That Was The Week

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

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

Show Notes: Patterns in the ChaosDon't be a VictimMay 2, 2025Show Notes: Patterns in the ChaosOverviewThis week's newsletter “Patterns in the Chaos” explores how individuals and organizations can move from passive observers to active agents of change. In an era defined by conflicting signals—tech giants under legal fire, explosive AI adoption, and lofty visions of abundance—the key is to identify cross-cutting patterns and choose which future you want to build.Our content spans court battles over monopolies, the rise of agentic AI in enterprises, evolving capital markets, debates over human value in an automated world, and strategic adaptation in turbulent times. Listeners will gain insights into how these forces interconnect and shape the next chapter of technology, policy, and society.Key Trend 1: The Rise of Agentic AI in EnterpriseSignificance: AI is shifting from a research topic to a mission-critical operational layer. Organizations are embedding autonomous software agents into R&D, go-to-market, and everyday workflows.Talking Point 1: Widespread Agentic AI AdoptionTalking Point 1: Nine in ten R&D teams plan to implement agentic AI this year, signaling a transition from experimentation to production.“91% of R&D Respondents have implemented or are planning to implement agentic AI” (David Poole, Georgian & NewtonX – https://georgian.io/agentic-ai-adoption-insights-from-600-executives/)This momentum underscores that AI planning, reasoning, and execution capabilities are now viewed as essential for competitive R&D.Talking Point 2: Re-Architecting Infrastructure for AgentsTalking Point 2: Companies are considering the web browser as the next OS-level platform for AI agents.“We need to build an OS-level agent, and a browser is essentially a containerized operating system” (Aravind Srinivas, on Spyglass – https://spyglass.org/ai-web-browser/)To avoid catastrophic misinterpretations, teams must also cultivate robust semantic layers that feed agents the context they lack.“Teams will become cultivators of a constantly evolving collection of cross-domain semantic layers” (Tom Tunguz – https://www.tomtunguz.com/semantic-layer/)Key Trend 2: Monopoly, Regulation, and the Future of Tech PowerSignificance: High-stakes antitrust actions against Apple and Google are not just about market share today but about control over tomorrow's AI and distribution channels.Talking Point 1: Google's Default Search Under ScrutinyTalking Point 1: The Justice Department warns that Google's exclusive search deals could “supercharge” its AI rollout and foreclose competition.“Default placement … could be leveraged to ‘supercharge' new AI offerings, ensuring consumers turn first to Google” (David McCabe, NYT – https://www.nytimes.com/2025/05/01/technology/google-antitrust-trial-ai.html)Regulators argue that data-fuel advantages from search defaults give Google an unfair head start in AI services.Talking Point 2: Apple's App Store DefianceTalking Point 2: A federal judge referred Apple to criminal prosecutors for ignoring a 2021 injunction on App Store anti-steering rules.“Apple's goal: to dissuade customer usage of alternative purchase opportunities and maintain its anticompetitive revenue stream” (John Gruber, Daring Fireball – https://daringfireball.net/2025/04/gonzales_rogers_apple_app_store_ruling)This decision forces platforms to reassess how they enforce fees and policies, with potential global ripples.Key Trend 3: Capital Markets Evolution—New Funding Paths and VC ModelsSignificance: Funding mechanisms are diversifying—SPACs are back, VC firms are retooling their partnership models, and founders must navigate changing incentives at each stage.Talking Point 1: SPACs Make a ComebackTalking Point 1: After a rocky 2021, blank-check companies are targeting sectors from autonomous trucking to nuclear power.“Kodiak Robotics announced a SPAC merger at a pre-money valuation around $2.5 billion” (Joanna Glasner, Crunchbase – https://news.crunchbase.com/public/spac/tariffs-ai-robotics-crypto-biotech/)Startups see SPACs as a viable alternative to traditional IPOs, attracting capital at scale.Talking Point 2: VC as a “Full-Stack” Support PlatformTalking Point 2: Andreessen Horowitz redefined venture capital by building specialized teams (talent, marketing, regulatory) around each investment.“Founders deserve more than just capital, but a comprehensive, long-term support system” (a16z – https://www.youtube.com/watch?v=qpBDB2NjaWY)This contrasts with multi-stage funds whose “pipeline” approach can inflate early valuations without seed-stage expertise (Taavet Hinrikus, 20VC – https://www.youtube.com/watch?v=RvHnRxKdg2M).Key Trend 4: Human Agency, Abundance, and the Value of PeopleSignificance: As automation and AI proliferate, human skills, relationships, and democratic participation become scarce—and thus, strategic—assets.Talking Point 1: From Scarcity to Abundance Requires Purposeful PolicyTalking Point 1: Ezra Klein's “Abundance” review criticizes timid calls for incremental reform and urges a democratic blueprint for real abundance.“This is the real discussion we need to be having: how can we achieve the disruptive level of change required for an actual abundance agenda in a democratic fashion.” (Albert Wenger – https://paragraph.com/@continuations/abundance-book-review)Bold policy and collective agency are essential to realize unlimited access to what humans need.Talking Point 2: Human Interaction as a Luxury in the Digital EraTalking Point 2: AI companions and curated human engagement are emerging as valuable services for the socially isolated.“New technologies often feel dystopian, until they feel commonplace … AI friends are a good thing, actually.” (Rex Woodbury – https://www.digitalnative.tech/p/ai-friends-are-a-good-thing-actually)“Human engagement is often reserved for those who can afford it, leading to a society where personal attention is a luxury.” (Humans As Luxury Goods – https://platforms.substack.com/p/humans-as-luxury-goods-in-the-age)Key Trend 5: Strategic Adaptation Amidst ChaosSignificance: Periods of upheaval create openings for startups and organizations that can navigate uncertainty, discipline pilots toward production, and rethink industrial strategy.Talking Point 1: Chaos as a Catalyst for Creative DestructionTalking Point 1: Startups thrive as “tricksters” in turbulent times, deploying architectural innovation to topple incumbents.“Periods of upheaval … create opportunities for startups to disrupt entrenched incumbents.”(Packy McCormick – https://www.notboring.co/p/chaos-is-a-ladder)Embracing uncertainty can be a deliberate strategy for reinvention.Talking Point 2: Overcoming “Death by 1,000 Pilots”Talking Point 2: The real challenge is not launching PoCs but scaling them into production with robust infrastructure, monitoring, and operations.“It's easy to fire up a pilot … you can get stuck in this ‘death by 1,000 pilots' approach.” (Rodney Zemmel, McKinsey Digital, via O'Reilly – https://www.oreilly.com/radar/death-by-1000-pilots/)Companies must build clear paths from experimentation to value realization.Discussion QuestionsHow can enterprises avoid “death by 1,000 pilots” while rapidly scaling agentic AI capabilities?What are the trade-offs between antitrust interventions (e.g., breaking up defaults) and the risk of stifling AI innovation?In a world where human interaction becomes a luxury, how should companies balance automation with services that emphasize personal touch?Can SPACs and “full-stack” VC platforms coexist, or will one model dominate early-stage funding in the next cycle?Given the tension between incremental regulatory fixes and calls for disruptive abundance agendas, what level of policy boldness is both feasible and desirable?How might a forced sale of a browser or default search slot reshape the competitive dynamics of AI distribution? (Controversy: divestiture as remedy)Are hyper-optimistic growth projections (e.g., OpenAI's $129 billion by 2029) fantasy, or do they play a functional role in mobilizing capital? (Controversy: realism vs. hype)Closing SegmentAcross regulation, capital, technology and human value, one pattern emerges: agency matters. Whether you're a founder, policy-maker, or individual, inertial forces abound—but so do levers for change. Embracing agentic AI, reshaping capital structures, demanding bold policy, and elevating human skills can turn chaos into opportunity. As we close, remember: “History is decided by human decisions taken in real time.” What decision will you make today to shape tomorrow? 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: Venture Blues: Cloud, Silver LiningOverviewThis week's “Venture Blues” editorial brings into focus a brewing transformation in early-stage venture capital. As funds endure stretched timelines and mounting LP pressure, long-taboo secondary markets are stepping into the limelight. At the same time, traditional VC structures—anchored to power-law home runs and decade-long illiquidity—are under fresh scrutiny.What makes this collection compelling is its blend of on-the-ground investor testimony (from Dan Gray, Hunter Walk, Rob Hodgkinson) and hard data (Carta charts, Series B MOIC trends) that together sketch a venture asset class at a crossroads: can it engineer better liquidity and more dependable returns without sacrificing outsized upside?Key Trend 1: The Liquidity Imperative and Rise of SecondariesAs portfolio companies stall in late-stage rounds, early-stage VCs and LPs alike are waking up to the need for earlier liquidity—and rediscovering secondaries.Why it matters:– Stigma around selling GP stakes is eroding when 10-year fund cycles stretch toward 15 years.– Liquidity becomes critical to meet IRR targets and redeploy capital.Talking Point 1: From Taboo to ToolboxQuote:“The obvious desperation for liquidity has — for now — removed the stigma associated with secondaries.”— Dan Gray's X postEarly-stage managers, once loath to let shares go, now view secondaries as a legitimate value-preservation tactic.Removing psychological barriers makes secondaries a core liquidity channel, not just a last-resort option.Talking Point 2: Fund Cycles Stretch, LP Calculations ShiftQuote:“For the earliest funds (pre-seed, seed) this means instead of 10 year fund cycles for LPs, you're seeing closer to 15, which fundamentally changes LP calculations about the asset class.”— Hunter Walk, HomebrewLonger holding periods erode IRRs and cash-on-cash returns.LPs factor in delayed distributions, pressing GPs to surface secondary opportunities sooner.Key Trend 2: Structural Challenges in Traditional VC ModelsDespite aggregate Series B investments growing 476% over eight years, most value remains on paper—and out of reach.Why it matters:– Healthy MOIC doesn't equate to real cash returns.– Most LPs lack access to top-performing funds and can't live off latent value.Talking Point 1: MOIC vs. Cash—The Distribution DilemmaQuote:“And the 4.76x is measured in MOIC, not cash, so was not distributed.”— Venture Blues editorialVenture's celebrated power law produces massive paper returns skewed toward a handful of winners.Without distributions, LPs can't recycle gains, creating a false sense of asset-class health.Talking Point 2: Concentration of Compelling ManagersQuote:“Most LPs do not get returns, and certainly not liquid returns (the only real kind).”— Venture Blues editorialA small club of star GPs capture most performance.Broader LP community remains exposed to illiquidity without average outcome participation.Key Trend 3: Rethinking the LP Base and Investor AlignmentEconomic uncertainty is forcing a recalibration of who backs VC—and how.Why it matters:– Traditional LPs (endowments, pensions) face funding pressures.– New entrants (sovereign wealth, retail, alternatives platforms) demand different structures.Talking Point 1: Endowment Exodus to SecondariesQuote:“A harbinger of change is Yale, who pioneered the ‘endowment model'… selling $6 bn in its PE portfolio in secondaries for the first time.”— Rob HodgkinsonEndowments under the gun from taxes, tariff impacts and political hostility.Liquid strategies gain priority, reshaping demand for evergreen and secondary vehicles.Talking Point 2: LP Preferences Shape Fund ProductsQuote:“VC is changing. Venture firms need to rethink not just who they raise from, but how their LP base influences what they're offering.”— Rob HodgkinsonA move toward evergreen, co-invest, direct, and secondary funds rather than classic 10-year vehicles.Funds must tailor structures to new LP appetites for liquidity and risk profiles.Key Trend 4: Emerging Structures for De-Risked, Liquid VC InvestmentsAlgorithmic selection and private-company indexes promise to lower risk, broaden access and embed liquidity.Why it matters:– De-couples returns from a small set of GPs and rare unicorns.– Creates tradable vehicles for average VC outcomes.Talking Point 1: Filtering the 7% That MatterQuote:“Investing in this 7% as an index gives investors the ability to participate in de-risked average outcomes.”— Venture Blues editorialData and machine learning reject 93% of Series B rounds.The top 7% deliver 6.2x MOIC in five years, enabling an index tilted for performance.Talking Point 2: Liquidity by DesignQuote:“There is no longer a dependency on which fund an LP can invest in… And liquidity is built into the index approach.”— Venture Blues editorialIndex shares can be bought and sold once listed on public markets.Retail investors and non-traditional allocators gain direct VC exposure.Discussion QuestionsHow has the elongation of fund cycles from 10 to 15 years altered LPs' appetite for early-stage VC?Can the rise of secondaries truly resolve liquidity challenges, or does it merely shift them to later rounds?With secondaries becoming “primary” for early-stage VCs, is there a risk of misaligned incentives between GPs and founders?How might new LP entrants (retail platforms, sovereign wealth funds) reshape venture fundraising and governance?Is algorithmic selection and index-based investing a silver bullet for de-risking VC, or does it introduce new systemic biases?Is the core issue in venture the lack of liquidity or the inherent power-law structure forcing “home runs”?What unintended consequences could emerge from tradable private-company indexes?Closing SegmentVenture Blues reveals an asset class in flux: the thirst for liquidity is rewriting norms, LPs are demanding new structures, and data-driven models offer a glimpse at more equitable, de-risked returns. As we watch secondaries soar and index products emerge, the central question remains: can VC evolve beyond its 70-year blueprint to deliver both outsized growth and true liquidity?Final thought: the silver lining in today's venture clouds may be a fundamentally redesigned asset class that finally brings average, liquid outcomes within reach.Stay tuned as we track which of these trends will reshape the venture landscape for good. 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: Are Google and Meta Screwed?And does it make any Sense?April 18, 2025OverviewThis week's newsletter delves into a pivotal moment for two of tech's biggest players: Meta and Google. Long dominant through strategic acquisitions and platform control, both are now under intense legal scrutiny. At the same time, a new platform shift—centered on AI—threatens to upend their business models, just as geopolitical forces reshape global markets.Listeners will gain insight into how antitrust battles, legacy acquisitions, AI innovation, and trade wars intersect to challenge the future of these giants. We'll connect disparate articles to reveal patterns that go beyond individual stories.Key TrendsKey Trend 1: Government Antitrust Pressure and Legal BattlesSignificance: After decades of unchecked growth, Meta and Google face unprecedented antitrust scrutiny. The outcomes could reset the rules for digital markets—and determine whether breakups or massive fines become the norm.Talking Point 1: Meta's High-Stakes Trial“In a just world, the FTC has no shot to win this case. The case is so nebulous and weak…”– M.G. Siegler, “The Meta Points of Meta's Trial” (https://spyglass.org/meta-trial/)• Highlights the FTC's challenge: litigating past acquisitions with vague theories of harm.Talking Point 2: Google Guilty in Ad Tech Monopoly“A judge ruled that Google holds a monopolistic position in the technology of online advertising, unfairly harming rivals and advertisers.”– David McCabe, New York Times(https://www.nytimes.com/2025/04/17/technology/google-ad-tech-antitrust-ruling.html)• Marks the second major U.S. court loss for Google in under a year, setting the stage for structural remedies.Key Trend 2: Strategic Platform Shifts and Legacy AcquisitionsSignificance: Meta's survival has hinged on buying Instagram and WhatsApp; now those very deals are under fire. The pattern echoes past shifts—desktop to mobile—and underscores how acquisitions can both secure and imperil platform relevance.Talking Point 1: The Value and Vulnerability of Instagram“Without Instagram, Meta is screwed.”– M.G. Siegler, Spyglass (https://spyglass.org/without-instagram-meta-is-screwed/)• Shows Instagram's ad revenue underpins Meta's funding for new bets (metaverse, AI).Talking Point 2: Echoes of the Mobile Battle“Facebook 2.0 will try to kill Facebook 1.0 and Google 2.0 will try to kill Google 1.0.”– Editorial, “Are Google and Meta Screwed?” (Newsletter for April 11, 2025)• Reminds us how prior platform shifts demanded reinvention—AI may require the same.Key Trend 3: AI‑Driven Disruption and the Next PlatformsSignificance: Just as mobile upended desktop, AI is redrawing the map of search, discovery, and social engagement. Meta and Google must adapt to challengers like OpenAI, Anthropic, xAI and novel features such as memory and reasoning.Talking Point 1: AI Search and Discovery Race“OpenAI, Anthropic, Perplexity, and Grok capture users for AI based search and discovery.”– Editorial, “Are Google and Meta Screwed?”• Signals user migration away from traditional search and feeds.Talking Point 2: The AI Price War and Memory Features“OpenAI slashes prices for GPT‑4.1 by up to 75%, igniting an AI price war among tech giants.”– Bryson Masse, VentureBeat (https://venturebeat.com/ai/gpt-4-1-ai-price-war-developers/)“Claude's memory feature … allows the chatbot to recall details from previous interactions.”– Michael Nuñez, VentureBeat(https://venturebeat.com/ai/claude-just-gained-superpowers-anthropics-ai-can-now-search-your-entire-google-workspace-without-you/)• Underscores how product feature arms races could outflank legacy ad models.Key Trend 4: Global Economic Realignments and Trade WarsSignificance: Tech doesn't operate in a vacuum. Tariffs and nationalism are reshaping supply chains and consumer behavior, with knock‑on effects for digital giants reliant on ad dollars and global audiences.Talking Point 1: Tariffs as a “Tectonic Plate Shift”“Trump's tariffs are part of a broader movement in the global economy which he describes as a ‘tectonic plate shift.'”– Peter R. Orszag, New York Times video (https://www.nytimes.com/video/opinion/100000010103488/trumps-tariffs-are-part-of-a-tectonic-plate-shift-in-the-global-economy.html)• Reflects how trade policy uncertainty seeps into tech investment and consumer prices.Talking Point 2: The End of Globalism vs Economic Globalization“Globalisation as we've known it for the past couple of decades has come to an end.”– Frank Furedi, Spiked (https://www.spiked-online.com/2025/04/15/the-end-of-globalism-is-nigh/)• Positions economic nationalism alongside persistent interdependence—tech firms must navigate both.Discussion QuestionsHow do the FTC's and DOJ's strategies against Meta and Google reflect a shift in government confidence and capability to regulate tech giants?Would breaking up Instagram and WhatsApp—or forcing Google to divest its ad tech—spur innovation or simply weaken platforms in an era of AI competition?In what ways has the shift from mobile to AI mirrored past platform transitions, and what lessons should Meta and Google apply as they pursue “2.0” strategies?Is the AI price war (GPT‑4.1 cuts, Claude memory, Grok features) a sustainable model for developers and businesses, or will it erode margins across the ecosystem?Do Trump's tariffs and rising economic nationalism ultimately strengthen China's tech incumbents (Huawei, Temu, Shein) more than they pressure U.S. companies? (Controversial)With visionaries like Jack Dorsey and Elon Musk calling to “delete all IP law,” how should tech firms balance creator rights against AI training needs? (Controversial) 7. How does the narrative of “the end of globalism” influence Big Tech's investment in international expansion and localized product strategies?Closing IdeasMeta and Google stand at a crossroads: legal rulings threaten their core business structures while AI challengers redefine user engagement.Their historic playbook—acquiring emerging rivals and evolving ad models—now collides with fast‑moving technology, activist regulators, and geopolitical headwinds.Final Thought: Survival for these giants will depend on agility—embracing AI as the next platform, rethinking past acquisitions, and navigating a world where borders, both digital and national, are being redrawn.Generated on 4/18/2025 with Newsletter Creator 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

OverviewThe "Whiplash" newsletter delves into various critical topics that reflect significant shifts in global dynamics, particularly in technology, geopolitics, and economic trends. These articles highlight the evolution of data infrastructure, the impact of U.S.-China trade tensions, advancements in AI and robotics, and the challenges facing globalization. This collection of content offers insights into how these trends are reshaping industries and international relations, emphasizing the need for adaptability and strategic alliances in an increasingly complex world.Key TrendsKey Trend 1: Technological Advancements and AISignificance: The articles highlight the transformative power of AI and graph technology in enhancing decision-making processes and creating more personalized experiences. AI is increasingly crucial in optimizing business operations and amplifying human potential rather than replacing it.Talking Point 1: Reid Hoffman's perspective on AI emphasizes its potential to enhance human capabilities, making us more human. This view is reflected in his book Superagency, which argues that AI leads to more human agency rather than less.Talking Point 2: The integration of AI into SaaS models is revolutionizing unit economics by improving customer experiences, predictive analytics, and operational efficiency. This shift is making businesses more agile and efficient.Key Trend 2: Geopolitical Tensions and TradeSignificance: The articles discuss the escalating tensions between the U.S. and China, particularly over trade policies and technological sovereignty. These tensions are reshaping global trade dynamics and challenging traditional economic alliances.Talking Point 1: The U.S. tariffs imposed on China have inadvertently benefited China by prompting it to focus on domestic consumption and technological innovation. This strategic shift is making China more self-sufficient.Talking Point 2: The TikTok negotiations illustrate the complexities of cross-border technology regulation and the challenges of aligning national security concerns with economic interests.Key Trend 3: Globalization and Economic ShiftsSignificance: The articles explore the potential collapse of globalization due to rising nationalism and trade barriers. This trend has significant implications for economic growth, cultural exchange, and international cooperation.Talking Point 1: The shift away from globalization is driven by protectionist policies and geopolitical conflicts, which could lead to slower economic growth and increased instability.Talking Point 2: China's rise as a dominant trade partner reflects a broader trend of economic power redistribution, with implications for global market dynamics and technological innovation.Discussion QuestionsWhat are the potential long-term consequences of the U.S.-China trade tensions on global economic stability?How can AI be effectively integrated into business operations to enhance productivity and retain human value?In what ways does the shift towards protectionism affect international cooperation and global governance?How might the evolution of data infrastructure impact industries like finance and healthcare?What role do strategic alliances play in countering economic challenges posed by major powers like China?How can businesses adapt to the changing landscape of globalization and technological advancements?What ethical considerations arise from the increasing reliance on AI in decision-making processes?Closing SegmentThe most important trends highlighted in the "Whiplash" newsletter revolve around technological innovation, geopolitical tensions, and economic shifts. These themes underscore the need for strategic adaptability, international cooperation, and ethical considerations in navigating the complex dynamics of the modern world. As AI continues to transform industries and global trade patterns evolve, understanding these trends is crucial for businesses, policymakers, and individuals seeking to thrive in an increasingly interconnected and rapidly changing world. The final thought: In a world where change is the only constant, embracing innovation and fostering cooperation will be key to unlocking future success and stability. 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 week's newsletter centers on the explosive rise of AI, highlighting how OpenAI's massive funding round and soaring valuation are signaling a transformative shift in both technology and finance. The content weaves together themes on the evolving nature of creativity in the AI era, intense debates around copyright and intellectual property rights, and strategic investments that are helping AI expand into new sectors such as education. The interplay of technology, ethics, and global market dynamics makes this a compelling discussion for anyone watching the AI revolution unfold.Key Trend 1: Explosive Growth and Valuation in AIAcross the newsletter, OpenAI emerges as the poster child of AI's rapid ascent—raising $40 billion at a $300 billion valuation, with projections hinting at exponential revenue growth over the next few years.Talking Point 1:The funding round “of $40 billion at $300 billion valuation” is a clear indication of the immense investor confidence in AI. Quote: “No one would have predicted that $1 trillion is almost too small to contain what is being built.” (Editorial) Reference: NY Times article on OpenAI's valuationTalking Point 2:This financing milestone, when compared to historic tech deals, underscores how AI is redefining the scale and pace of innovation. Evidence: “After Wiz sold to Google for $32 billion in cash, and X ‘sold' to xAI… Enter OpenAI with a new $40 billion raise…” (Editorial)Key Trend 2: The Evolution of Creativity and Authorship in the Age of AIThe newsletter prompts us to re-examine the creative process as AI tools become increasingly intertwined with content creation. One burning question is: “When does writing stop being ‘yours'?” as AI begins to shoulder some of the creative workload.Talking Point 1:The evolving role of AI in writing invites debate on what constitutes true authorship and originality. Quote: “How does the emergence of AI reshape our understanding of authorship and originality?” (Editorial quoting JF Martin essay)Talking Point 2:Despite the sophisticated capabilities of AI, the content emphasizes that “the creation of truly meaningful and high-quality content still relies heavily on human direction and insight,” fostering a creative partnership rather than a displacement of human ingenuity.Evidence: “The intricate dance of crafting prompts, providing feedback, and ultimately evaluating the AI's output…” (Editorial)Key Trend 3: Copyright Controversies and the Ethics of AI TrainingAlongside the excitement around AI, ethical and legal debates are emerging—most notably around how AI models are trained, especially when they use copyrighted materials without explicit permission.Talking Point 1:Controversies over using copyrighted content, such as O'Reilly books, have already led to lawsuits and heated debates about intellectual property rights. Quote: “Reports suggesting that AI models, potentially including OpenAI's, have been trained on copyrighted material like O'Reilly books…” (Editorial) Reference: TechCrunch article on copyrighted AI trainingTalking Point 2:This evolving legal landscape signals an urgent need for more transparent guidelines and ethical frameworks that balance technology's potential with respect for content creators.Evidence: “Navigating these ethical and legal complexities will be essential as AI becomes more deeply embedded in content creation.” (Editorial)Key Trend 4: AI's Growing Role in Education and Personalized LearningThe investment in SchoolAI highlights an important application of AI beyond traditional tech sectors, as it moves into education to personalize learning and improve both teacher and student experiences.Talking Point 1:SchoolAI's innovative approach uses AI to “personalize education for every student and teacher,” making learning more engaging and adaptable to individual needs.Quote: “My first 30-minute meeting with SchoolAI founder Caleb Hicks stretched to over ninety as we delved into his vision.” (Editorial) Reference: SchoolAI investment articleTalking Point 2:By integrating AI into classrooms, SchoolAI is also addressing pressing challenges like teacher shortages and the need for customized support for each student.Evidence: “SchoolAI's platform is used in over 1 million classrooms across the U.S. and more than 80 countries…” (Editorial)Discussion QuestionsHow sustainable is the current wave of massive AI funding given historical tech market cycles?In what ways might the blending of human creativity and AI tools redefine traditional notions of authorship?What ethical boundaries should be established regarding the use of copyrighted materials for training AI systems?Could the integration of AI into education help bridge learning gaps, or might it exacerbate existing inequalities?How will ongoing geopolitical tensions and evolving trade policies impact future innovation and investment in AI?What kind of legal and regulatory frameworks are needed to balance innovation with intellectual property rights in the AI era?How do we ensure that AI remains an enabler of human creativity rather than a replacement?Closing SegmentThe newsletter paints a vivid picture of an era defined by dramatic shifts in technology and market dynamics. The staggering growth in AI valuations, the redefinition of creative authorship, and the ethical challenges surrounding data and copyrights all point to a transformative period in business and culture. As AI finds new applications in education and beyond, the ultimate challenge—and opportunity—will be balancing rapid technological advances with ethical responsibility and sustained human oversight. Final Thought: As we stand at the crossroads of an AI-driven future, the choices we make about funding, regulation, and creative collaboration will shape not only industries but the very way we understand and preserve human ingenuity. 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: AI Gets Into PublishingOverviewThis newsletter issue brings together a diverse range of stories that center around how artificial intelligence is reshaping the technology, investment, legal, and media landscapes. While AI is fueling record-breaking funding rounds and accelerating product innovations, it is also stirring legal debates and forcing publishers and content creators to rethink their business models in a rapidly evolving digital ecosystem.Listeners can expect an engaging discussion on how advanced funding and interoperability trends are driving AI's integration into products and operations, alongside the challenges of copyright enforcement and digital disruption in media. The collection underscores the multifaceted impact of AI—from high-stakes investments and legal contestations to product innovations that bridge text and image, and even the transformation of publishing itself.Key Trend 1: Massive AI Funding and Investment TransformationsAcross several articles, the newsletter highlights how record-breaking funding rounds and strategic investments are accelerating AI development. Investors are betting big on AI innovations—from OpenAI's nearly $40 billion funding initiative to unicorn startups driven by healthcare, cybersecurity, and agentic AI applications.- Talking Point 1: The surge in capital backing AI ventures underscores the strategic importance of financial support for cutting-edge innovation.- For example, TechCrunch reported that OpenAI is close to closing a SoftBank-led $40 billion round, emphasizing that “substantial capital is becoming critical for scaling advanced AI research” ([TechCrunch](https://techcrunch.com/2025/03/26/openai-will-reportedly-close-its-softbank-led-40-billion-round-soon/)).- Similarly, venture capital trends observed in the “Venture Beacon” report show improved fundraising conditions and fewer down rounds, signaling renewed investor confidence ([DEallawyers](https://www.deallawyers.com/blog/2025/03/survey-the-state-of-venture-capital.html)).- Talking Point 2: The evolving model of liquidity in venture-backed companies, where secondary transactions now dominate, marks a fundamental restructuring of investment dynamics.- As highlighted in “The Great Liquidity Shift,” 71% of exit dollars originated from secondary transactions rather than traditional IPOs or M&A, reflecting an adaptive strategy in turbulent markets ([Tom Tunguz](https://tomtunguz.com/the-exit-path-of-2024/)).- Unicorn reports from Crunchbase further illustrate how investments in sectors like healthcare and cybersecurity are reshaping the valuation landscape and fueling innovation ([Crunchbase](https://news.crunchbase.com/cybersecurity/healthcare-unicorns-ai-february-2025/)).Key Trend 2: Legal and Ethical Challenges in AI CommercializationThe newsletter also delves into the legal front where AI's rapid evolution collides with longstanding copyright and ethical concerns. Legal disputes and regulatory uncertainties are emerging as key hurdles that tech companies and publishers must navigate.- Talking Point 1: AI's use of copyrighted content is under intense legal scrutiny, as seen in the lawsuit against OpenAI.- A recent ruling allowed a copyright lawsuit, initiated by the New York Times, against OpenAI to proceed, highlighting the risks of using copyrighted materials without permission ([TheInformation](https://www.theinformation.com/briefings/judge-allows-copyright-lawsuit-openai-proceed)).- This case opens the debate on balancing technological innovation with the protection of intellectual property rights—a challenge that is critical in shaping future AI training practices.- Talking Point 2: Traditional publishers are grappling with how AI-driven tools disrupt established economic models and audience engagement.- For instance, the World History Encyclopedia's dramatic 25% drop in traffic due to Google's AI Overviews demonstrates how AI-driven content summarization can undercut traditional revenue streams ([BigTechnology](https://www.bigtechnology.com/p/as-ai-takes-his-readers-a-leading?publication_id=46510&utm_campaign=email-post-title&r=ktr9&utm_medium=email)).- This tension invites a broader discussion about reimagining compensation and support structures for content creators in the age of AI.Key Trend 3: Integration and Interoperability of AI Across TechnologiesA recurring theme is the drive toward openness and integration across AI platforms, which is transforming user experiences and broadening the capabilities of digital tools.- Talking Point 1: Open standards and interoperability are becoming essential as firms seek to integrate AI functions seamlessly into their products.- OpenAI's decision to adopt Anthropic's Model Context Protocol signals a commitment to interoperability—enabling better data integration and more scalable AI solutions ([TechCrunch](https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data/)).- This collaborative evolution between past rivals underlines the fact that open source solutions are a strategic lever for rapid innovation.- Talking Point 2: Technological breakthroughs in multimodal AI systems are setting new consumer expectations.- The introduction of GPT-4o's native image generation within ChatGPT marks a leap forward, merging text and visuals to deliver “a frightening degree of verisimilitude” ([TechJuice](https://www.techjuice.pk/openai-enhances-chatgpt-with-powerful-native-image-generation-using-gpt-4o/)).- Such advancements not only redefine creative workflows for digital artists but also raise important questions about ethical usage and intellectual property protections.Key Trend 4: The Evolving State of Digital Publishing and MediaDigital publishers are being forced to innovate as AI disrupts legacy models of content distribution and audience engagement. Traditional media outlets are exploring new strategies to sustain relevance and revenue.- Talking Point 1: AI-powered tools are reshaping how readers access and engage with content, challenging longstanding agreements between publishers and tech platforms.- The experience of the World History Encyclopedia, which lost 25% of its traffic to AI-generated summaries by Google, underscores the disruptive impact of AI in digital publishing ([BigTechnology](https://www.bigtechnology.com/p/as-ai-takes-his-readers-a-leading?publication_id=46510&utm_campaign=email-post-title&r=ktr9&utm_medium=email)).- This trend pushes publishers to reconsider their business models while also prompting questions about fairness and compensation.- Talking Point 2: In response, some traditional outlets are embracing change by integrating independent creator networks to diversify their content and engage newer audiences.- A notable example is Fast Company's launch of a creator network featuring independent writers, which aims to bridge the gap between conventional journalism and the digital content revolution ([TheInformation](https://www.theinformation.com/articles/30-year-old-magazine-embracing-creators)).- This approach not only rejuvenates content delivery but also serves as a model for how heritage media can adapt in a rapidly shifting digital ecosystem.Discussion Questions- How do the massive funding rounds for AI companies influence the pace of technological innovation, and what risks do these investments entail?- In what ways should legal frameworks evolve to address the challenges posed by AI's use of copyrighted content?- Can the integration of open standards in AI systems truly accelerate innovation, or does it create new vulnerabilities in an increasingly interconnected ecosystem?- How should traditional publishers rethink their revenue models when AI-driven content summarization threatens direct engagement?- What are the implications of shifting exit strategies in venture capital, particularly with the rise of secondary transactions over traditional IPOs?- Is the democratization of creative tools through multimodal AI a net positive for artistic communities, or does it risk eroding the value of human creativity?- How can media outlets balance the need for innovative content delivery with maintaining rigorous ethical and copyright standards?Closing SegmentThe discussion today underlines four fundamental trends: record-setting AI investments, mounting legal and ethical challenges, the push for interoperability and groundbreaking multimodal innovations, and the evolving landscape of digital publishing. Together, these trends highlight not only the transformative potential of AI but also the complex interplay of finance, law, and creative expression. As we consider the future of technology and media, it's clear that innovation must be balanced with responsibility—ensuring that the rapid pace of change benefits society as a whole.A compelling final thought: In an era defined by disruption, the true winners will be those who not only drive innovation but also establish ethical and robust frameworks that safeguard creativity, fairness, and integrity. 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

Talking Points from the Newsletter's EditorialCritique of European Commission's Regulatory Actions • The editorial strongly criticizes the European Commission's enforcement of interoperability requirements under the Digital Markets Act (DMA), particularly targeting Apple. It views these measures as an example of governmental overreach into business decisions, arguing that market forces are sufficient to regulate companies like Apple. • Key EU demands include opening iOS features to third-party developers, which Apple claims will hinder innovation and compromise user privacy. • The editorial contrasts this regulatory approach with the organic diffusion of AI technologies, as described by OpenAI CEO Sam Altman, who likens AI's impact to the transistor—ubiquitous, cheap, and transformative.Technological Innovation vs. Ideological Divides • The editorial highlights a growing ideological divide between progressives and conservatives regarding technology. Progressives are portrayed as skeptical of technological advancements, while conservatives embrace innovation and acceleration. • Jaye Chen's essay on STEM graduates leaning toward conservative ideologies underscores this shift, attributing it to progressives' failure to integrate technical talent into their causes and their tendency to view technology as a problem needing control.Celebration of Recent Tech Achievements • The editorial celebrates notable technological breakthroughs, including: • OpenAI's launch of its high-performance O1-Pro AI model. • BYD's unveiling of EV batteries capable of recharging in five minutes. • Nvidia's announcement of next-generation products that are 100 times faster than current offerings.Introduction of ‘Reflect' App • The editorial introduces a new app called Reflect, designed to help teens privately discuss life challenges. It leverages AI tools such as OpenAI, Perplexity, and Anthropics Claude as conversational partners for emotional support.Advocacy for Market-Driven Innovation • The overarching theme advocates for minimizing government interference in economic and technological decisions. It argues that markets are better equipped to judge corporate failures or successes without regulatory micromanagement 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

Here's a prioritized list of talking points focusing on the gravity of each issue for humanity, based on the provided sources:• The rapid advancement of AI and its potential impact on society:◦ The editorial highlights that technological advancement is reshaping the world at an unprecedented speed, raising questions about the value of civilization itself.◦ The AI revolution could lead to post-scarcity abundance, potentially solving humanity's most intractable problems.• The geopolitical implications of AI and chip manufacturing:◦ The semiconductor supply chain remains precarious despite the booming AI industry.◦ The U.S. chip ban and restrictions have unintended consequences, potentially causing countries to rely on China.◦ Sheikh Tahnoon bin Zayed Al Nahyan is leveraging wealth to propel the UAE to the forefront of the global AI race, balancing ties with China and the U.S..• The transformation of information interfaces and potential for democratization of knowledge:◦ AI-powered browsers may democratize knowledge and reduce information asymmetries, enabling individuals to navigate complexity independently.• The role of government in the age of AI and regulation:◦ The government should enable experimentation while establishing guardrails, avoiding control or restriction of development.◦ There are mounting concerns among European founders that the region's bureaucracy is impeding its capacity for innovation and growth.• The limitations of AI and the need for human wisdom:◦ While AI excels at qualitative insights, it still struggles with deterministic tasks.◦ In venture capital, the ability to make "irrational" decisions based on gut feeling and emotional intelligence becomes a priceless asset.• The increasing competition and innovation in the AI sector:◦ Chinese companies like DeepSeek are disrupting markets, spurring competition.◦ Tencent unveiled an AI model to rival DeepSeek's rapid response system.• The emergence of AI-powered apps and "vibecoding":◦ ChatGPT prompts could evolve into standalone apps, potentially reshaping software development.◦ A.I. tools allow nontechnical hobbyists to build apps and websites by typing prompts.• The launch of new AI models and tools:◦ OpenAI launched GPT-4.5 “Orion,” its largest AI model.◦ Anthropic released Claude 3.7 Sonnet, a "hybrid reasoning model".• Venture capital investment trends:◦ Data-driven research has commoditized VC, making human judgment more critical.◦ VC Firm Slow Ventures is investing in content creators.◦ Taktile's AI decision platform is receiving funding from top investors.• Other startup and tech industry developments:◦ Perplexity is launching its AI browser, Comet.◦ Stripe's valuation is surging, reflecting VC hopes and fears.◦ Snowflake is growing its startup accelerator.◦ Venus Williams is backing the WeWard startup that rewards users for walking.◦ Nomagic is developing AI-powered robotic arms. 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

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

#44 of the 2024 That Was The Week Newsletter. I'm with Musk discusses the politicization of everything and the need to focus on the core ideas and how they relate to human 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

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

There is one winner regarding the most significant story this week. Elon Musk and Vivek Ramaswamy have been made advisors to the Trump administration on Government efficiency in a department called DOGE (Department of Government Efficiency). Their advisor status is widely assumed to be to avoid apparent conflicts, but in reality, they are likely to wield much power.It is rumored that Marc Andreessen was also seen on election night in Mara-a-Lago and is engaged in giving Trump advice on Tech issues.Many of my friends (perhaps you are one of them) are horrified that Elon has this much power and are inclined to assume bad things will happen. That may well be right, but….. 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

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

Hat Tip to this week's creators: @BrankoMilan, @europressos, @AfPalasciano, @adam_tooze, @MCC_Brussels, @Norm_Lewis, @KateClarkTweets, @Alex_Lazarow, @AABerwick, @BenFoldy, @peternixey, @rhodgkinson, @andyjayhawk, @_odsc, @Kantrowitz, @amir, @steph_palazzolo, @Kyle_L_Wiggers, @girlstothefront, @mcbridesg, @geneteare, @elonmuskContentsEditorial: Essays of the WeekCan an international economic system exist in the world of nationalisms?Draghi Says EU Itself at Risk Without More Funds, Joint DebtDraghi's view of Europe: Investment, R&D & the US-EU comparisonMusk, Telegram and the European Assault on Online SpeechVenture Capitalists Turn to Novel Methods to Return CashThe Rise Of Fintech FamiliesThe Shadow Dollar That's Fueling the Financial UnderworldStartup Success - How to Measure it?Illiquidity is a feature, not a bugVideo of the WeekElon Musk Live at All In SummitAI of the WeekWaymo and Uber expand their robotaxi partnership to Austin and AtlantaNew AI Chip Surpasses Nvidia, AMD, and Intel with 20x Faster Speeds and Over 4 Trillion TransistorsIs OpenAI's New “o1” Model The Big Step Forward We've Been Waiting For?OpenAI COO Says ChatGPT Passed 11 Million Paying SubscribersOpenAI In Talks To Raise $6.5 Billion at $150 Billion ValuationKeen On: Gary Marcus on How to Tame Silicon Valley's AI BaronsMistral releases Pixtral 12B, its first multimodal modelNews Of the WeekWhy the SpaceX spacewalk is such a huge dealSilicon Valley's Y Combinator to Double Number of Cohorts Per YearThe Unicorn Board Adds 8 New Companies, With One Newly Minted Entry Valued At $16B Startup of the WeekAI-Powered Work Assistant Glean Doubles Valuation To $4.6B In Less Than Seven MonthsX of the WeekAustralian Government is “Fascist” - Elon Musk 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

Hat Tip to this week's creators: @albertwenger, @chaykak, @washingtonpost, @pxlnv, @gideonrachman, @paulg, @KateClarkTweets, @scottehartley, @geneteare, @jesslivingston, @ycombinator, @garrytan, @rhodgkinson, @signalrank, @jordannovet, @erinkwoo, @markgurman, @Kyle_L_Wiggers, @CovariantAI, @_thatstartupguy 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

I am still on my summer hiatus, but Andrew's travel was postponed, and he wanted to do a show. So here it is, video only. Enjoy, and see you on August 16th. 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

Hat Tip to this week's creators: @jaredheyman, @PeterJ_Walker, @cartaInc, @Om, @davemcclure, @vntrcapital, @mgsiegler, @sarahfielding_, @elevenlabsio, @fredwilson, @markgurman, @e_howcroft, @UtkarshShetti, @steph_palazzolo, @runwayml, @EricHSchwartz, @CloudflareContentsEditorial: Rise of the Algorithms: Private Markets Indexing is Coming.Essays of the WeekLarry Fink says BlackRock's deal to acquire Preqin could lead to indexing private markets.On Rebel Theorem 3.0First Cut—State of Private Markets: Q2 2024The Future of Writing: How AI Will Reshape Our ToolsVideo of the WeekFrom Startups to Secondary VC Investments: Dave McClure's Insights from 500 Startups and Paypal (VNTR)AI of the WeekLowering the Boom on the New Boom TimesYou can now get AI Judy Garland or James Dean to read you the newsThe USV LibrarianApple Poised to Get OpenAI Board Observer Role as Part of AI PactOpenAI CTO Admits Creative Jobs Can Be Harmed By AINews Of the WeekCircle Becomes First to Receive License in the EU to Issue Stablecoins Under MiCABritain's Revolut surges to record profit as it seeks $40 bln valuationKuo: New AirPods to Feature Cameras for Enhanced Spatial ExperiencesStartup of the WeekRunway, an AI Video Startup, in Talks With General Atlantic for $4 Billion–Valuation FundraiseX of the WeekCloudflare AI bot blocker 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

Hat Tip to this week's creators: @PeterJ_Walker, @mgsiegler, @jglasner, @lennysan, @AndreRetterath, @alex, @pmarca, @nklsrh, @dmehro, @timmarchman, @adamclarkestes, @Kyle_L_Wiggers, @MTemkiContentsEditorial: Essays of the WeekIs there an AI Bubble?Robotics Startups On The Rise In 2024Behold: the HackquisitionThe Entrapment of AppleThe social radar: Y Combinator's secret weapon | Jessica LivingstonCan We Fully Automate Startup Investing?The 2024 IPO I'm Most Excited AboutVideo of the WeekThe true story -- as best I can remember -- of the origin of Mosaic and Netscape.AI of the WeekI Will F*****g Piledrive You If You Mention AI AgainPerplexity Is a B******t MachineWhat, if anything, is AI search good for?Andrew Ng plans to raise $120M for next AI FundNo MacBook Air Killer, All MacBook Air FillerHebbia raises nearly $100M Series B for AI-powered document search led by Andreessen HorowitzNews Of the WeekNo, a $100m + Series A Round isn't NormalIt takes ten years to succeed as a StartupElon Musk has won $56bn pay package despite judge ruling it void, Tesla arguesKleiner Perkins announces $2 billion in fresh capital, showing that established firms can still raise large sumsStartup of the WeekWebtoon Rises Modestly In IPO DebutX of the WeekAI Poetry Camera? Seriously?EditorialIt's Sunday, two days later than I usually send this out. Two excuses. I was in recovery from PTSD after the “debate.” And then I almost had a relapse watching England in the Euro last 16 game against Slovakia.I'm unsure of my mental state now (we won 2-1 in extra time). But the other, more important “game” is still undecided.But in AI, it seems everybody is getting PTSD from wild allegations that AI might kill the human race to now new suggestions that there may be a bubble in valuations for early-stage companies.The items in this week's newsletter are really good. MG Seigler, Alex Wilhelm and Peter Walker dominate. The first two are former TechCrunch writers (hats off to Mike Arrington for his talent-spotting). Peter is the leading contributor to VC data; he has access to Carta data and uses it super effectively.MG and Alex have relatively new newsletter sites - SpyGlass and Cautious Optimism, respectively). They are great observers and even better writers - subscribe. Links in their articles are below.Big tech seems to be running scared of AI regulation. This from MG Seigler's : No MacBook Air Killer, All MacBook Air FillerMicrosoft really s**t the bed here both from a security and PR perspective. And what's left sounds very 'meh'. It's almost like Microsoft forget the 'Copilot' part of 'Copilot+ PCs'. And certainly they forgot the '+' part.MG also wrote about the EU and Apple, claiming that the EU is seeking to entrap Apple by refusing to state what Apple can and cannot do with its AI intentions. Apple, in response, is saying it will not launch AI in Europe until the EU says what product flexibility it has.You have to smile. Apple plays this game super well.Finally, he has ‘Behold the Hackquisition', which shows how big tech avoids M&A blocks by buying teams instead of companies.Alex Wilhelm's anticipation of the Circle (USDC) IPO is a great example of his regular style and substance.Peter Walker heads up data storytelling at Carta (great title). This week, he also has three pieces, all originally posted on his LinkedIn profile.‘Is there an AI bubble' (my title) examines the spread of Series A venture funding valuations. He separates the percentiles and measures the spread between them, noting that the gap between the 50th percentile and the 95th is the widest ever - even wider than 2021 and 2022. This is for SaaS rounds that include much AI.In H1 2019, the 50th percentile for pre-money valuations was $26M (Series A SaaS companies only, primary rounds). The 95th pct at that time was $96M.Now that's a pretty large gap. We're talking a 3.7x jump from the middle to the top end.But today things are even more skewed.

Hat Tip to this week's creators: @leopoldasch, @JoeSlater87, @GaryMarcus, @ulonnaya, @alex, @ttunguz, @mmasnick, @dannyrimer, @imdavidpierce, @asafitch, @ylecun, @nxthompson, @kaifulee, @DaphneKoller, @AndrewYNg, @aidangomez, @Kyle_L_Wiggers, @waynema, @QianerLiu, @nicnewman, @nmasc_, @steph_palazzolo, @nofilmschoolContents* Editorial: * Essays of the Week* Situational Awareness: The Decade Ahead* ChatGPT is b******t* AGI by 2027?* Ilya Sutskever, OpenAI's former chief scientist, launches new AI company* The Series A Crunch Is No Joke* The Series A Crunch or the Seedpocalypse of 2024 * The Surgeon General Is Wrong. Social Media Doesn't Need Warning Labels* Video of the Week* Danny Rimer on 20VC - (Must See)* AI of the Week* Anthropic has a fast new AI model — and a clever new way to interact with chatbots* Nvidia's Ascent to Most Valuable Company Has Echoes of Dot-Com Boom* The Expanding Universe of Generative Models* DeepMind's new AI generates soundtracks and dialogue for videos* News Of the Week* Apple Suspends Work on Next Vision Pro, Focused on Releasing Cheaper Model in Late 2025* Is the news industry ready for another pivot to video?* Cerebras, an Nvidia Challenger, Files for IPO Confidentially* Startup of the Week* Final Cut Camera and iPad Multicam are Truly Revolutionary* X of the Week* Leopold AschenbrennerEditorialI had not heard of Leopold Aschenbrenner until yesterday. I was meeting with Faraj Aalaei (a SignalRank board member) and my colleague Rob Hodgkinson when they began to talk about “Situational Awareness,” his essay on the future of AGI, and its likely speed of emergence.So I had to read it, and it is this week's essay of the week. He starts his 165-page epic with:Before long, the world will wake up. But right now, there are perhaps a few hundred people, most of them in San Francisco and the AI labs, that have situational awareness. Through whatever peculiar forces of fate, I have found myself amongst them.So, Leopold is not humble. He finds himself “among” the few people with situational awareness.As a person prone to bigging up myself, I am not one to prematurely judge somebody's view of self. So, I read all 165 pages.He makes one point. The growth of AI capability is accelerating. More is being done at a lower cost, and the trend will continue to be super-intelligence by 2027. At that point, billions of skilled bots will solve problems at a rate we cannot imagine. And they will work together, with little human input, to do so.His case is developed using linear progression from current developments. According to Leopold, all you have to believe in is straight lines.He also has a secondary narrative related to safety, particularly the safety of models and their weightings (how they achieve their results).By safety, he does not mean the models will do bad things. He means that third parties, namely China, can steal the weightings and reproduce the results. He focuses on the poor security surrounding models as the problem. And he deems governments unaware of the dangers.Although German-born, he argues in favor of the US-led effort to see AGI as a weapon to defeat China and threatens dire consequences if it does not. He sees the “free world” as in danger unless it stops others from gaining the sophistication he predicts in the time he predicts.At that point, I felt I was reading a manifesto for World War Three.But as I see it, the smartest people in the space have converged on a different perspective, a third way, one I will dub AGI Realism. The core tenets are simple:* Superintelligence is a matter of national security. We are rapidly building machines smarter than the smartest humans. This is not another cool Silicon Valley boom; this isn't some random community of coders writing an innocent open source software package; this isn't fun and games. Superintelligence is going to be wild; it will be the most powerful weapon mankind has ever built. And for any of us involved, it'll be the most important thing we ever do. * America must lead. The torch of liberty will not survive Xi getting AGI first. (And, realistically, American leadership is the only path to safe AGI, too.) That means we can't simply “pause”; it means we need to rapidly scale up US power production to build the AGI clusters in the US. But it also means amateur startup security delivering the nuclear secrets to the CCP won't cut it anymore, and it means the core AGI infrastructure must be controlled by America, not some dictator in the Middle East. American AI labs must put the national interest first. * We need to not screw it up. Recognizing the power of superintelligence also means recognizing its peril. There are very real safety risks; very real risks this all goes awry—whether it be because mankind uses the destructive power brought forth for our mutual annihilation, or because, yes, the alien species we're summoning is one we cannot yet fully control. These are manageable—but improvising won't cut it. Navigating these perils will require good people bringing a level of seriousness to the table that has not yet been offered. As the acceleration intensifies, I only expect the discourse to get more shrill. But my greatest hope is that there will be those who feel the weight of what is coming, and take it as a solemn call to duty.I persisted in reading it, and I think you should, too—not for the war-mongering element but for the core acceleration thesis.My two cents: Leopold underestimates AI's impact in the long run and overestimates it in the short term, but he is directionally correct.Anthropic released v3.5 of Claude.ai today. It is far faster than the impressive 3.0 version (released a few months ago) and costs a fraction to train and run. it is also more capable. It accepts text and images and has a new feature that allows it to run code, edit documents, and preview designs called ‘Artifacts.'Claude 3.5 Opus is probably not far away.Situational Awareness projects trends like this into the near future, and his views are extrapolated from that perspective.Contrast that paper with “ChatGPT is B******t,” a paper coming out of Glasgow University in the UK. The three authors contest the accusation that ChatGPT hallucinates or lies. They claim that because it is a probabilistic word finder, it spouts b******t. It can be right, and it can be wrong, but it does not know the difference. It's a bullshitter.Hilariously, they define three types of BS:B******t (general)Any utterance produced where a speaker has indifference towards the truth of the utterance.Hard b******tB******t produced with the intention to mislead the audience about the utterer's agenda.Soft b******tB******t produced without the intention to mislead the hearer regarding the utterer's agenda.They then conclude:With this distinction in hand, we're now in a position to consider a worry of the following sort: Is ChatGPT hard b**********g, soft b**********g, or neither? We will argue, first, that ChatGPT, and other LLMs, are clearly soft b**********g. However, the question of whether these chatbots are hard b**********g is a trickier one, and depends on a number of complex questions concerning whether ChatGPT can be ascribed intentions.This is closer to Gary Marcus's point of view in his ‘AGI by 2027?' response to Leopold. It is also below.I think the reality is somewhere between Leopold and Marcus. AI is capable of surprising things, given that it is only a probabilistic word-finder. And its ability to do so is becoming cheaper and faster. The number of times it is useful easily outweighs, for me, the times it is not. Most importantly, AI agents will work together to improve each other and learn faster.However, Gary Marcus is right that reasoning and other essential decision-making characteristics are not logically derived from an LLM approach to knowledge. So, without additional or perhaps different elements, there will be limits to where it can go. Gary probably underestimates what CAN be achieved with LLMs (indeed, who would have thought they could do what they already do). And Leopold probably overestimates the lack of a ceiling in what they will do and how fast that will happen.It will be fascinating to watch. I, for one, have no idea what to expect except the unexpected. OpenAI Founder Illya Sutskever weighed in, too, with a new AI startup called Safe Superintelligence Inc. (SSI). The most important word here is superintelligence, the same word Leopold used. The next phase is focused on higher-than-human intelligence, which can be reproduced billions of times to create scaled Superintelligence.The Expanding Universe of Generative Models piece below places smart people in the room to discuss these developments. Yann LeCun, Nicholas Thompson, Kai-Fu Lee, Daphne Koller, Andrew Ng, and Aidan Gomez are participants. 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

Hat Tip to this week's creators: @tedgioia, @benthompson, @stratechery, @peterwalker99, @omri_drory, @sama, @mariogabriele, @gruber, @giannandrea, @craigfederighi, @gregjoz, @alex, @MParekh, @waxeditorial, @romaindillet, @cookie, @ttunguz, @KantrowitzContents* Editorial: Checkmate!* Essays of the Week* Is Silicon Valley Building Universe 25?* Apple Intelligence is Right On Time* 2018 cohort graduation rates?* How VCs Become A******s* Startup Playbook* How to Find a Unicorn* Video of the Week* John Gruber, John Giannandrea, Craig Federighi, and Greg Joswiak on Apple Intelligence* AI of the Week* OpenAI's growth is one of the most astounding business results of all time* AI: New Focus on 'Accelerated' Local AI Devices. RTZ #387* News Of the Week* visionOS 2: Spatial Personas Can Touch Fingers, High Five, Fist Bump Each Other With Visual and Audio Feedback* Raspberry Pi is now a public company* Carta's valuation to be cut by $6.5 billion in upcoming secondary sale* LinkedIn Adds New Elements to Its Newsletter Creation Platform* Startup of the Week* Databricks' Accelerating Growth* X of the Week* 3, 3 Trillion Dollar CompaniesEditorial: Checkmate!Checkmate! That seems like the appropriate word if you analyze what happened with OpenAI this week.After being built into every conceivable Microsft interface, Apple announced that it would integrate OpenAI into all of its operating systems across devices via Siri.By locking up Microsoft and Apple, it has effectively locked out Google, at least for now. That will leave Google itself as the only large implementation of its Gemini AI family.This gives Apple a global advantage in the iPhone versus Android battle. Few will prefer Gemini to OpenAI.Beyond that, Apple successfully showed how its own ‘Apple Intelligence' will face inwards to the device, interoperating with all apps and supporting ‘actions' while leaving all user data on the device. And when you need more power than the device can deliver, the new Apple Intelligence Cloud steps up in a fully encrypted secure environment. Even Apple cannot decrypt your data as it has no keys.Ben Thompson from Stratechery sums up Apple's play as follows:This is good news for Apple in two respects. First, with regards to the title of this Article, the fact it is possible to be too early with AI features, as Microsoft seemed to be in this case, implies that not having AI features does not mean you are too late. Yes, AI features could differentiate an existing platform, but they could also diminish it. Second, Apple's orientation towards prioritizing users over developers aligns nicely with its brand promise of privacy and security: Apple would prefer to deliver new features in an integrated fashion as a matter of course; making AI not just compelling but societally acceptable may require exactly that, which means that Apple is arriving on the AI scene just in time.The concept of “just in time” seems appropriate. Although, as a developer possessing all of the beta products, I can say that very few of the features announced are yet available.The contrast with Microsoft couldn't be more extreme. Its Recall product, which took a screen recording every five seconds and stored its findings in clear text on the device, got a backlash from journalists and privacy campaigners. Microsoft has all but canceled the product, and its PR tail is between its legs. Apple's ‘Crush' ad has almost been forgotten.Microsoft could make a mistake here. It is already working on products competing with OpenAI and might be tempted to go alone. What Bing is to Google, Microsoft AI will be to OpenAI. If it does so, it will once again shoot itself in the foot. OpenAI is far ahead in features and capabilities. Google cannot integrate it. Microsoft has gained an advantage from having done so. Apple too. Don't bite the hand that feeds you seems an apt reminder.This week's essays focus a lot on the social impact of innovation and venture capital.Ted Gioia's essay about “Universe 25” focuses on the Durkheim concept of ‘anomie.' It is the idea that our isolation leads to meaninglessness in life.“More than 100 years ago, sociologist Emile Durkheim studied the problem of anomie. That's not a word you hear very often nowadays. But we need to bring it back.Anomie is a sense that life has no purpose or meaning. The people who suffer from it are listless, disconnected, and prone to mental illnesses of various sorts. Durkheim believed, for example, that suicide was frequently caused by anomie.But the most shocking part of Durkheim's analysis was his view that anomie increased when social norms were lessened. You might think that people rejoice when rules and regulations get eliminated. But Durkheim believed the exact opposite.”Gioia examines the aimlessness of a world where people live in social media.The Venture Capital essays are excellent. Sam Altman's ‘Startup Playbook' contains intelligent advice for startup founding teams. And Mario Gabriele's piece about ‘How to Find a Unicorn' has good advice for emerging fund managers. Omri Drory's piece: How VCs Become A******s - is both funny and true. A great read 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 reminder for new readers. That Was The Week includes a collection of my selected readings on critical issues in tech, startups, and venture capital. I selected the articles because they are of interest to me. The selections often include things I entirely disagree with. But they express common opinions, or they provoke me to think. The articles are snippets sized to convey why they are of interest. Click on the headline, contents link, or the ‘More' link at the bottom of each piece to go to the original. I express my point of view in the editorial and the weekly video below.Hat Tip to this week's creators: @reidhoffman, @dougleone, , @credistick, @rex_woodbury, @NathanLands, @ItsUrBoyEvan, @berber_jin1, @cityofthetown, @keachhagey, @pmarca, @bhorowitz, , @signalrank, @steph_palazzolo, @julipuli, @MTemkin, @geneteare, @lorakolodny, @jasminewsun, @JBFlint, @asharma, @thesimonetti, @lessinContents* Editorial: * Essays of the Week* Crossing The Series A Chasm* The Consumer Renaissance* The Creator Economy on AI Steroids* AI Is Transforming the Nature of the Firm* The Opaque Investment Empire Making OpenAI's Sam Altman Rich* Video of the Week* The American Dream - Marc Andreessen and Ben Horowitz* AI of the Week* SignalRank Version 3 Improves Performance Again* How Long Can OpenAI's First-Mover Advantage Last?* OpenAI Employees Warn of Advanced AI Dangers* A Right to Warn about Advanced Artificial Intelligence* Nvidia hits $3tn and surpasses Apple as world's second-most valuable company* VCs are selling shares of hot AI companies like Anthropic and xAI to small investors in a wild SPV market* News Of the Week* Crunchbase Monthly Recap May 2024: AI Leads Alongside An Uptick In Billion-Dollar Rounds* Elon Musk ordered Nvidia to ship thousands of AI chips reserved for Tesla to X and xAI* Introducing video to Substack Chat* Instagram's Testing Video Ads That Stop You From Scrolling Further* Startup of the Week* NBA Nears $76 Billion TV Deal, a Defining Moment for Media and Sports* X of the Week* Doug Leone - I am supporting Trump. * Reid Hoffman - I am supporting BidenEditorialI woke on Tuesday to Doug Leone of Sequoia Capital on X saying:I have become increasingly concerned about the general direction of our country, the state of our broken immigration system, the ballooning deficit, and the foreign policy missteps, among other issues. Therefore, I am supporting former President Trump in this coming election.Doug has the right to support Trump. It is also clear that the immigration system is broken, the deficit is ballooning, many things are wrong with foreign policy, and there are “other issues.” Trump as the solution is less obvious. But there it is—hot on the tails of Chamath Palihipitaya and David Sacks announcing a fund-raiser for Trump on the All-In podcast (they said they would do the same for Biden).Reid Hoffman followed up a day later with:On one level, this is a straightforward choice, but any literate attempt to analyze Leone's issues might arrive at the following conclusions:* Like many Western nations, the USA is aging rapidly and has a shrinking working-age population across all skill sets. Immigrants are needed, and pro-immigration leadership is needed, creating a path to entry for large numbers of skilled and unskilled workers to fill empty jobs as we get close to full employment.* The deficit is large, and there are many palliatives available. Selling more to China would help, but both party leaders are protectionist. Taxes to reduce the divide between the 1% and the rest would help a bit. However, what would help the most is economic growth, which requires investment in technology and productivity. Neither leader seems too focused on innovation and investment.* Foreign Policy - well, sheesh, it's a big issue. However, saber-rattling about Taiwan and provoking China seems to be a hobby shared by both parties and does not seem smart. Ukraine and the future of Europe are better in Biden's hands, but not by a lot. Europe looks very shaky. The US is increasingly isolationist. The appetite for world leadership is on the decline. Again, the solution would focus on economic growth, which seems absent.Voting for Trump is a big no-no for me. But voting for Biden is, at best, a lesser evil instinct, not a belief system. The election will not be where the future is built, but it is important. Politicians are collectively disappointing.This week's video of the week from Marc Andreessen and Ben Horowitz is called “The American Dream” and champions their view about American Dynamism. And I must confess that this comes closer to a vision of the future than either political outfit. Their vision requires political support, massive government financial commitment, and private capital investment. I see no evidence of those happening.The real winning effort seems to be happening on the ground. This week, Nvidia hit $3 trillion, eclipsing Apple as the world's second-most valuable company. This is even though Apple has 7 times the revenue of Nvidia.This week's first essays also focus on prospects for boom time. Rex Woodbury's ‘The Consumer Renaissance' examines the impact of consumer spending on our lives. In ‘The Creator Economy on AI Steroids, ' Nathan Lands focuses on how emerging tools will transform creativity. But in ‘AI Is Transforming the Nature of the Firm, ' Evan Armstrong gets closest to a future vision.”AI is the first universally flexible technology. It can interact with our digital environments in similar ways to humans, so it can have all the flexibility that we do. In that way, it may be the last technology we ever need.This seems to be the crux of hope in a world where dreams and nightmares are strangely devoid of detail. What the world needs (not only America) is hope. And hope is born from optimism. Optimism is born from success. The most likely success of the next decades will result from specific uses of AI that improve human life.I know and like Doug Leone. I know and like Reid Hoffman. Doug's bar for success needs to be higher. Voting for Trump is not right, and even if it were, it would not be sufficient.Reid also needs a higher bar. Voting for Biden will not be sufficient even if it is right.Let's focus on where success can be found, grow optimism, and breed hope. There is a need for a broad technical revolution and the social rebirth it enables. Silicon Valley and its friends globally need to invent the next version of human existence to the benefit of all. The social rebirth requires a conscious effort; technology will not magically bring it about. More in this week's video.Essays of the WeekCrossing The Series A ChasmDan GrayDan Gray, a frequent guest author for Crunchbase News, is the head of insights at Equidam, a startup valuation platform, and a venture partner at Social Impact Capital.June 5, 2024As we get deeper into 2024, there is increasing concern about the state of Series A fundraising. The bar for investment appears much higher, and fewer startups are reaching it.This is a problem for founders, and investors like Jenny Fielding, managing partner of Everywhere Ventures, who said, “Every Seed investor's dilemma: All my Series A buddies want to meet my companies early! All my companies are too early for my Series A buddies.”To attach some data to this, we can see that the median step-up in valuation from seed to Series A has gone from $19.5 million in Q1 2022 to $28.7 million in Q1 2024. Series A firms seem to be looking for much stronger revenue performance, with targets of $2 million to $3 million in ARR, compared to $1 million to $2 million just a few years ago.The outcome is that while 31.8% of Q1 2020 seed startups closed their Series A within two years, that fell to just 12% for Q1 2022 — which should worry everyone.Why are Series A investors so much more demanding?Today's Series A investors are looking at startups that raised their seed between 2021 and 2023, which identifies the root of the problem: it spans the Q2 2022 high-tide mark for venture capital.For example, there were 1,695 seed rounds of more than $5 million in 2021, rising to 2,248 in 2022, then falling to 1,521 in 2023. As a comparison, there have been just 137 so far in 2024.The result is two categories of startups that are looking to raise their Series A today:* Pre-crunch startups that raised generous seed rounds and stretched the capital out as far as they could, to grow into inflated valuations.* Post-crunch startups that raised modest seed rounds on more reasonable terms, with shorter runways and less demonstrable growth.Strictly speaking, neither is more appealing than the other; the first group has less risk, the second offers more upside, and both are adapted to current market realities. It shouldn't cause a problem for investors, provided they can distinguish between the two.The cost of market inefficiencyVenture investors have a market-based lens on investment decisions, which means looking fairly broadly at trends in revenue performance and round pricing to determine terms, e.g. a typical Series A is within certain bounds of revenue performance and valuation. While that approach may be serviceable and efficient under ideal conditions, the past few years have been far from ideal.Without distinguishing between the two cohorts, investors are now looking at the performance of Series A candidates that spent more than $5 million on a war chest for two to three years of growth alongside the valuations of candidates that raised around $2 million to prove scalability. It just doesn't work as an average, and thus the unreasonable expectations...MoreThe Consumer RenaissanceFrom Predicting Consumer AI Applications to Analyzing Consumer SpendREX WOODBURY, JUN 05, 2024“Consumer” has become something of a bad word in venture capital circles.We see this reflected in the early-stage markets: recent data from Carta showed that just 7.1% of Seed capital raised last year went to consumer startups. That's less than half the share from 2019 (14.3%).But I think consumer is actually a great place to be building and investing. Whenever something is out of favor, that's a sign it's probably a good place to spend time: this is an industry built on being contrarian, not built on following the herd. We're entering a compelling few years for consumer entrepreneurship.First, I'd argue that consumer is too narrowly defined. When people think consumer, they often think consumer social (a tough category) or consumer brands (a tough fit for venture compared to internet and software businesses, with typically lower return profiles). But consumer is broader. Consumer encompasses businesses that sell to consumers and those that rely on consumer spending. This means the obvious names—apps on our phones like Uber, Instacart, Spotify—and the enablers: Shopify, for instance, powers online retail; Faire powers offline retail; Unity powers game development. Each of the latter three is B2B2C, in its own way, but I would categorize each is also a consumer technology business.The wins in consumer can be massive. The biggest technology businesses in history began as consumer businesses—Google, Facebook, Apple, Amazon. The original companies comprising FAANG—with Microsoft conspicuously absent—were allconsumer.And some of the best returns of the last five years have stemmed from consumer tech IPOs. At Daybreak, we invest ~$1M at Pre-Seed and Seed. Here's how much a $1M investment in the Seed round of five recent consumer IPOs would yield:Big consumer wins compare favorably to big enterprise wins—relative to Snowflake's market cap, Uber is ~3x in size, Airbnb is ~2x in size, and DoorDash is roughly equal. (Snowflake is the biggest enterprise IPO of the last decade.) The last few years produced a windfall of consumer outcomes, yet investors today almost write off the category.At Daybreak, we don't focus exclusively on consumer; my view is that you need to balance more binary consumer outcomes with B2B SaaS and B2B marketplaces. But we do approach investing through the lens of the consumer—how people make decisions. The buyers of products like Figma and Ramp, after all, are people, and software companies are increasingly selling bottom-up into organizations. The line between consumer and enterprise has been blurring for years.This week's Digital Native makes the argument that consumer tech is a compelling place to build and invest. We'll look at the data to back up this argument, then delve into three categories of consumer that I'm particularly interested in right now:* Checking in on Consumer Spend* Consumer Tech: The Data Doesn't Lie* What to Watch: AI Applications* What to Watch: Shopping* What to Watch: Consumer Health* Rule of Thumb: Follow the SpendThis week we'll cover #1-3, and next week in Part II we'll tackle #4-6.Let's dive in

Hat Tip to this week's creators: @krishnanrohit, @EconSteveM, @abracarioca, @jasonlk, @HarryStebbings, @DavidStreitfeld, @PranavDixit, @amir, @waynema, @ingridlunden, @odsc, @seancaptain, @JacobERobbins, @Kantrowitz, @Ryan_S_Gladwin, @EricNewcomer, @maddierenbarger, @gruber, @paulgContents* Editorial: * Essays of the Week* Whither Utopia?* 1% of VC backed startups will make it past $100M ARR* From $1 to $100m revenue: Scaling VC backed SaaS with Notion Capital* China's $47B semiconductor fund puts chip sovereignty front and center* Chinese scientists develop cure for diabetes, insulin patient becomes medicine-free in just 3 months* Video of the Week* Harry Stebbings and Jason Lemkin on Seed Investing* AI of the Week* If A.I. Can Do Your Job, Maybe It Can Also Replace Your C.E.O.* OpenAI CEO Cements Control as He Secures Apple Deal* OpenAI signs 100K PwC workers to ChatGPT's enterprise tier as PwC becomes its first resale partner* Why London is a Powerhouse in Artificial Intelligence* AI May Dominate Billionaire Family Investments* Generative AI seed funding drops 76% as investors take wait-and-see approach* VC Says "Chaos" Coming for Startups, Ads, and Online Business as Generative AI Eats Web* News Of the Week* Ethereum ETFs: BlackRock Gets $10M Seed Investment and Grayscale Adds Coinbase Custody* Sequoia's Elon Play* Salesforce: We Need 50% More Pipeline Than Before To Hit the Plan* Startup of the Week* New from Lux, makers of Halide:* X of the WeekEditorial: Stand Back, Think Big, Dig DeepWe need big and deep thinkers with bold ideasI used Suno to create a theme song for this newsletter. You can download the MP3 to see how limited my creative skills are, even when using advanced AI.The lyrics are mine and include the following:[Verse]That Was The Week No time to be Meek The goal is to Seek The Next Big Thing [[Chorus]That Was The Week That Was The Week Stand Back Think Big Dig Deep That Was The WeekI'm starting with this in honor of the essay of the week written by Rohit Krishnan - “Whither Utopia”. Rohit charts the rise of utopian ideas (before that was a pejorative term), and the fall of utopian thinking. Toward the end of the essay he states:Instead of grand narratives the focus became on micro narratives, skepticism of rational progress, and, perhaps consequently, a reliance on technology to be the answer.Micro narratives pervade technology today, while macro narratives are frowned upon or described as dangerous. OpenAI has become a magnet for hostility to big ideas and transformative technologies.Rohit points out that technology may have obviated the need for large social thinking about organizing the world. I think that may be a temporal anomaly. As AI improves productivity and frees humans to have more leisure time (in the negative lexicon, “eats jobs”), the macro narrative around wealth distribution is likely to raise its head loudly.So the theme this week is “Stand Back, Think Big, Dig Deep.”It seems very likely that AI, or at least the LLM version we are experiencing now, will remove hours and hours of monotonous work from many humans each week. It seems very likely that the world will become cleverer as Apple introduces AI to the iPhone in Junes WWDC, and Android follows suit. Billions of us will have a ready-made, multi-skilled assistant. Increasingly, it will be able to carry out tasks and report results. It also seems likely that physical beings running computers with this AI embedded, will be capable of real-world tasks. And it seems likely that we will be able to raise science to a new level, as the Chinese diabetes technology reported below demonstrates. Oh, and the entire world will have access to these new skills and tools. The trend will be towards them being free.We are on the verge of an era of enormous advancement in what we can collectively do.So, this is not a time for fear, complaints, or accusations. it is a time to get stuff done.PWC adopting ChatGPT and Apple reportedly doing so are early signals of a new technical revolution.China's $47 billion semiconductor fund (see below) will undoubtedly be able to leverage AI to make advanced semiconductors faster than we made the first ones.The new world will challenge all of today's institutions and require new social arrangements, both globally and locally, as the earth flattens from an economic and demographic point of view and human demands regarding work are reduced.You can't have rapid technical s***s without equally dramatic social s***s. Rohit's historical survey of utopian thinkers demonstrates that all greatly impacted how societies evolved. This generation needs to ask some big questions, dig deep for answers, and do so from an overview of where we are and where we want to go. 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

Hat Tip to this week's creators: @edzitron, @bysarahkrouse, @dseetharaman, @JBFlint, @packyM, @KamalVC, @VaradanMonisha, @Claudiazeisberg, @IDTechReviews, @cjgustafson222, @NathanLands, @psawers, @lightspeedvp, @jaygoldberg, @avcContents* Editorial: Dear Sam, A Letter from a Founder to a Founder* Essays of the Week* Sam Altman Is Full Of S**t* Behind the Scenes of Scarlett Johansson's Battle With OpenAI* Sky voice actor says nobody ever compared her to ScarJo before OpenAI drama* Better Tools, Bigger Companies* The Pervasive, Head-Scratching, Risk-Exploding Problem With Venture Capital* Video of the Week* OpenAI vs Gemini 1.5* AI of the Week* Does AI have a gross margin problem?* OpenAI and Wall Street Journal owner News Corp sign content deal* Scale AI Raises $1B In Accel-Led Round; Hits $13.8B Valuation* The Awful State of AI in California* News Of the Week* It's Time to Believe the AI Hype* The 49-Year Unicorn Backlog* Humane, the creator of the $700 Ai Pin, is reportedly seeking a buyer* NVIDIA CRUSHES EARNINGS, AGAIN* Startup of the Week* SUNO'S HIT FACTORY* Warpcast of the Week* Be GenerousEditorial: Dear Sam, A Letter from a Founder to a Founder.This week let's break the pattern and write this as a letter to Sam Altman.Dear Sam,It's been a swings and roundabouts week for you at OpenAI.I had a week like that in the spring of 1998. I was at Internet World launching RealNames to the world. RealNames invented paid clicks on keywords. Our first partner was AltaVista, and Google was our second—calling the feature "I'm Feeling Lucky."It was the simplest technology ever. We had a keyword, bought by a customer. An example might be Disney buying "Bambi." They would buy it in every country and language they wanted and point it to a specific URL in each place. Search engines would look at the keywords you typed in (later browsers too) and if RealNames had it as a paid keyword, they would send the user to the site, with no search results. Just a direct navigation. RealNames got paid for the customer sent.At the launch, we used the example of the keyword “Bambi” to show how superior our keywords were compared to domain names. In those days, Bambi.com pointed to a porn site. Our launch demo showed that typing "Bambi" went to Disney, but typing "Bambi.com" did not. All was well except we altered our network settings the eve of the launch, and when we demoed the use of "Bambi" at the launch, it (you can guess) went to the porn site.Journalists wrote about RealNames as a scam and bad actors.Luckily, we had great partners, and within 12 hours the network issue was fixed, and all was well. But for 24 hours, I felt like the world was collapsing around me. On the one hand, we launched our company, mostly to great acclaim; on the other, we were being destroyed in the tech media.Sam, I know how this week must have felt. Your decision to pull the ‘Sky' voice was right. And despite the horrors of the first 24 hours, this will pass.That said, you mismanaged this entire thing. I'm sure you acted in good faith in wanting to embrace the “Her” meme. It is a good idea. And ‘Sky' was a good effort.It seems clear you had spoken to Scarlett Johansson and failed to reach an agreement. I'm prepared to believe you could not react fast enough to change the voice prior to the demo.But once it went awry, you needed to do more than wait for a legal challenge before pulling it, and you needed to say something before the actress. Not doing so means that many people, probably most, think you did the entire thing on purpose.Clearly, you did not preconceive this. If you did, then the fact that you were happy to pull the voice, and your knowledge that the actress was not prepared to have her voice used, would have stopped you before it got as far as it did. You would be very reckless to have thought you could get away with using a voice like hers without her permission.So, you need to either go on the record and get this behind you or ignore it and hope it goes away. I think now we have ‘ScarJo' as a word, the latter might prove difficult.Best Regards,Keith (A fellow Founder)Beyond ScarJo there are some great essays this week. Pack McCormick writes about why AI will lead to more jobs and bigger companies. In framing his case he says”Technologies are tools. I don't mean that in the normal way that people mean it to say that technology is neither good nor bad.Tools are good.Humans can build better things with tools than they can without them.But tools aren't the point. They're tools.Tools lead to new possibilities and those lead to new endeavors. Read his essay below.And a team made up of @KamalVC, @VaradanMonisha, @Claudiazeisberg have penned an essay called ‘The Pervasive, Head-Scratching, Risk-Exploding Problem With Venture Capital'. The main thesis is about investing in private companies versus public companies. They have a great graphic showing that the range of outcomes in Venture Capital is very wide compared to other asset classes:Venture Capital's top percentiles out-perform other asset classes, but most do not. The safest asset class is global equity (public company stock).Building on this they show that large Venture investors that invest across 500 or more companies can compete with less risky assets by diversification.This depicts a simulation of a manager doing 15 deals, compared to 500 and shows more deals equals less risk.I recommend reading the full piece, linked in the contents above and the headline below. I think they are right, but there is a better way of derisking. The advice they give below is better than traditional venture capital, but that is a low bar:To de-risk venture capital, CIOs simply need to acknowledge that VC math is different from public markets math. The importance of low-probability, excess-return-generating investments means that proper diversification requires a portfolio of at least 500 startups.It will take work to assemble such a portfolio. It is hard to do by investing directly. Current funds and funds-of-funds are rarely designed with diversification in mind. Instead, they concentrate funding in a small subset of ultra-popular entrepreneurs, sectors, and geographies, which risks driving down returns on capital, leaving higher-return strategies underfunded.Investors who allocate and diversify their funds wisely and accept the evidence will not only achieve better and less-volatile returns, but will also ultimately nudge GPs to finally design diversified funds.In my day job - also about de-risking venture - we use AI to reduce risk, removing companies that are highly unlikely to be successful. The remaining companies (about 7% of the full set of venture backed companies) out-perform the market in a narrower band of outcomes:Here is how the SignalRank Index compares to the S&P500 and the NASDAQ. We assume an investor puts $1 into the S&P, the NASDAQ and The SignalRank Index in each year from 2014-2019 and then show the returns from each (average and median in the case of SignalRank).The median outcome from venture investments is that the investor loses money. The average is a lot better. But almost no managers achieve the average. By using AI to reduce risk we get the average outcome in 2014 to be 4.31x the investment (the white numbers), compared to the S&P500 1.39 and the NASDAQ 1.89. SignalRanks Median outcome is 2.24.De-risking venture capital is important and the writers of the essay show that it is possible to de-risk by diversification. But we can do even better by both diversifying and using data intelligence to remove downside outliers.I will leave you with that thought. More next 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

Congratulations to this week's chosen creators: @sama, @openai, @om, @krishnanrohit, @peternixey, @eringriffith, @AndreRetterath, @ry_paddy, @cutler_max, @Kantrowitz, @PranavDixit, @ttunguz, @geneteare, @sarahfielding_, @carlfranzenContents* Editorial: Eyes, Ears, Hands, and Mouth* Essays of the Week* GPT-4o* How OpenAI Stole Google's Thunder* AI embraces its product arc* OpenAI's Spring release will end up being far more significant than most of us might suspect* Tensions Rise in Silicon Valley Over Sales of Start-Up Stocks* Most Used Startup Databases & How to Find the Best Provider* Video of the Week* Math Problems with ChatGPT 4o* AI of the Week* Her* OpenAI Wants To Get Big Fast, And Four More Takeaways From a Wild Week in AI News* Google Search will now show AI-generated answers to millions by default* AI Spending Patterns : It's Not What You Think* News Of the Week* AI, Web3 And E-Commerce Led For New Unicorns In April 2024* Biden administration quadruples import tariff for Chinese EVs* Startup of the Week* ChatGPT now lets you import files directly from Google Drive, Microsoft OneDrive* X of the Week* Sam Altman on Ilya leaving OpenAIEditorialOpenAi and Google announced their AI offerings' next iteration this week. As @Om Malik explains in one of this week's Essays of the Week, OpenAi won in this high-stakes battle.Make no mistake — the reason OpenAI is achieving all this success (and hype) is because they have a product that for now is stellar. Nonetheless, OpenAI has created excitement that reminds me of the emergence of Palm, and later social networks. They stoked the imagination, and possibilities. Of course!Om is right. Sam Altman did his own post later in the day of the announcements:First, a key part of our mission is to put very capable AI tools in the hands of people for free (or at a great price). I am very proud that we've made the best model in the world available for free in ChatGPT, without ads or anything like that. Free to consumers, or 8 billion earthlings, is possible due to the revenues OpenAI can make from business users. It represents a very big step forward. The company also released a desktop app, initially on the Mac, that can interact with other apps.But for me, the best way to think about what was delivered, aside from free, is summed up in this week's title—Eyes, Ears, Hands, and Mouth. OpenAI has enabled every smartphone camera on the planet to become the AI's eyes and ears. Both still images and video can be used as inputs to a conversation. Of course, the microphone, too. This week's video of the week shows this for teaching a student how to solve a math problem. The mouth reference acknowledges that we can now speak to ChatGPT in a human-like way, including cross-talking and interruptions. And, of course, we can still type using our hands.This changes the problem of giving AI data—images, video, sound, and speech can all become data for input and learning.They also gave chatGPT a memory. It can remember things across sessions. The scope of what will now be possible is expanded to a much longer list.Rohit Krishnan writes about what comes next in his essay:The true change will come once we can enable large numbers of them to work together. And we're getting glimpses of how they can do this across all modalities that are important to use. Whether that's writing code or seeing something or listening to something or writing or reading something or a mixture of all of these.He is talking about AI to AI interactions that can produce even better and faster outcomes. I did this myself earlier in the week. I was asking ChatGPT to create a chart showing the performance of the SignalRank Index against the S&P 500 and the NASDAQ over the 2014-1019 period.ChatGPT did not have the NASDAQ data, so I asked Claude.ai for it. Once I had it I went back to ChatGPT and it completed the work. Here's the chart:It seems clear that almost any problem that can be described, shown, listened to can now be given to ChatGPT and answered.Eyes, Ears, Hands, and mouths are all part of our intelligent robotic future, too. The building blocks for rapid productivity advancement are being put into place.Marc Andreessen and Ben Horowitz discuss the implications for manufacturing in their podcast this week.This was a very important 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