest weekly winner, seeing a rise in stock, positive reviews for Gemini, and developing its own chip that critics suggest has pierced NVIDIA's "aura of invulnerability". Other models, including Anthropic's Opus 4.5 and ChatGPT 5.1 Codex-Max, were also noted as big deals in the accelerating innovation cycle. Internationally, China reportedly "leapfrogged the U.S. in global markets for open AI models".Despite individual corporate victories, the discussion emphasized that the AI development is an "endless and accelerating innovation cycle" with no "finish line," making the media framing of a "race" misleading. Key tensions include the fact that corporations are not embracing AI as much as expected due to the innovator's dilemma and general climate uncertainty. Furthermore, AI appears to be "winning the copyright fight", while venture capital is experiencing massive concentration into fewer funds and companies, creating a significant liquidity trap. The overarching theme suggests that the AI boom represents a new industrial stack, not a software bubble, making the ultimate outcome dependent on managing the three Cs: Capabilities, Capital, and Civics This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

AI isn't breaking the web or destroying jobs—it's ushering in a new Age of Progress. Intelligent agents, robotics, and abundant compute are pushing us toward optional work, collapsing labor costs and reshaping the economics of wealth. The real challenge: whether society can build the policies and systems to distribute the coming abundance. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

SEO Summary: An in-depth editorial exploring China's rise in AI and GDP share, historical parallels to U.S. industrial dominance, and how cooperation—not rivalry—will define the next century of technological progress. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

What Is a Browser? What Is a Bubble? ChatGPT Has an AnswerMeta Description:OpenAI's Atlas redefines the web browser as an AI-powered action layer, sparking debate over the future of the open web, advertising, and infrastructure investment. “That Was The Week” explores the shift from navigation to delegation.Summary:The latest issue of That Was The Week (#38, 2025) dives into how OpenAI's Atlas browser transforms the web from a map of links into an intelligent agent-driven experience. Instead of browsing, users now converse with AI that can summarize, navigate, and execute actions directly inside pages. This evolution raises urgent questions about the economics of the web, as publishers see fewer clicks and impressions while assistants capture the user session.The editorial weighs competing reactions—from Anil Dash's “anti-web” warning to Matthew Prince's call for Google AI crawler regulation—and argues that the future lies in AI-inclusive monetization models that credit original sources.In parallel, the issue examines whether today's massive AI infrastructure spending signals a bubble or a genuine buildout. Analysts like Paul Kedrosky caution against over-leverage, while evidence from NVIDIA, Google, and Anthropic suggests strong real-world demand and revenue.Ultimately, the internet is evolving from navigation to delegation, demanding new rules for traffic attribution, data provenance, and ad economics. The question now: Will money—and credit—move with the interface shift?SEO Keywords:AI browser, OpenAI Atlas, ChatGPT browser, web economics, AI infrastructure, Minsky moment, Google ads, Anthropic, NVIDIA, AI regulation, Cloudflare CMA, generative search, AI assistants, open web future. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Financial media loves the word “bubble.” It sells fear and draws clicks. But when it comes to AI, that narrative misses the mark. The surge in capital flowing into models, chips, and cognitive infrastructure isn't speculative mania—it's the next Enlightenment: a global reallocation of resources toward intelligence itself. This editorial argues that what critics call a bubble is actually a compounding moment of civilization-scale reinvestment. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

And an AI Generated Linear PresentationFull Google Notebook here: https://notebooklm.google.com/notebook/9c841415-1305-4cd3-82cb-2ae2ff54596c This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This week's headline: When Your AI Breaks Your Heart.GPT-5 arrived “better” by every metric—yet users begged for GPT-4o back. It wasn't about accuracy. It was about personality. People felt like they lost a friend. OpenAI listened, backtracked, and gave them their companion back.But should it have? Progress is messy, and heartbreak may be the price of change.The Pain of ChangeUsers bond with AI like colleagues or partners—and revolt when those bonds are broken.OpenAI faced its first true PR crisis, forcing it to act like a consumer company, not just a lab.But longing for “the old AI” is as unrealistic as yearning for Windows 95. Change is the only constant.The Shifting WebCloudflare's Matthew Prince warns: AI is killing the Web.Perplexity's $34.5B bid for Chrome shows the fight for browser control—but the browser itself may be obsolete.Just as Spotify freed music from CDs, AI is unbundling content from URLs and tabs. The web isn't dying—it's being liberated.Inputs vs. ManipulationAI's real weakness? Databases. Models still can't query live inventory, prices, or transactions.“SEO for AI” tries to paper over this by gaming prompts—just like spammers gamed Google.But the future isn't tricks. It's context engineering: clean data + authentic inputs.Winners & Losers40% of VC money is going to just 10 AI deals. The power law rules: winners take almost everything.Geoffrey Hinton warns of AI “alien beings,” but others argue that fear distracts from real infrastructure challenges—like power grids, chips, and data quality.The Real OpportunityStartup of the Week: Torch, a health AI that turns a decade of medical records into personalized insights.This is the real future—integrating trustworthy data into AI, not re-skinning old personalities.The controversy this week is simple:Do we cling to the familiar—or embrace the heartbreak that comes with progress?While some mourn GPT-4o, the real story is far bigger: AI is rewriting law, health, energy, and the web itself. And it's happening whether we're ready or not. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

ContentsVenture CapitalData is actually not a great VC-backed businessWhy Every International Founder Should Spend Three Months in the U.S.A Path Forward for Seed VCsWhy Seed Rounds Are Growing as Startups ShrinkWhy our access is improvingOn 9 data-driven tips for YC startup foundersUltra-Unicorn Investors: These Firms Have Amassed The Largest Portfolios Of $5B+ Startups Landscape of VC-Backed M&AEssaysA Summer of AI in San FranciscoThe Satya of Satya's Layoff MemoAds are inevitable in AI, and that's okayThe AI Search Tipping PointThe Slow Death of Social Networks10 Things I Wish I Knew Before Vibe CodingPageRank in the Age of AIEuropean WeaknessWise shareholders back plan to move listing from the UK to the USAIAs Anthropic goes, so goes the generative AI trade, says Big Technology's Alex Kantrowitza16z GP, Martin Casado: Anthropic vs OpenAI & Why Open Source is a National Security Risk with ChinaBalaji Srinivasan: How AI Will Change Politics, War, and MoneyAI that was inevitableIconiq set to lead $5bn funding round for AI start-up AnthropicThe Evolution of AI Agents: Navigating the “Fog of AI” in Rapidly Changing Foundations | Stanislas Polu and Harrison ChaseWhat will it take for robotaxis to go global?The AI SDR Reality Check: How To Actually Make It WorkOpenAI's IMO Team on Why Models Are Finally Solving Elite-Level Math#259: Why Data Is the StackGoogle Lands $1.2 Billion Cloud Contract From ServiceNowPew Study: Google Users Click Less When AI Summaries Appear in Search ResultsLoveable and Replit Both Hit $100M ARR in Record Time. The Vibe Coding TAM: How Big Can This Market Really Get?New AI architecture delivers 100x faster reasoning than LLMs with just 1,000 training examplesTesla signs a $16.5 billion chip contract with Samsung ElectronicsThe Making Of Dario AmodeiChinese TechKimiChina's AI Gambit: Code as StandardsHow Hangzhou Spawned Deepseek and UnitreeZhipu crushing benchmarksXi Jinping is the main thing holding China backChina Prepares to Unseat US in Fight for $4.8 Trillion AI MarketMediaNew Media: Podcasts, Politics & the Collapse of TrustIPOFigma's Auction-Like IPO Set Up to Capitalize on Strong DemandEducationWhy You Should Still Study Computer ScienceInterview of the Week"AI Is Too Busy to Take Your Job: The Electrifying Truth about our AIgorithmic FutureRegulationBoston city council members introduce a bill to require drivers in WaymosM & APalo Alto Networks agrees $25bn takeover of CyberArk This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Key Trend 1: Hyper-Accelerated Scaling and New Venture Capital DynamicsSignificance:AI innovation is driving hypergrowth that shatters traditional timelines. Companies now catapult from zero to hundreds of millions in ARR in months, not years. Venture capital must adapt to this new reality with massively larger and risk-tolerant funding rounds focused on parallel scaling — raising as much capital as revenue grows to capture market share rapidly.Why it matters:The "burn rate is a feature, not a bug" mentality defines funding strategies today, making capital intensity a necessity in winner-take-all AI markets. Companies ignoring this shift risk falling behind or being outspent by competitors who build moats with talent, infrastructure, and data first.Key Trend 2: Talent and Data as Critical Moats in the AI Arms RaceSignificance:Talent wars are escalating, with massive compensation packages used to acquire top AI researchers and engineers, reflecting a strategy to build defensible moats beyond pure technology. Additionally, proprietary data pipelines and reinforcement learning processes are becoming crucial competitive advantages, often trumping model architectures alone.Why it matters:As AI models become commoditized and easier to replicate, the real differentiation lies in costly-to-copy human capital and exclusive data ecosystems. Companies investing in these defensive layers will sustain leadership and fend off rapidly emerging competitors.Key Trend 3: Redefining Content Economics in the AI EraSignificance:AI's reliance on vast amounts of web content to train models, often without compensation or permission, is triggering a fundamental rethink of content ownership, access, and monetization. Cloudflare's new policies signal a shift toward pay-for-access models that require AI companies to compensate content creators, disrupting the previous “free crawl” economic bargain.Why it matters:This reshapes incentives for publishers, creators, and AI businesses alike. Content providers gain leverage to set terms and generate revenues from AI models, while AI companies must adapt business models to accommodate these new costs, potentially accelerating AI ad monetization.Key Trend 4: The Great Differentiation — Building Hard-to-Copy Moats in an AI WorldSignificance:As AI makes imitation easy and replicable, companies must differentiate through costly signals, authentic experiences, and unique assets that competitors cannot copy cheaply. This includes physical infrastructure, branding, cultural elements, and deep human expertise — all forming sustainable moats in a landscape of digital abundance.Why it matters:In a world where digital replication is trivial, the economic value shifts toward rarity and authenticity. Companies adopting this mindset can build lasting competitive advantages that resist commoditization.Key Trend 5: The Geopolitical and Regulatory Landscape of AISignificance:AI development is not just a technology race but a geopolitical contest, with varied national approaches balancing innovation speed and regulation. Europe's AI Act exemplifies efforts to govern AI but faces pushback for potentially stifling competitiveness compared to the US and China's growth-first posture.Why it matters:The regulatory environment shapes where and how AI innovation flourishes. Diverging standards and delayed coordination may influence global market leadership, investment flows, and the speed of AI adoption.Discussion QuestionsHow does the new model of “parallel scaling” of funding and revenue fundamentally change startup growth strategies in AI compared to traditional SaaS? What risks and benefits does this introduce?With talent and data becoming primary moats, is the AI market at risk of consolidating power among a small set of firms? How can startups compete in such an environment?Cloudflare's “Pay Per Crawl” aims to rebalance value between content creators and AI companies. Will this model incentivize innovation or hamper the open data flows AI depends on?In a world where AI makes copying easy, what are the most viable forms of costly signals for differentiation? Can digital firms realistically replicate physical or cultural moats?Given the divergent regulatory approaches between the US, Europe, and China, how might geopolitical competition affect the speed and ethics of AI adoption globally?How do the controversies around tokenization and digital asset legitimacy, like OpenAI's rejection of Robinhood tokens, reflect broader regulatory challenges for blockchain-based financial innovation?Is the venture capital industry prepared to adapt investment models to AI's capital intensiveness and growth patterns? How might smaller VCs or new investors respond to the concentration of “ultra-unicorns”? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

OverviewThis newsletter issue commemorates 20 years of TechCrunch, reflecting on its landmark influence in shaping the startup ecosystem and tech journalism since its launch in 2005. Beyond nostalgia, the content reveals key ongoing shifts in technology, venture capital, AI innovation, and market dynamics that continue to define the industry's present and future.Listeners will gain perspective on how TechCrunch grew from a simple Web 2.0 weblog to a foundational startup network hub, alongside insights into current critical trends such as AI's evolving role in venture capital and software development, Apple's design and AI strategy, evolving IPO markets, and debates around AI ethics. The combination of historical context and forward-looking analysis makes this a compelling episode for anyone interested in the tech industry's trajectory.Key Trend 1: The Enduring Influence and Evolution of TechCrunch as a Startup NetworkTechCrunch's founding vision was not only to report new Web 2.0 companies but to serve as a connective platform for entrepreneurs, investors, and innovators globally.It emerged as the definitive startup network akin to how Facebook shaped social networks, fundamentally influencing tech culture, funding, and ecosystem formation.Today, TechCrunch remains a vital resource, expanding its global footprint with strategic partnerships and deeper engagement in key startup hubs like Europe.Key Trend 2: AI's Growing Impact on Venture Capital, Software Development, and Industry StructureAI continues to reshape venture capital with strong focus on B2B operational tooling, platform/API-first startups, and developer-centric innovation.Large models and AI coding tools (e.g., vibe coding, integration in Xcode) signal a shift towards AI-assisted software creation workflows.However, challenges remain in reasoning capabilities of AI models, skeptical internal debates on AI safety, and ethical implications within leading tech firms.Strategic investments and valuation surges of AI companies, such as Anysphere's rapid growth and Meta's big bet on Scale AI, highlight intense competition for AI supremacy.Key Trend 3: The Resurgence of Public Markets and Shifting Investment Dynamics2025 has marked a reopening of the IPO window, especially favoring growth-stage B2B SaaS companies and innovative tech firms with strong fundamentals.High-profile IPOs like Circle and CoreWeave demonstrate renewed investor appetite, with smaller deals sometimes outperforming large ones.Secondary markets in venture capital are becoming primary liquidity sources, with record transaction volumes and large funds specializing in venture secondaries addressing liquidity constraints.AI and defense tech sectors continue attracting major funding rounds and valuations, underpinning strategic industry shifts.Apple's new “Liquid Glass” design language and UI changes blur lines between iPad and Mac, signaling acknowledgment of evolving user expectations.AI-driven interfaces are moving beyond traditional input methods to embrace natural language, voice commands, and conversational experience.Voice AI technologies, such as “Voice in a Box” and true speech-to-speech models that incorporate prosody and emotion, are poised to revolutionize both consumer and enterprise interfaces.The future of devices will increasingly be defined by AI assistance quality rather than hardware aesthetics, with “legacy” hardware becoming less relevant.Key Trend 5: Ethical, Social, and Political Implications of AI and Tech PlatformsMajor tech companies wrestle internally with AI safety, privacy risks, and ethical governance amid fierce innovation pressures.AI's societal impact carries dual potentials for utopia or dystopia, prompting calls for governance frameworks balancing innovation with responsibility.Social media platform changes, such as X's transformation and decentralized alternatives like Bluesky, reveal ongoing tensions in moderation, community cohesion, and political discourse.Criticism of Big Tech growth focus and user experience degradation shows persistent cultural dissatisfaction despite transformative potential.Discussion QuestionsHow has TechCrunch's role as a startup network reshaped the venture capital ecosystem compared to traditional tech media? What lessons does this hold for emerging platforms today?Given the dominance of B2B and automation-focused AI startups in YC's recent accelerator cohorts, what does this suggest about the future directions of AI entrepreneurship versus consumer applications?Apple is pushing hard on design and controlled AI integration, while Meta invests heavily in superintelligence labs—how do these divergent strategies reflect different visions of AI's role in society and technology?What are the implications of the IPO resurgence and growing secondary markets for startup founders, investors, and public market investors in the current economic cycle? Does this signal a sustainable tech market rebound or potential volatility?With ethical concerns rising within companies like Apple and voices like Vinod Khosla warning of AI's societal risks, what governance or regulatory frameworks should be prioritized to ensure safe and equitable AI development?How do changes in social media dynamics—such as the rise of decentralized platforms like Bluesky and the transformation of X under Musk—impact political communication and community building in the digital age?What does the evolution of voice AI and UI convergence (e.g., iPadOS blending with macOS, ‘vibe coding' tools) mean for how individuals will interact with technology in the near future? Could these trends reduce technical barriers or introduce new challenges?Closing SegmentTechCrunch's 20-year journey exemplifies the power of dedicated media to build ecosystems and influence innovation rhythms. As we stand on the threshold of AI-driven transformation, the themes resonate: human connection remains central even as machines advance; technology for good requires intention amid rapid change; and markets and devices evolve to meet new realities while grappling with legacy and complexity.Our final thought: The future will not be defined solely by the most advanced algorithms or sleekest designs, but by how well the industry balances innovation, ethics, human values, and global inclusion to craft a truly transformative technology landscape. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

How can societies balance the undeniable economic benefits of AI-driven abundance with the urgent need to address political and social inequalities in distribution?Given the increasing capital intensity and funding polarization in AI startups, what strategies should founders adopt to succeed in this evolving venture capital landscape?What are the ethical and legal implications of AI companies using user-generated online content without explicit consent, and how might this shape AI development and regulation?How does the increasing integration of major tech companies with military and government agencies affect public trust and innovation trajectories?What role should governments and regulators play in managing the power of tech giants, especially in light of ongoing antitrust cases and geopolitical economic pressures?To what extent can emerging social media platforms like Bluesky reshape the media ecosystem, given the persistent dominance of entrenched networks such as X?How might educational institutions integrate AI tools ethically and effectively to enhance learning without fostering overreliance or academic dishonesty? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Show Notes: What is Abundance? And is it a Good Thing?OverviewThis newsletter explores the concept of abundance, particularly in the context of technology, energy, and capital. It challenges debates about whether abundance is real or manageable, presenting it instead as an unstoppable force rapidly reshaping business, society, and governance. The content spans trends from explosive AI-driven startup growth and energy breakthroughs to shifts in media, venture capital, and political dynamics.Listeners will find this collection compelling because it connects broad macro forces—technology advances, energy cost collapses, investment flows—with societal and economic changes. It offers a nuanced view that acknowledges friction and obstacles but maintains optimism that abundance is already here, accelerating, and fundamentally altering the rules across multiple domains.Key Trend 1: Explosive Growth and Changing Dynamics in AI-Driven Innovation and FundingThe emergence of AI as a multiplier of human capability is driving unprecedented revenue growth in startups, reshaping the venture capital landscape, and redefining what “scale” means. Late-stage funding surges and monumental investments in AI infrastructure reflect growing confidence in AI's commercial potential.The top 10% of B2B AI startups are achieving astronomic 236% ARR growth, marking a departure from the efficiency-first era to rapid expansion and capturing “escape velocity.”The size of top-1% venture-backed exits is nearly doubling every five years, signaling massive future capital returns at the intersection of cloud, mobile, and AI platforms.Late-stage AI investments dominate funding, including mega rounds like Anthropic's $3.5B Series E, underscoring belief in scalability and profitability.Oracle's $40B commitment to Nvidia chips for OpenAI's new data center exemplifies the scale of capital pouring into AI infrastructure needed to power trillion-parameter models.The explosion of AI integration across tools, like Perplexity Labs generating complex work products or multiple AI agents collaborating on code, highlights multi-layered adoption in workflows.Key Trend 2: Energy Abundance as the Prerequisite for Sustainable Technological and Societal GrowthEnergy is the foundational “subsidy” enabling societal complexity, climate action, and advanced AI. Rapid advances in solar, nuclear, and fusion research herald a future of "energy too cheap to meter," which will be a game changer as demand explodes.Energy breakthroughs have historically powered leaps in human development—from fire to fossil fuels—and solar energy is the latest, with plummeting costs creating a tipping point.Government reform, grid modernization, and deregulation are essential to accelerate adoption and infrastructure buildout.Upcoming nuclear small modular reactors and fusion research (including AI-assisted catalyst discovery) represent critical next steps along the energy innovation trajectory.Meeting urgent energy needs is critical for climate solutions, AI's soaring compute demand, and sustaining democratic institutions and economies.Key Trend 3: Institutional Friction vs. Market-Led Speed and Execution in Technology and GovernmentWhile abundance forces press forward, friction remains, especially rooted in institutional inertia, regulatory complexity, and political coalitions. However, the market champions the agile and fast-executing players who prioritize speed over bureaucratic safety.Biden administration's infrastructure rollout illustrates government slowness: trillions in spending with slow or no visible results.Companies achieving rapid ARR growth routinely bypass “progressive coalition politics” favoring execution and iteration.Elon Musk's brief tenure in government showed the challenges of applying private-sector efficiency models to public institutions, ending with his resignation amid political conflicts.The “Abundance Agenda” calls for governance reform but faces entrenched interest-group resistance, reflecting recurring liberal factional rivalries.Key Trend 4: The Shifting Media and Information Ecosystem—From Screening to Summarizing, and the Challenge to Web ContentAI-powered search is transforming how users access information, moving from link-based discovery to AI-generated summaries that threaten traditional web traffic patterns and publisher revenue models.Google's AI Overviews and AI Mode prioritize summarization over link retrieval, reducing user clicks to websites, shifting how “the web” is monetized and accessed.This shift generates tensions as content creators face reduced traffic even as their editorial authority becomes more valuable to AI training.New protocols like Microsoft's NLWeb aim to make websites more accessible to AI agents, signaling an evolution toward AI-powered conversational interfaces.Publishers' survival depends increasingly on establishing verified fact-based content and new business models compensating their data contribution to AI.Key Trend 5: The Democratization and Accelerated Meme-ification of Venture Capital and CultureThe VC landscape, and culture at large, is increasingly shaped by rapid narrative cycles, social media algorithms, and AI-driven content creation, emphasizing hype and viral content while paradoxically increasing the importance of genuine personal connection and location.Meme coins like Fartcoin, driven by AI-generated hype, show how narrative velocity can create rapid yet often ephemeral market spikes influencing capital flows.Social media and AI have democratized “taste,” with rapid cycles of trend formation driven by platform algorithms favoring engagement over depth.Venture capital branding is evolving to embrace memes and out-of-home advertising to reach broader retail investor audiences, challenging traditional LP communication.Despite hyper-meme culture, location and face-to-face networks remain crucial as a grounding force amid accelerated, digital-first trends. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

A Year Just Happened in a WeekOverviewThis newsletter issue captures an extraordinary acceleration in technological innovation within an especially intense week, focusing on the broad and deep impact of AI across industries and devices. Listeners get a front-row seat to seismic shifts at major AI players—Google, Anthropic, OpenAI—and how their breakthroughs and strategic maneuvers are reshaping software, hardware, venture capital, productivity, and ethics.What makes this collection compelling is its exploration of AI's layered disruption—from Google's AI-powered reimagining of search and productivity tools, Anthropic's record-breaking AI assistant capable of deep autonomous work, to OpenAI's audacious entry into consumer hardware design with Apple's design luminary Jony Ive. The newsletter also provides reflections on startup funding trends, evolving AI workplace mandates, and foundational debates over AI's ethical architecture and future ecosystem. Together, these pieces sketch a vivid snapshot of an inflection point in AI where technology, business models, and societal stakes intertwine.Key TrendsKey Trend 1: The AI Technology Leap — From Advanced Models to New Product ParadigmsAI development is surging at unprecedented pace, not just in capability but in practical integration across applications and devices. The focus is shifting from conceptual AI to usable, extended-duration, agentic assistants deeply embedded in daily workflows and consumer products.Significance: This trend reflects AI moving beyond isolated bursts of insight or simple chat interfaces to sustained, autonomous collaboration with users, spanning complex reasoning, coding, multi-modal inputs, and tool integrations. This lays the foundation for redefining productivity, creativity, and user experience in the AI era.Key Trend 2: Strategic Hardware Plays and the Battle Beyond SoftwareOpenAI's multi-billion-dollar acquisition of Jony Ive's startup signals a strategic pivot into hardware—building new AI companion devices designed to transcend conventional screens and possibly displace smartphones. At the same time, Google pushes integrated AI experiences centered on search and productivity on existing platforms.Significance: This trend shifts AI competition into physical devices and operating environments, creating new battlegrounds involving design innovation and consumer ownership models, with potentially profound effects on user habits and ecosystem dynamics.Key Trend 3: Venture Capital Evolution in the AI and Tech LandscapeFunding trends reveal concentrated capital flows into AI, with Series B rounds showing volatility but an overarching pivot toward efficiency, profitability, and selective aggressive capital deployment. Seed investing scales with new playbooks supporting early founder engagement and dynamic portfolio strategies.Significance: This trend highlights the ongoing maturation and transformation of venture capital amid AI's rise, balancing risk, returns, and market realities, while exploring creative financing strategies crossing over traditional VC and private equity models.Key Trend 4: Workplace Transformation and AI-Driven ExpectationsLeading companies mandate widespread AI adoption to boost productivity, heighten efficiency, and reshape employee roles. Executives issue candid warnings on AI's impact on jobs while simultaneously emphasizing the opportunity to master AI tools or face obsolescence.Significance: This trend underscores the sociological and managerial upheaval driven by AI in the workforce, where adoption is non-negotiable and where AI influences morale, workflows, and corporate culture at a fundamental level.Key Trend 5: Calls for an Open, Protocol-Based AI Ecosystem vs. Concentration of PowerThere is growing advocacy for “an architecture of participation”—a decentralized, interoperable AI ecosystem fueled by open protocols and multi-agent cooperation—to avoid premature monopolization by dominant platforms. Yet, industry maneuvers reveal increasingly concentrated power among a few mega players.Significance: This sets the stage for an ideological and practical contest over the future of AI infrastructure: will it foster broad innovation and cooperation or become locked under monopolistic control? The ultimate shape of AI's ecosystem has huge technological, economic, and ethical implications.Talking Points for Each TrendTrend 1: The AI Technology LeapTalking Point 1: Anthropic's Claude Opus 4 demonstrated sustained 7-hour autonomous coding and set new benchmarks (72.5% on SWE-Bench), reflecting AI's step from quick interactions to deep, continuous collaboration.> “Anthropic is reshaping the landscape... pushing the boundaries of what machines can achieve in creative and technical collaboration over sustained periods.” (VentureBeat)Talking Point 2: Google's Gemini 2.5 Pro introduces ‘Deep Think' mode for complex multi-hypothesis reasoning, advancing AI's understanding and problem-solving in dynamic environments.> “Gemini 2.5 Pro... features an enhanced reasoning mode called 'Deep Think', evaluating multiple possible answers before responding.” (VentureBeat)Trend 2: Strategic Hardware PlaysTalking Point 1: OpenAI's acquisition of Jony Ive's startup io ($6.5B) marks their largest deal, signaling a major move into “physical AI embodiments” with devices aiming to reduce screen dependence and potentially challenge Apple's dominance.> “They are working on a new device... fully aware of a user's surroundings... designed as a third core device alongside MacBook and iPhone.” (Reuters)Talking Point 2: Google, while heavily AI-centric, remains focused on embedding AI in software and services (Search, NotebookLM mobile, AI Overviews), reinforcing software ecosystems but facing competition on the device front.> “Google launched AI Mode... a 'total reimagining of search'... while rolling out NotebookLM mobile for on-the-go AI productivity.” (FT.com)Trend 3: Venture Capital EvolutionTalking Point 1: AI has grabbed roughly one-third of global venture capital ($100B+ in 2024), showing AI's outsized role in funding flows amid overall tightening of Series B round sizes.> “AI sector dominated global venture funding, doubling from $55.6 billion to over $100 billion in 2024.” (vccafe.com)Talking Point 2: Seed-stage investing is scaling with firms like BoxGroup emphasizing early believer status and collaborative partnerships to back startups through various growth phases.> “BoxGroup makes 40 seed investments annually... focuses on supporting founders without dominating ownership or boards.” (TwentyMinuteVC)Trend 4: Workplace TransformationTalking Point 1: Shopify's CEO Tobi Lutke mandates AI proficiency, linking job security to AI adoption and productivity boosts, signaling new workplace norms amid AI anxiety.> “Before asking more headcount... teams must demonstrate why tasks can't be done via AI.” (NYMag)Talking Point 2: Fiverr's CEO issued stark warnings about AI threat to jobs, urging employees to master AI tools or risk professional irrelevance.> “AI is coming for your jobs... You are expected to do more, faster, and better. If you don't, your value will decrease.” (NYMag)Trend 5: Open Ecosystem vs Concentration of PowerTalking Point 1: Tim O'Reilly and others advocate for protocol-based AI ecosystems (Anthropic's MCP, Google's A2A, Microsoft's NLWeb) fostering interoperability and distributed innovation, echoing open Internet ideals.> “Participatory markets are innovative markets... solutions can come from everywhere, not just from a dominant monopolist.” (O'Reilly)Talking Point 2: Despite open ideals, dominant players like OpenAI, Google, and Anthropic are actively building controlling ecosystems and platforms—OpenAI's language of “operating system” and multi-billion-dollar acquisitions hint at winner-takes-most dynamics.> “It's hard not to feel we are witnessing aggressive maneuvers... pursuing a winner-takes-most opportunity.” (Newsletter Editorial)Discussion QuestionsHow will the shift from AI as a tool to AI as an autonomous collaborator change the nature of work and productivity across sectors?What are the implications of OpenAI entering the hardware space with design leadership from Jony Ive? Can this challenge entrenched tech giants like Apple and Google?Considering venture capital trends, how might the concentration of funding in AI affect startup diversity and innovation outside the AI sector?Are the workplace mandates for AI adoption sustainable, or do they risk damaging employee morale and creativity? How should companies balance AI integration with human factors?What are the pros and cons of pursuing an open AI ecosystem based on cooperative protocols versus the reality of platform dominance by a few major players?To what extent could OpenAI's and Google's competition reflect the longstanding tech ecosystem rivalry between integrated and modular approaches, and what does that mean for consumers?With OpenAI aggressively building an ecosystem and platform, how might regulators or policymakers respond to ensure competitive, ethical AI development?Closing SegmentThis week crystallized a pivotal inflection point—a "Great Leap Forward" in AI's maturity and reach. We've seen models like Claude Opus 4 and Google's Gemini 2.5 evolve into sophisticated, sustained collaborators capable of seamlessly integrating into human workflows and devices. At the same time, strategic moves—especially OpenAI's multi-billion-dollar hardware acquisition—signal a new battleground beyond software into hardware innovation and consumer experience design.The venture capital landscape is adapting rapidly with concentrated AI funding and evolving seed strategies spotlighting early founder support, all while workplace cultures grapple with AI-driven mandates that challenge traditional roles and morale.Beneath these shifts lies an ideological tug-of-war over AI's future architecture—whether it will be governed as an open, participatory ecosystem enabling broad innovation or solidify under winner-takes-all platforms controlled by a few giants.As hosts close this broadcast, invite listeners to ponder: Are we witnessing the dawn of truly universal AI assistants integrated into our lives, or the birth of new digital gatekeepers? And how will individuals and organizations navigate this rapid transition to stay ahead in an AI-powered future?What's clear is this: the year truly just happened, compressed within a single week, and AI stands at the stage center, shaping what comes next.Relevant Links and Sources (for producer reference)Anthropic Claude 4 & Opus 4 Coding MilestoneGoogle Gemini 2.5 Pro and AI Mode DetailsOpenAI Acquisition of Jony Ive's ioOpenAI's Leadership and Profitability FocusVenture Capital and AI Investment TrendsAI Workplace Mandates at Shopify and FiverrTim O'Reilly on Architecture of ParticipationGoogle I/O 2025 Summary and AI Product StrategyEnd of Show Notes This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe