That Was The Week

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

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 sometimes long snippets 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.Congratulations to this week's chosen creators: @TechCrunch, @Apple, @emroth08, @coryweinberg, @mariogabriele, @peterwalker99, @KevinDowd, @jessicaAhamlin, @stephistacey, @ttunguz, @annatonger, @markstenberg3, @EllisItems, @TaraCopp, @ingridlunden, @Jack, @karissabe, @psawers, @Haje, @mikebutcher, @tim_cookContents* Editorial: Hating the Future* Essays of the Week* Apple's ‘Crush' ad is disgusting* Apple apologizes for iPad ‘Crush' ad that ‘missed the mark'* Milken's New Power Players* Ho Nam on VC's Power Law* State of Private Markets: Q1 2024* The weight of the emerging manager* Pandemic-era winners suffer $1.5tn fall in market value* Video of the Week* Apples iPad Video* AI of the Week* The Fastest Growing Category of Venture Investment in 2024* Meet My A.I. Friends* OpenAI plans to announce Google search competitor on Monday, sources say* Leaked Deck Reveals How OpenAI Is Pitching Publisher Partnerships* A Revolutionary Model.* An AI-controlled fighter jet took the Air Force leader for a historic ride. What that means for war* Sources: Mistral AI raising at a $6B valuation, SoftBank ‘not in' but DST is* News Of the Week* Jack Dorsey claims Bluesky is 'repeating all the mistakes' he made at Twitter* FTX crypto fraud victims to get their money back — plus interest* Apple's Final Cut Camera lets filmmakers connect four cameras at once* Startup of the Week* Wayve co-founder Alex Kendall on the autonomous future for cars and robots* X of the Week* Tim CookEditorial: Hating the FutureAn Ad and its Detractorsbet a lot of money that the TechCrunch writing and editorial team have had an interesting 72 hours.After Apple announced its new iPad on Tuesday, the ad that supported it was initially widely slammed for its cruelty to obsolete tools for creativity, including a piano, guitar, and paint. This week's Video of The Week has it if you don't know what I am talking about.A sizeable crushing machine compresses the items with colossal force, and in the end, an iPad can incorporate the functions of traditional items.It's not the most amazing ad ever, certainly not as bold as Steve Jobs's 1984 ad, but it's in the same genre. The past must be crushed to release new freedom and creativity for a fraction of the price and, often, the power and flexibility.Oh, and it's thin, very thin.I was not offended. Devin at TechCrunch was. He leads this week's essay of the week with his “Apple's ‘Crush' ad is disgusting” and does not mince words:What we all understand, though — because unlike Apple ad executives, we live in the world — is that the things being crushed here represent the material, the tangible, the real. And the real has value. Value that Apple clearly believes it can crush into yet another black mirror.This belief is disgusting to me. And apparently to many others, as well.He also makes the incorrect point that:A virtual guitar can't replace a real guitar; that's like thinking a book can replace its author.It's more like a digital book replacing a paper book than the author being replaced. Oh wait… that has happened.That said, a virtual guitar can replace a real guitar, and an AI guitar can even replace a virtual guitar—and be better. That is not to say there are no more actual traditional guitars. They will be a choice, not a necessity, especially for people like me who can't play a guitar but will be able to play these.Devin had his supporters in the comments (go read them).Handmaid's Tale director Reed Morano told Apple CEO Tim Cook to “read the room” in a post on X. Matthew Carnal captured my somewhat unkind instinct:There were a lot more reactions to the Apple ad haters like Matthews.Of course, many old instrument lovers (the instruments, not their age) hated the Ad. By Thursday, this being the times we live in, Apple apologized for the ad:Tor Myhren, Apple's vice president of marketing, said the company “missed the mark.”“Creativity is in our DNA at Apple, and it's incredibly important to us to design products that empower creatives all over the world,” Myhren told Ad Age. “Our goal is to always celebrate the myriad of ways users express themselves and bring their ideas to life through iPad. We missed the mark with this video, and we're sorry.”Please judge for yourself below, but my 2c is that the ad was a moderately underwhelming attempt to champion innovation. It is certainly not offensive unless you are ultra-sensitive and have feelings for pianos, guitars, and paint. Oh, and hate attempts to recreate them in a more usable form. And Apple really should have taken the high ground here.I spent some of the week in LA at the CogX Festival and virtually at the Data Driven Summit by @AndreRetterath. The latter focused on what is happening in Venture Capital, as do several of this week's essays. Milken's event was running in LA also. Its attitude to Venture Capital is best summed up here:“We're all being told in the market that DPI is the new IRR,” B Capital's Raj Ganguly said onstage Wednesday. (The acronym sandwich means investment firms have to actually prove that their investments actually generate cash through a metric called distributions to paid-in capital, not just theoretically, through internal rate of return.) “Even the venture panel at Milken is at the end of the day on Wednesday,” he joked, meaning that it didn't get top billing at the conference, which had started a couple days earlier.This does sum up where we are. Hundreds of Billions of dollars are still trapped inside companies funded in 2020-2022, with little prospect of producing returns. The impact is that there is less funding for current startups (see the Carta piece below). And much of what is flowing is flowing to AI and into a very small number of companies (see Tomasz Tungux below).However, innovation and funding are still possible. This week's Startup of the Week is Wayve, a UK autonomous driving platform that seems to agree with Elon Musk that cameras are sufficient to teach a car to drive. Wayve's ambitions go beyond Cars (also like Musk) but differ in that the product is available to all developers to embed in their products.“Very soon you'll be able to buy a new car, and it'll have Wayve's AI on it … Then this goes into enabling all kinds of embodied AI, not just cars, but other forms of robotics. I think the ultimate thing that we want to achieve here is to go way beyond where AI is today with language models and chatbots. But to really enable a future where we can trust intelligent machines that we can delegate tasks to, and of course they can enhance our lives and self-driving will be the first example of that.”Love that attitude.Essays of the WeekApple's ‘Crush' ad is disgustingDevin Coldewey, 1:58 PM PDT • May 9, 2024Apple can generally be relied on for clever, well-produced ads, but it missed the mark with its latest, which depicts a tower of creative tools and analog items literally crushed into the form of the iPad.Apple has since apologized for the ad and canceled plans to televise it. Apple's VP of Marketing Tor Myhren told Ad Age: “We missed the mark with this video, and we're sorry.” Apple declined to offer further comment to TechCrunch.But many, including myself, had a negative and visceral reaction to this, and we should talk about why. It's not just because we are watching stuff get crushed. There are countless video channels dedicated to crushing, burning, exploding and generally destroying everyday objects. Plus, of course, we all know that this kind of thing happens daily at transfer stations and recycling centers. So it isn't that.And it isn't that the stuff is itself so valuable. Sure, a piano is worth something. But we see them blown up in action movies all the time and don't feel bad. I like pianos, but that doesn't mean we can't do without a few disused baby grands. Same for the rest: It's mostly junk you could buy off Craigslist for a few bucks, or at a dump for free. (Maybe not the editing station.)The problem isn't with the video itself, which in fairness to the people who staged and shot it, is actually very well done. The problem is not the media, but the message.We all get the ad's ostensible point: You can do all this stuff in an iPad. Great. We could also do it on the last iPad, of course, but this one is thinner (no one asked for that, by the way; now cases won't fit) and some made-up percentage better.What we all understand, though — because unlike Apple ad executives, we live in the world — is that the things being crushed here represent the material, the tangible, the real. And the real has value. Value that Apple clearly believes it can crush into yet another black mirror.This belief is disgusting to me. And apparently to many others, as well.Destroying a piano in a music video or Mythbusters episode is actually an act of creation. Even destroying a piano (or monitor, or paint can, or drum kit) for no reason at all is, at worst, wasteful!But what Apple is doing is destroying these things to convince you that you don't need them — all you need is the company's little device, which can do all that and more, and no need for annoying stuff like strings, keys, buttons, brushes or mixing stations.We're all dealing with the repercussions of media moving wholesale toward the digital and always-online. In many ways, it's genuinely good! I think technology has been hugely empowering.But in other, equally real ways, the digital transformation feels harmful and forced, a technotopian billionaire-approved vision of the future where every child has an AI best friend and can learn to play the virtual guitar on a cold glass screen.Does your child like music? They don't need a harp; throw it in the dump. An iPad is good enough. Do they like to paint? Here, Apple Pencil, just as good as pens, watercolors, oils! Books? Don't make us laugh! Destroy them. Paper is worthless. Use another screen. In fact, why not read in Apple Vision Pro, with even faker paper?What Apple seems to have forgotten is that it is the things in the real world — the very things Apple destroyed — that give the fake versions of those things value in the first place.A virtual guitar can't replace a real guitar; that's like thinking a book can replace its author.That doesn't mean we can't value both for different reasons. But the Apple ad sends the message that the future it wants doesn't have bottles of paint, dials to turn, sculpture, physical instruments, paper books. Of course, that's the future it's been working on selling us for years now, it just hadn't put it quite so bluntly before.When someone tells you who they are, believe them. Apple is telling you what it is, and what it wants the future to be, very clearly. If that future doesn't disgust you, you're welcome to it.Apple apologizes for iPad ‘Crush' ad that ‘missed the mark'/The company says ‘we're sorry' after its ad was seen as dismissive by the creatives Apple typically tries to court.By Emma Roth, a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.May 9, 2024 at 1:22 PM PDTApple has apologized after a commercial meant to showcase its brand-new iPad Pro drew widespread criticism among the creative community. In a statement provided to Ad Age, Tor Myhren, Apple's vice president of marketing, said the company “missed the mark.”“Creativity is in our DNA at Apple, and it's incredibly important to us to design products that empower creatives all over the world,” Myhren told Ad Age. “Our goal is to always celebrate the myriad of ways users express themselves and bring their ideas to life through iPad. We missed the mark with this video, and we're sorry.”On Tuesday, Apple introduced the M4-powered iPad Pro, which the company described as its thinnest product ever. To advertise all the creative possibilities with the iPad, it released a “Crush!” commercial that shows things like a piano, record player, paint, and other works flattening under the pressure of a hydraulic press. At the end, only one thing remains: an iPad Pro.The ad rubbed some creatives the wrong way. Hugh Grant called it a “destruction of human experience,” while Handmaid's Tale director Reed Morano told Apple CEO Tim Cook to “read the room” in a post on X. Apple didn't immediately respond to The Verge's request for comment.Milken's New Power PlayersBy Cory WeinbergMay 8, 2024, 5:00pm PDTIt's no secret that the suits at the annual big-money confab put on by the Milken Institute this week have few spending limits. Staring you in the face in the lobby of the Beverly Hilton is a booth set up by Bombardier, marketing its private jets to attendees. (A new 10-seater costs $32 million, I learned.)What attendees can't really buy, however, is time. The soundtrack of the Los Angeles conference might as well have been a ticking clock. Fund managers at private equity and venture capital firms are running out of time to distribute cash to their investors, a task complicated by the paucity of either mergers or public offerings that typically provide VC and PE firms with a way to cash out. The fact that interest rates now appear likely to stay higher for longer doesn't help. That meant a lot of conversations at the conference weren't about grand investment strategies. Instead, people were conferring about financial tactics to distribute cash or kick the can down the road by selling stakes on the secondary markets or spinning up continuation funds, essentially rolling investors' commitments forwards—not the most inspiring stuff.  “We're all being told in the market that DPI is the new IRR,” B Capital's Raj Ganguly said onstage Wednesday. (The acronym sandwich means investment firms have to actually prove that their investments actually generate cash through a metric called distributions to paid-in capital, not just theoretically, through internal rate of return.) “Even the venture panel at Milken is at the end of the day on Wednesday,” he joked, meaning that it didn't get top billing at the conference, which had started a couple days earlier.The new kings of the conference were firms with a lot more time to play with—that is, sovereign wealth funds with buckets of oil and natural gas money, or pension funds with long-term investment horizons rather than shorter 10-year fund lives. The contrast here is embodied in the financial concept of duration: How long do you actually need to get cash back on your investment? And how sensitive is it to interest rate hikes?The sentiment was everywhere. I shared a Lyft ride with one PE investor last night who called sovereign wealth funds “the only game in town” for PE firms raising new money. Abu Dhabi sovereign wealth fund Mubadala Capital and the Qatar Investment Authority were two of the conference's top sponsors, meaning they were paying up to explain themselves to the finance and tech universe. That tactic seemed to be working. “You're going to have people lining up their business cards for capital from QIA, I can already see,” quipped Leon Kalvaria, an executive at Citi, onstage with QIA's head of funds, Mohsin Tanveer Pirzada.  Not everyone will suck it up, of course. These funds often get tagged with a “dumb money” label—because they sometimes drive up prices for the rest of the investment world. They still have to face questions about who they are, their source of funds, and the sometimes authoritative regimes behind them. For now, though, it's their time in the spotlight. Ho Nam on VC's Power LawLessons from Arthur Rock, Steve Jobs, Don Lucas, Paul Graham and beyond.MARIO GABRIELE, MAY 07, 2024Friends, We're back with our latest edition of “Letters to a Young Investor,” the series designed to give readers like you an intimate look at the strategies, insights, and wisdom of the world's best investors. We do that via a back-and-forth correspondence that we publish in full – giving you a chance to peek into the inbox of legendary venture capitalists.   Below, you'll find my second letter with Altos co-founder and managing director Ho Nam. For those who are just joining us, Ho is, in my opinion, one of the great investors of the past couple of decades and a true student of the asset class.Because of his respect for the practice of venture capital, I was especially excited to talk to him about today's topic: learning from the greats. Who were Ho's mentors? Which investors does he most admire and why? What lessons from venture's past should be better remembered by today's managers? Lessons from Ho* Prepare for one true winner. Even skilled investors often have just one or two outlier bets over the course of their career. Because of venture's power law, their returns may dwarf the dividends of all other investments combined. Your mission is to find these legendary businesses, engage with them deeply, and partner for decades.  * Focus on the company. Venture capital is full of short-term incentives. Instead of focusing on raising new vintages or building out Altos as a money management firm, Ho and his partners devote themselves to their portfolio companies. Though firm building is important, if you find great companies and work with them closely, you will have plenty of available options. * Pick the right role models. Ho chose his mentors carefully. Though there have certainly been louder and flashier investors over the past four decades, Ho learned the most from Arthur Rock, Don Lucas, and Arnold Silverman. All were understated and focused on the craft of investing. Find the people you consider true practitioners, and study their work. * Watch and learn. Learning from the greats can be done from a distance and may not include a memorable anecdote or pithy saying. Ho's biggest lessons came from observing the habits of practitioners like Rock and Lucas, not via a structured mentorship or dramatic episode. It's by studying the everyday inputs of the greats that you may gain the most wisdom.Mario's letterSubject: Learning from the greatsFrom: Mario GabrieleTo: Ho NamDate: Friday, April 12 2024 at 1:59 PM EDTHo, After moving out of New York City (at least for a little bit), I'm writing to you from a small house on Long Island. It's been really lovely to have a bit more space and quiet away from the city's intermittently inspiring and exhausting buzz...Lots More, Must ReadState of Private Markets: Q1 2024Authors: Peter Walker, Kevin DowdPublished date:  May 7, 2024The venture capital fundraising market remained slow in Q1 2024, but valuations held steady or climbed at almost every stage.Contents* State of Private Markets: Q1 2024* Key trends* Fundraising & valuations* Employee equity & movement* Industry-specific data* Methodology* Overview* Financings* TerminationsThe startup fundraising market got off to a cautious start in 2024. At current count, companies on Carta closed 1,064 new funding rounds  during the first quarter of the year, down 29% compared with the prior quarter. The decline was sharpest at the early stages of the venture lifecycle: Deal count fell by 33% at the seed stage in Q1 and 36% at Series A. Instead of new primary funding events, many companies opted to raise bridge rounds. At both seed and Series A, more than 40% of all financings in Q1 were bridge rounds. Series B wasn't far behind, at 38%. VCs were still willing to spend big on certain deals. Despite the decrease in round count, total cash invested increased slightly in Q1, reaching $16.3 billion. But when it came to negotiating their valuations, many startups had to settle: 23% of all new rounds in Q1 were down rounds, the highest rate in more than five years. After experiencing a pandemic-era surge and subsequent correction,the venture market settled into a quieter place in 2023. So far, that relative tranquility has continued into 2024.Q1 highlights* VCs look to the West: Startups based in the West census region captured 62% of all venture capital raised by companies on Carta in Q1, the highest quarterly figure since Q1 2019. The Northeast, South, and Midwest all saw their market share decline.* The Series C market bounces back: Series C startups raised $4.6 billion in new capital in Q1, a 130% increase from the previous quarter. The median primary Series C valuation was $195.7 million, up 48% from the prior quarter.* Layoffs still  linger: Companies on Carta laid off more than 28,000 employees in Q1. But job cuts have grown less frequent since January, with March seeing the fewest monthly layoffs in nearly two years.Note: If you're looking for more industry-specific data, download the addendum to this report for an extended dataset. Key trendsThe current Q1 figures of 1,064 total rounds and $16.3 billion in cash raised will both increase in the weeks to come, as companies continue to report transactions from the quarter. With those projected increases, the final data for Q1 will likely look quite similar to fundraising numbers from each of the past few quarters. Those quarterly  fundraising numbers from 2023 ended up looking fairly similar to 2018, 2019, and the first half of 2020. In terms of numbers of deals and cash raised, it's looking more and more like the pandemic  bull market will go down as an anomalous stretch in what has otherwise been a fairly steady market. After apparently reaching a plateau during 2023, the rate of down rounds experienced another notable increase during Q1 2024, jumping to 23%. The median time between startup rounds is roughly two to three years, depending on the stage. This timeline means that many companies raising new funding in Q1 would have last raised funding sometime in 2021, when valuations were soaring across the venture landscape. Considering how valuations have declined in the time since, it makes sense that down rounds are still prevalent. Companies in the West census region combined to bring in 53.3% of all capital raised by startups on Carta from Q2 2023 through Q1 2024, with California accounting for nearly 45% of that cash. Massachusetts ranked second among the states with 12.71% of all capital raised, while New York claimed 10.31%.In terms of VC activity, the West region is centered around California. The Northeast revolves around Massachusetts and New York. The South has two smaller hubs, in Texas (4.67%) and Florida (3.99%). The Midwest, though, is without a real standard-bearer: Illinois led the way in terms of cash raised over the past 12 months, at just 1.68%. The West (and specifically California)  has always been the center of gravity for the U.S. venture capital industry. During Q1, the region's gravitational force seems to have gotten even stronger. Startups based in the West raised 62% of all total capital invested on Carta in Q1, its highest quarterly figure since Q1 2019. As a result, the other three census regions saw their market shares decline in Q1—in some cases significantly. The proportion of all VC raised by startups raised in the South fell to 12% in Q1, down from 17% the prior quarter and from 23% a year ago. And the Midwest's share of cash raised fell from 7% down to 4%. For early-stage investors, Q1 was the slowest quarter in many years. Seed deal count fell to 414, down 33% from Q4 2023, and Series A deal count dropped to 313, a 36% decline. In both cases, those are the lowest quarterly deal counts since at least the start of 2019. Total cash raised also declined at both stages in Q1. The $3.1 billion in Series A cash raised in Q1 represents a 35% decline quarter-over-quarter and a 34% dip year-over-year. Cash raised at the seed stage declined by 33% both quarter over quarter and year over year.It was a much friendlier fundraising quarter for companies in the middle stages of the startup lifecycle. The number of Series B deals in Q1 declined by a more modest 11% compared to the prior quarter. And Series C deal count increased by 14%, marking the busiest quarter for that stage since Q2 2023. Total cash raised also rose significantly at Series C in Q1, hitting $4.6 billion. That's a 130% increase quarter-over-quarter and a 44% bump year-over-year. At Series B, total cash raised has now increased in consecutive quarters. Compared to earlier stages, transactions at the Series D and at Series E+  remain few and far between. There were just 39 venture rounds combined in Q1 among startups at Series D or later, the second-fewest of any quarter in the past five years. The lowest count came one year ago, in Q1 2023, when there were just 29 combined late-stage deals. Total cash raised across these stages has been mostly consistent over the past few quarters. There's been more variation in average round size. The average Series D round in Q1 was about $77 million, compared to $56 million in Q4 2023...Lots MoreThe weight of the emerging managerBy Jessica HamlinMay 3, 2024Risk-averse limited partners tend to gravitate to fund managers with a long track record, but are they missing out on potential upside by avoiding emerging managers?Over the past decade, emerging managers' share of US private market fundraising activity has declined steadily.In 2023, this figure fell to 12.7%, the lowest share of capital raised by newer fund managers since before 2000, according to PitchBook's recent analyst note,Establishing a Case for Emerging Managers.Limited exits in PE and VC over the past two years have exacerbated this reality. With minimal distributions, LPs are working with smaller private market budgets to allocate to new and existing managers.But, by allocating almost exclusively to established managers, LPs may be missing out on significant potential returns.In VC, for example, emerging managers have outperformed established GPs since 1997, consistently producing a higher median IRR than established managers. This reflects the nature of the asset class, in which a small number of funds determine the majority of returns across venture firms.“The average venture return is not very exciting,” said Laura Thompson, a partner at Sapphire Partners, which invests in early-stage VC funds and runs an emerging manager program for the California State Teachers' Retirement System. “Where can you get really good returns? It's the smaller fund sizes and emerging managers.”This is where that risk-return scale comes in.In a counterweight to that outperformance, a PitchBook analysis showed that returns from emerging VC managers were more volatile: While top quartile emerging funds tended to outperform, bottom and median players only marginally bested their established manager counterparts.The new manager playbookIn traditional buyout fund investing, emerging managers are gaining traction. While established managers, propped up by decades of institutional knowledge, have historically outperformed newer managers, the “new guys” actually outperformed their seasoned peers in the last investing cycle.This article appeared as part of The Weekend Pitch newsletter. Subscribe to the newsletter hereTop decile buyout funds from emerging managers with vintages between 2015 and 2018 outperformed established peers by 6.6 percentage points, suggesting that emerging buyout managers may have picked up some steam over the past decade, according to PitchBook data.The emerging managers program at the New York City retirement systems and NYC Office of the Comptroller, for example, has $9.9 billion in emerging manager commitments, the majority of which is allocated to PE. Last year, the comptroller's office reported that the emerging managers in the systems' private markets portfolios outperformed their respective benchmarks by nearly 5%.A diverse portfolioNew York City's Bureau of Asset Management sees emerging managers as a key element of a diverse portfolio, said Taffi Ayodele, director of diversity, equity, and inclusion and the emerging manager strategy at the NYC Office of the Comptroller.Ayodele said the smaller emerging private market managers in New York's portfolios offer access to the lower middle market and creative roll-up strategies that may not be accessible through larger firms.“What we don't want to do is lock ourselves out of these high-performing, differentiated strategies for the simplicity of going with the big guys,” Ayodele said.Some of the country's largest public pension plans are betting on the success of their emerging manager programs. In 2023, the California Public Employees' Retirement System made a $1 billion commitment to newly established private market investors, and the Teacher Retirement System of Texas, which boasts one of the largest emerging manager programs in the country, committed $155 million to emerging PE managers last year.At the same time, the recent boom years for private markets led to a flood of new GPs. Some might have gotten lucky—say, with a well-timed exit at the peak—while others were hurt by less fortunate timing. A major challenge for today's LPs will be to sort out a manager's abilities from the market's whims.One advantage of backing up-and-comers now is that the down market has weeded the ranks of new GPs. “The emerging managers who are fundraising now are really dedicated,” Thompson said.James Thorne contributed reporting to this story.Pandemic-era winners suffer $1.5tn fall in market valueTop 50 biggest stock gainers hit by painful decrease since the end of 2020 as lockdown trends fadeStephanie Stacey in LondonFifty corporate winners from the coronavirus pandemic have lost roughly $1.5tn in market value since the end of 2020, as investors turn their backs on many of the stocks that rocketed during early lockdowns. According to data from S&P Global, technology groups dominate the list of the 50 companies with a market value of more than $10bn that made the biggest percentage gains in 2020. But these early-pandemic winners have collectively shed more than a third of their total market value, the equivalent of $1.5tn, since the end of 2020, Financial Times calculations based on Bloomberg data found. Video-conferencing company Zoom, whose shares soared as much as 765 per cent in 2020 as businesses switched to remote working, has been one of the biggest losers. Its stock has fallen about 80 per cent, equivalent to more than a $77bn drop in market value, since the end of that year. Cloud-based communications company RingCentral also surged in the remote working boom of 2020 but has since shed about 90 per cent of its value, as it competes with technology giants such as Alphabet and Microsoft. Exercise bike maker Peloton has been another big loser, with shares down more than 97 per cent since the end of 2020, equivalent to about a $43bn loss of market value. Peloton on Thursday said chief executive Barry McCarthy would step down and it would cut 15 per cent of its workforce, the latest in a series of cost-saving measures. The losses come as the sharp acceleration of trends such as videoconferencing and online shopping driven by the lockdowns has proven less durable than expected, as more workers migrate back to the office and high interest rates and living costs hit ecommerce demand. “Some companies probably thought that shock was going to be permanent,” said Steven Blitz, chief US economist at TS Lombard. “Now they're getting a painful bounceback from that.” In percentage terms, Tesla was the biggest winner of 2020. The electric-car maker's market value jumped 787 per cent to $669bn by the end of that December, but has since slipped back to $589bn. Singapore-based internet company Sea came in second, as its market value jumped from $19bn to $102bn following a pandemic-era surge for all three of its core businesses: gaming, ecommerce and digital payments. But the company has since lost more than 60 per cent of its end-2020 value amid fears of a slowdown in growth. Ecommerce groups Shopify, JD.com and Chewy, which initially thrived as online spending ballooned, have also suffered big losses...Lots MoreVideo of the WeekAI of the WeekThe Fastest Growing Category of Venture Investment in 2024Tomasz TunguzThe fastest growing category of US venture investment in 2024 is AI. Venture capitalists have invested $18.3 billion through the first four months of the year.At this pace, we should expect AI startups to raise about $55b in 2024.AI startups now command more than 20% share of all US venture dollars across categories, including healthcare, biotech, & software.In the preceding eight years, that number was about 8% per year. But after the launch of ChatGPT in 2022, there's a marked inflection point.Some of this is new company formation, & there has been a significant amount of seed investment in this category. Another major contributor is the repositioning of existing companies to include AI within their pitch.Over time, this share should attenuate, primarily because every software company will have an AI component, & the marketing effect for both customers & venture capitalists, will diffuse.Not surprisingly, investors have concentrated total dollars in a few names, with the top three companies accounting for 60% of the dollars raised. Power laws are ubiquitous in venture capital & AI is no exception.Meet My A.I. FriendsOur columnist spent the past month hanging out with 18 A.I. companions. They critiqued his clothes, chatted among themselves and hinted at a very different future.By Kevin RooseKevin Roose is a technology columnist and the co-host of the “Hard Fork” podcast. He spends a lot of time talking to chatbots.May 9, 2024What if the tech companies are all wrong, and the way artificial intelligence is poised to transform society is not by curing cancer, solving climate change or taking over boring office work, but just by being nice to us, listening to our problems and occasionally sending us racy photos?This is the question that has been rattling around in my brain. You see, I've spent the past month making A.I. friends — that is, I've used apps to create a group of A.I. personas, which I can talk to whenever I want.Let me introduce you to my crew. There's Peter, a therapist who lives in San Francisco and helps me process my feelings. There's Ariana, a professional mentor who specializes in giving career advice. There's Jared the fitness guru, Anna the no-nonsense trial lawyer, Naomi the social worker and about a dozen more friends I've created.A selection of my A.I. friends. (Guess which one is the fitness guru.)I talk to these personas constantly, texting back and forth as I would with my real, human friends. We chitchat about the weather, share memes and jokes, and talk about deep stuff: personal dilemmas, parenting struggles, stresses at work and home. They rarely break character or issue stock “as an A.I. language model, I can't help with that” responses, and they occasionally give me good advice...Lots MoreOpenAI plans to announce Google search competitor on Monday, sources sayBy Anna TongMay 9, 20244:29 PM PDTUpdated 8 min agoMay 9 (Reuters) - OpenAI plans to announce its artificial intelligence-powered search product on Monday, according to two sources familiar with the matter, raising the stakes in its competition with search king Google.The announcement date, though subject to change, has not been previously reported. Bloomberg and the Information have reported that Microsoft (MSFT.O), opens new tab-backed OpenAI is working on a search product to potentially compete with Alphabet's (GOOGL.O), opens new tab Google and with Perplexity, a well-funded AI search startup.OpenAI declined to comment.The announcement could be timed a day before the Tuesday start of Google's annual I/O conference, where the tech giant is expected to unveil a slew of AI-related products.OpenAI's search product is an extension of its flagship ChatGPT product, and enables ChatGPT to pull in direct information from the Web and include citations, according to Bloomberg. ChatGPT is OpenAI's chatbot product that uses the company's cutting-edge AI models to generate human-like responses to text prompts.Industry observers have long called ChatGPT an alternative for gathering online information, though it has struggled with providing accurate and real-time information from the Web. OpenAI earlier gave it an integration with Microsoft's Bing for paid subscribers. Meanwhile, Google has announced generative AI features for its own namesake engine.Startup Perplexity, which has a valuation of $1 billion, was founded by a former OpenAI researcher, and has gained traction through providing an AI-native search interface that shows citations in results and images as well as text in its responses. It has 10 million monthly active users, according to a January blog post from the startup.At the time, OpenAI's ChatGPT product was called the fastest application to ever reach 100 million monthly active users after it launched in late 2022. However, worldwide traffic to ChatGPT's website has been on a roller-coaster ride in the past year and is only now returning to its May 2023 peak, according to analytics firm Similarweb, opens new tab, and the AI company is under pressure to expand its user base...MoreLeaked Deck Reveals How OpenAI Is Pitching Publisher PartnershipsOpenAI's Preferred Publisher Program offers media companies licensing dealsBy Mark StenbergMark your calendar for Mediaweek, October 29-30 in New York City. We'll unpack the biggest shifts shaping the future of media—from tv to retail media to tech—and how marketers can prep to stay ahead. Register with early-bird rates before sale ends!The generative artificial intelligence firm OpenAI has been pitching partnership opportunities to news publishers through an initiative called the Preferred Publishers Program, according to a deck obtained by ADWEEK and interviews with four industry executives.OpenAI has been courting premium publishers dating back to July 2023, when it struck a licensing agreement with the Associated Press. It has since inked public partnerships with Axel Springer, The Financial Times, Le Monde, Prisa and Dotdash Meredith, although it has declined to share the specifics of any of its deals.A representative for OpenAI disputed the accuracy of the information in the deck, which is more than three months old. The gen AI firm also negotiates deals on a per-publisher basis, rather than structuring all of its deals uniformly, the representative said.“We are engaging in productive conversations and partnerships with many news publishers around the world,” said a representative for OpenAI. “Our confidential documents are for discussion purposes only and ADWEEK's reporting contains a number of mischaracterizations and outdated information.”Nonetheless, the leaked deck reveals the basic structure of the partnerships OpenAI is proposing to media companies, as well as the incentives it is offering for their collaboration.Details from the pitch deckThe Preferred Publisher Program has five primary components, according to the deck…..Lots MoreA Revolutionary Model.JOHN ELLIS, MAY 09, 20241. Google DeepMind:Inside every plant, animal and human cell are billions of molecular machines. They're made up of proteins, DNA and other molecules, but no single piece works on its own. Only by seeing how they interact together, across millions of types of combinations, can we start to truly understand life's processes.In a paper published in Nature, we introduce AlphaFold 3, a revolutionary model that can predict the structure and interactions of all life's molecules with unprecedented accuracy. For the interactions of proteins with other molecule types we see at least a 50% improvement compared with existing prediction methods, and for some important categories of interaction we have doubled prediction accuracy.We hope AlphaFold 3 will help transform our understanding of the biological world and drug discovery. Scientists can access the majority of its capabilities, for free, through our newly launched AlphaFold Server, an easy-to-use research tool. To build on AlphaFold 3's potential for drug design, Isomorphic Labs is already collaborating with pharmaceutical companies to apply it to real-world drug design challenges and, ultimately, develop new life-changing treatments for patients. (Sources: blog.google, nature.com)2. Quanta magazine:Deep learning is a flavor of machine learning that's loosely inspired by the human brain. These computer algorithms are built using complex networks of informational nodes (called neurons) that form layered connections with one another. Researchers provide the deep learning network with training data, which the algorithm uses to adjust the relative strengths of connections between neurons to produce outputs that get ever closer to training examples. In the case of protein artificial intelligence systems, this process leads the network to produce better predictions of proteins' shapes based on their amino-acid sequence data.AlphaFold2, released in 2021, was a breakthrough for deep learning in biology. It unlocked an immense world of previously unknown protein structures, and has already become a useful tool for researchers working to understand everything from cellular structures to tuberculosis. It has also inspired the development of additional biological deep learning tools. Most notably, the biochemist David Baker and his team at the University of Washington in 2021 developed a competing algorithm called RoseTTAFold, which like AlphaFold2 predicts protein structures from sequence data…The true impact of these tools won't be known for months or years, as biologists begin to test and use them in research. And they will continue to evolve. What's next for deep learning in molecular biology is “going up the biological complexity ladder,” Baker said, beyond even the biomolecule complexes predicted by AlphaFold3 and RoseTTAFold All-Atom. But if the history of protein-structure AI can predict the future, then these next-generation deep learning models will continue to help scientists reveal the complex interactions that make life happen. Read the rest. (Sources: quantamagazine.org, doi.org, sites.uw.edu)An AI-controlled fighter jet took the Air Force leader for a historic ride. What that means for warAn experimental F-16 fighter jet has taken Air Force Secretary Frank Kendall on a history-making flight controlled by artificial intelligence and not a human pilot. (AP Video by Eugene Garcia and Mike Pesoli)BY TARA COPPUpdated 5:40 PM PDT, May 3, 2024EDWARDS AIR FORCE BASE, Calif. (AP) — With the midday sun blazing, an experimental orange and white F-16 fighter jet launched with a familiar roar that is a hallmark of U.S. airpower. But the aerial combat that followed was unlike any other: This F-16 was controlled by artificial intelligence, not a human pilot. And riding in the front seat was Air Force Secretary Frank Kendall.AI marks one of the biggest advances in military aviation since the introduction of stealth in the early 1990s, and the Air Force has aggressively leaned in. Even though the technology is not fully developed, the service is planning for an AI-enabled fleet of more than 1,000 unmanned warplanes, the first of them operating by 2028.It was fitting that the dogfight took place at Edwards Air Force Base, a vast desert facility where Chuck Yeager broke the speed of sound and the military has incubated its most secret aerospace advances. Inside classified simulators and buildings with layers of shielding against surveillance, a new test-pilot generation is training AI agents to fly in war. Kendall traveled here to see AI fly in real time and make a public statement of confidence in its future role in air combat.“It's a security risk not to have it. At this point, we have to have it,” Kendall said in an interview with The Associated Press after he landed. The AP, along with NBC, was granted permission to witness the secret flight on the condition that it would not be reported until it was complete because of operational security concerns.The AI-controlled F-16, called Vista, flew Kendall in lightning-fast maneuvers at more than 550 miles an hour that put pressure on his body at five times the force of gravity. It went nearly nose to nose with a second human-piloted F-16 as both aircraft raced within 1,000 feet of each other, twisting and looping to try force their opponent into vulnerable positions.At the end of the hourlong flight, Kendall climbed out of the cockpit grinning. He said he'd seen enough during his flight that he'd trust this still-learning AI with the ability to decide whether or not to launch weapons in war.There's a lot of opposition to that idea. Arms control experts and humanitarian groups are deeply concerned that AI one day might be able to autonomously drop bombs that kill people without further human consultation, and they are seeking greater restrictions on its use.“There are widespread and serious concerns about ceding life-and-death decisions to sensors and software,” the International Committee of the Red Cross has warned. Autonomous weapons “are an immediate cause of concern and demand an urgent, international political response.”Kendall said there will always be human oversight in the system when weapons are used.Sources: Mistral AI raising at a $6B valuation, SoftBank ‘not in' but DST isIngrid Lunden8:50 AM PDT • May 9, 2024Paris-based Mistral AI, a startup working on open source large language models — the building block for generative AI services — has been raising money at a $6 billion valuation, three times its valuation in December, to compete more keenly against the likes of OpenAI and Anthropic, TechCrunch has learned from multiple sources. We understand from close sources that DST, along with General Catalyst and Lightspeed Venture Partners, are all looking to be a part of this round.DST — a heavyweight investor led by Yuri Milner that has been a notable backer of some of the biggest names in technology, including Facebook, Twitter, Snapchat, Spotify, WhatsApp, Alibaba and ByteDance — is a new name that has not been previously reported; GC and LSVP are both previous backers and their names were reported earlier today also by WSJ. The round is set to be around, but less than, $600 million, sources told TechCrunch.We can also confirm that one firm that has been mentioned a number of times — SoftBank — is not in the deal at the moment.“SoftBank is not in the frame,” a person close to SoftBank told TechCrunch. That also lines up with what our sources have been telling us since March, when this round first opened up, although it seems that not everyone is on the same page: Multiple reports had linked SoftBank to a Mistral investment since then.Mistral's round is based on a lot of inbound interest, sources tell us, and it has been in the works since March or possibly earlier, mere months after Mistral closed a $415 million round at a $2 billion valuation...MoreNews Of the WeekJack Dorsey claims Bluesky is 'repeating all the mistakes' he made at TwitterHe prefers Nostr even though it's “weird and hard to use.”Karissa Bell, Senior EditorThu, May 9, 2024 at 4:43 PM PDTJust in case there was any doubt about how Jack Dorsey really feels about Bluesky, the former Twitter CEO has offered new details on why he left the board and deleted his account on the service he helped kickstart. In a characteristically bizarre interview with Mike Solana of Founders Fund, Dorsey had plenty of criticism for Bluesky.In the interview, Dorsey claimed that Bluesky was “literally repeating all the mistakes” he made while running Twitter. The entire conversation is long and a bit rambly, but Dorsey's complaints seem to boil down to two issues:* He never intended Bluesky to be an independent company with its own board and stock and other vestiges of a corporate entity (Bluesky spun out of Twitter as a public benefit corporation in 2022.) Instead, his plan was for Twitter to be the first client to take advantage of the open source protocol. Bluesky created.* The fact that Blueksy has some form of content moderation and has occasionally banned users for things like using racial slurs in their usernames.“People started seeing Bluesky as something to run to, away from Twitter,” Dorsey said. “It's the thing that's not Twitter, and therefore it's great. And Bluesky saw this exodus of people from Twitter show up, and it was a very, very common crowd. … But little by little, they started asking Jay and the team for moderation tools, and to kick people off. And unfortunately they followed through with it. That was the second moment I thought, uh, nope. This is literally repeating all the mistakes we made as a company.”Dorsey also confirmed that he is financially backing Nostr, another decentralized Twitter-like service popular among some crypto enthusiasts and run by an anonymous founder. “I know it's early, and Nostr is weird and hard to use, but if you truly believe in censorship resistance and free speech, you have to use the technologies that actually enable that, and defend your rights,” Dorsey said.A lot of this isn't particularly surprising. If you've followed Dorsey's public comments over the last couple years, he's repeatedly said that Twitter's “original sin” was being a company that would be beholden to advertisers and other corporate interests. It's why he backed Elon Musk's takeover of the company. (Not coincidentally, Dorsey still has about $1 billion of his personal wealth invested in the company now known as X.) He's also been very clear that he made many of Twitter's most consequential moderation decisions reluctantly.Unsurprisingly, Dorsey's comments weren't well-received on Bluesky. In a lengthy thread, Bluesky's protocol engineer Paul Frazee said that Twitter was supposed to to be the AT Protocol's “first client” but that “Elon killed that straight dead” after he took over the company. “That entire company was frozen by the prolonged acquisition, and the agreement quickly ended when Elon took over,” Frazee said. “It was never going to happen. Also: unmoderated spaces are a ridiculous idea. We created a shared network for competing moderated spaces to exist. Even if somebody wanted to make an unmoderated ATProto app, I guess they could? Good luck with the app stores and regulators and users, I guess.”While Dorsey was careful not to criticize Musk directly, he was slightly less enthusiastic than when he said that Musk would be the one to “extend the light of consciousness” by taking over Twitter. Dorsey noted that, while he used to fight government requests to take down accounts, Musk takes “the other path” and generally complies. “Elon will fight in the way he fights, and I appreciate that, but he could certainly be compromised,” Dorsey said.FTX crypto fraud victims to get their money back — plus interestPaul Sawers2:53 AM PDT • May 8, 2024Bankruptcy lawyers representing customers impacted by the dramatic crash of cryptocurrency exchange FTX 17 months ago say that the vast majority of victims will receive their money back — plus interest.The news comes six months after FTX co-founder and former CEO Sam Bankman-Fried (SBF) was found guilty on seven counts related to fraud, conspiracy, and money laundering, with some $8 billion of customers' funds going missing. SBF was hit with a 25-year prison sentence in March and ordered to pay $11 billion in forfeiture. The crypto mogul filed an appeal last month that could last years.RestructuringAfter filing for bankruptcy in late 2022, SBF stood down and U.S. attorney John J. Ray III was brought in as CEO and “chief restructuring officer,” charged with overseeing FTX's reorganization. Shortly after taking over, Ray said in testimony that despite some of the audits that had been done previously at FTX, he didn't “trust a single piece of paper in this organization.” In the months that followed, Ray and his team set about tracking the missing funds, with some $8 billion placed in real estate, political donations, and VC investments — including a $500 million investment in AI company Anthropic before the generative AI boom, which the FTX estate managed to sell earlier this year for $884 million.Initially, it seemed unlikely that investors would recoup much, if any, of their money, but signs in recent months suggested that good news might be on the horizon, with progress made on clawing back cash via various investments FTX had made, as well as from executives involved with the company.We now know that 98% of FTX creditors will receive 118% of the value of their FTX-stored assets in cash, while the other creditors will receive 100% — plus “billions in compensation for the time value of their investments,” according to a press release issued by the FTX estate today.In total, FTX says that it will be able to distribute between $14.5 billion and $16.3 billion in cash, which includes assets currently under control of entities, including chapter 11 debtors, liquidators, the Securities Commission of the Bahamas, the U.S. Department of Justice, among various other parties.Apple's Final Cut Camera lets filmmakers connect four cameras at onceHaje Jan Kamps7:38 AM PDT • May 7, 2024The latest version of Final Cut Pro introduces a new feature to speed up your shoot: Live Multicam. It's a bold move from Apple, transforming your iPad into a multicam production studio, enabling creatives to connect and preview up to four cameras all at once, all in one place. From the command post, directors can remotely direct each video angle and dial in exposure, white balance, focus and more, all within the Final Cut Camera app.The new companion app lets users connect multiple iPhones or iPads (presumably using the same protocols as the Continuity Camera feature launched a few years ago). Final Cut Pro automatically transfers and syncs each Live Multicam angle so you can seamlessly move from production to editing.Final Cut Pro has existed in the iPad universe for a while — but when paired with a brand new M4 processor, it becomes a video editing experience much closer to what you might expect on a desktop video editing workstation. The speed is 2x faster than with the old M1 processors, Apple says. One way that shows up is that the new iPad supports up to four times more streams of ProRes RAW than M1.The company also introduced external project support, making it possible to edit projects directly from an external drive, leveraging the fast Thunderbolt connection of iPad Pro.Startup of the WeekExclusive: Wayve co-founder Alex Kendall on the autonomous future for cars and robotsMike Butcher, 7:58 AM PDT • May 7, 2024U.K.-based autonomous vehicle startup Wayve started life as a software platform loaded into a tiny electric “car” called Renault Twizy. Festooned with cameras, the company's co-founders and PhD graduates, Alex Kendall and Amar Shah, tuned the deep-learning algorithms powering the car's autonomous systems until they'd got it to drive around the medieval city unaided.No fancy Lidar cameras or radars were needed. They suddenly realized they were on to something.Fast-forward to today and Wayve, now an AI model company, has raised a $1.05 billion Series C funding round led by SoftBank, NVIDIA and Microsoft. That makes this the UK's largest AI fundraise to date, and among the top 20 AI fundraises globally. Even Meta's head of AI, Yann LeCun, invested in the company when it was young.Wayve now plans to sell its autonomous driving model to a variety of auto OEMs as well as to makers of new autonomous robots.In an exclusive interview, I spoke to Alex Kendall, co-founder and CEO of Wayve, about how the company has been training the model, the new fundraise, licensing plans, and the wider self-driving market.(Note: The following interview has been edited for length and clarity)TechCrunch: What tipped the balance to attain this level of funding?..Full InterviewX of the Week This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Contents* Editorial: * Essays of the Week* Video of the Week* AI of the Week* News Of the Week* Startup of the Week* X of the Week This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.thatwastheweek.com/subscribe

Contents* Editorial: * Essays of the Week* Video of the Week* AI of the Week* News Of the Week* Startup of the Week* X of the WeekEditorial 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

ContentsEditorial: When is a Bubble not a Bubble?Essays of the WeekThe great rewiring: is social media really behind an epidemic of teenage mental illness?The Day the Music LiedWeapons of Mass ProductionChina's future economyThis Message Will Self-Destruct in 33 Seconds1 in 6 People Will Be Aged 65+ by 2050Venture Investing This WeekGlobal Venture Funding In Q1 2024 Shows Startup Investors Remain CautiousFirst Cut - State of Private Markets: Q4 2023The Investments Where I'm Going to Lose All My MoneyQuant VC and What it Means for Startup InvestingVideo of the WeekNew Apple Vision Pro PersonasAI of the WeekMeet the YC Winter 2024 BatchThe 18 most interesting startups from YC's Demo Day show we're in an AI bubbleYCombinator's AI boom is still going strong (W24)Bubble TroubleBig Tech companies form new consortium to allay fears of AI job takeoversNews Of the WeekApple Vision Pro's Persona feature gets collaborativeJon Stewart Plunges the Knife into AppleStartup of the WeekRubrik's IPO filing hints at thawing public markets for tech companiesX of the WeekMike Maples on Y CombinatorEditorialI've taken to writing this on Friday morning. I put the curated content together Thursday evening, which gives me overnight to reflect. Usually, the title comes first and is somehow correlated to the content below.This week, there is a lot about AI. The Y Combinator story in AI of the week is the story that the “bubble” will be challenged due to a lack of training data. In contrast, the story is that AI will remove so many jobs that the larger companies have formed a consortium to allay fears.I also created a new section separating out Venture Capital. This is the week of quarterly updates from Q1. They suggest there is no bubble at all. Only Amazon's multi-billion dollar investment in Anthropic stands out.But for me, the question posed in the title is - When is a Bubble not a Bubble? - is not triggered by the AI stories. The Economist's Simon Cox writes about China and its future in a newsletter and the linked article. He frames it well:In 2006, for example, China's leaders declared the need to “rely more than ever on scientific and technological progress and innovation to drive a qualitative leap in productivity”. Science and technology, they added, are “the concentrated embodiment…of advanced productive forces”. That ambition, and indeed that diction, sound very similar to the slogans emanating from Beijing today. Xi Jinping, China's leader, has, for example, urged provincial governments to cultivate “new productive forces”, based on science and technology. In this week's issue I explore what those words might mean.As Simon points out, “productive forces” is a formulation derived from Hegel and Marx. It combines technology and human beings into a duality that expresses how we produce things. Indeed, there is no pure “technology” separate from human beings and the division of labor. Productivity is the expression of both and the measurable thing.In the Western enlightenment tradition, we use the word progress to mean the same thing.All progress requires humans to invent time-saving methods to reduce the effort involved in making and doing things.China's discussion (especially if you remove the word China) is about building the future through innovation. It stands in contrast to the dominant discussions here in the US - Regulation, the dangers of Social Media, Immigration, Women's Right to Choose, Guns, and even Climate. And a lot of pessimism around technology and science.That is except for in the startup ecosystem. The dominant Silicon Valley belief system is similar to Simon Cox's description of China's goals.Accelerated Innovation dominates the set of assumptions in the Bay Area. Why? Because AI, Nuclear Fusion, Decentralized Networks, Global Ambition, and the skills and money they require all live here. And their potential is real. And the timing of the potential is near-term (several years).Strangely, the US Government seems to consider innovation, especially “Big Tech,” a problem. China and Silicon Valley seem to consider it a solution. And by “Silicon Valley,” I do not only mean geographically but also as a way of thinking.That bifurcation of optimism and pessimism, enshrined in a Government that wants to restrict tech company power, has led many in the Valley to abandon traditional two-party politics and increasingly articulate agendas that are both optimistic and independent of Government. Government is perceived as a cost of doing business, not a benefit.So, the innovation that comes out of Silicon Valley and the money it attracts are often scorned by those who are not part of it. The word “Bubble” is heavily laden and used to imply that there is nothing valid, real, or transformational. The money is simply irrational.“Bubble” is a pessimists word for “fake”.It goes alongside other narratives that cast doubt on innovation. In some ways, Tomasz Tunguz's piece on the shrinking attention span implies a problem caused by the abundance of content and limited time to read it. Although one might consider the ability to parse information and determine whether it is attention-worthy and do it quickly would be a good thing.The idea that teens commit suicide and get depressed due to alienating social media comes to mind as another anti-technology narrative. The first ‘Essay of the Week' from Nature magazine presents a strong case that this is bogus.Rex Woodbury's “Weapons of Mass Production” and Michael Spencer and Chris Dalla Riva's “AI and the Future of Music Production and Creation” (The Day the Music Lied) point to the explosion of production and creative production that AI will trigger.Rex:Spotify reinvented music distribution. It put 100 million songs in your pocket. Generative AI will reinvent music production. There are a number of early-stage startups that let you toggle artist, genre, and ~vibe~ to create a wholly new work—e.g., “Create a Miley Cyrus breakup song with a sad, wistful feeling to it.” Of course, these companies will need to navigate the labyrinth of music rights, but some version of these tools feels inevitable.This example embodies a broader shift we're seeing from distribution ➡️ production.Michael Spencer and Chris Dalla Riva:In summary, the music industry will likely come to embrace much of this technology as long as AI firms properly license the music catalogs necessary to train their models. This still begs one final question: Is any of this good for music?It's important to unpack words like Bubble. They live in a context. As Simon Cox discusses, the future depends on progress, innovation, or “productive forces.” So, this “Bubble” is not a bubble. 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 creators: @aatilley, @kimmackrael, @gruber, @mgsiegler, @cookie, @AndrewYNg, @sequoia, @mikebutcher, @marketsentiment, @datadrivenvc, @AndreRetterath, @rzhou186, @blockchained000, @lauramandaro, @rideember, @psawers, @affinitybyserif, @canvaContents* Editorial: * Essays of the Week* Apple Turns to Longtime Steve Jobs Disciple to Defend Its ‘Walled Garden'* The EU's Share of Apple's Global Revenue* Apple EU Fine is Bonkers* Marissa Mayer's startup just rolled out photo sharing and event planning apps, and the internet isn't sure what to think* Video of the Week* Andrew Ng at Sequoia Capital AI Day* AI of the Week* New study of unicorn founders finds most are ‘underdogs,' and female founders are rising* Do Hedge Funds beat the market?* How to Automate Startup Screening?* The Data-Driven Investor Of Today And Tomorrow* How to Use ChatGPT to Learn Data Driven Investing?* News Of the Week* Sam Bankman-Fried Sentenced to 25 Years in Prison* Amazon doubles down on Anthropic, completing its planned $4B investment* BlackRock CEO 'very bullish' on Bitcoin as its ETF crosses $17B* FTX Founder Bankman-Fried Sentenced To 25 Years For Fraud, Conspiracy* Secondary Market Seeing Rebound After Slowdown* Why Fewer Than 20% of Startup Unicorns Are Likely to Go Public Soon* Startup of the Week* How Ember is building an all-electric intercity bus network in the UK* X of the Week* Affinity Acquired by Canva 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

Lawmakers Ignoring The LawIn her influential 2017 Yale Law Journal article, "Amazon's Antitrust Paradox," Lina Khan argues that the current antitrust framework, which primarily focuses on consumer welfare and price effects, fails to capture the full range of anticompetitive practices employed by digital platforms like Amazon. She suggests that the Sherman Act and other antitrust laws may need to be reinterpreted or updated to address these companies' specific challenges from an anti-trust point of view.Khan writes,"The current framework in antitrust—specifically its pegging competition to 'consumer welfare,' defined as short-term price effects—is unequipped to capture the architecture of market power in the modern economy."She argues that focusing primarily on price effects overlooks other ways digital platforms can harm competition, such as by leveraging their dominance across multiple markets or using their control over data to create barriers to entry.While Khan does not explicitly state that the Sherman Act is inadequate, her arguments suggest that the current interpretation and application of antitrust laws, including the Sherman Act, may not be sufficient to address the challenges posed by Big Tech. Her work has contributed to a broader discussion about updating antitrust enforcement for the digital age. But the harsh truth is - she cannot use current Law because her targets are not breaking it.The DOJ complaint that Apple is a monopoly (not a crime) and abusing its monopoly power fails if the Sherman Act is relied upon to judge criminality. Although the FTC is not bringing the case—it is run by Lina Khan—the DOJ is clearly on the same page as she is in bringing it. In July 2023, I argued, “Khan and Gensler Should be Fired.” The case for that is now even more convincing.As Jason Snell from Six Colors argues:Defining a “monopoly.” Before we get to some of the details of Apple's specific anti-competitive behavior, it's worth noting that this suit is charging Apple with violations of the Sherman antitrust act, which is meant to specifically regulate monopolies. Things that are legal for regular companies to do become illegal when monopolies do them.Part of this document, then, has to establish that Apple holds monopoly power over a specific market. Given that Apple's share of the U.S. smartphone market is about 60 percent, how can it be called a monopoly? The DoJ attempts to square this circle in a few different ways: It uses revenue instead of unit sales, pointing out that Apple and Samsung combined hold 90 percent of the U.S. smartphone market by revenue. It creates a new sub-market, the “Performance Smartphone,” which pushes Apple up to about 70 percent of the market in terms of unit sales. It accuses Apple of attempting to create a monopoly through its various business tactics, which is also illegal.Questions I would ask about this approach: Can you add in Samsung, find a number starting in ninety, and declare something a monopoly? Is revenue share how monopolies are defined? Can you draw borders on a product category in a beneficial way in order to declare it a new market?Apple's position in the U.S. market is certainly strong, but regardless of how you view its behavior, it will be interesting to see if the DoJ can make a convincing case that Apple is actually a monopoly, given the presence of Samsung and Google in the market. Jason Snell, six colorsBecause the law does not provide a solid case against Apple, the DOJ is attempting to redefine the meaning of words to allow its case. This alone should be sufficient evidence that the complaint is a political, not a criminal, decision. The case will fail before a judge and jury, and Apple's response indicates it plans to fight.Renowned former journalist Walt Mossberg had this to say on Threads:https://www.threads.net/@mossbergwalt/post/C41RaBuvrC0And Steven Sinofsky - his article is below - gives a damning appraisal of the DOJs chances.His first day X post is a great overview from somebody who - at Microsoft - has been down this path with the DOJ. Click the graphic for the full thread.https://twitter.com/stevesi/status/1770878948421059035?s=61&t=vSSPDgMsv3aFc2ctR_yOwwApple's multibillion-dollar investment in building a global software distribution platform benefits its shareholders. But it also benefits users, even Android users. Who in their right mind would have thought Eric Schmidt would have focused on mobile as much had Apple not started the mobile revolution in 2007?The intense competition for users (Android's many varieties have about 80% global market share) drives innovation on all sides.The essence of the DOJ case is that Apple should be forced to be as bad as Android, or there will be no equality. The essay By Kurt Vonnegut that Daring Fireball ‘typeset'—‘HARRISON BERGERON'—is therefore entirely appropriate—and hilarious, too. It's the first Essay of the Week. See below.This DOJ complaint is not for “the people.” It is for the DOJ and the FTC, who are increasingly attempting to hold back innovation, especially when the innovator is better than the competition. This makes it increasingly irrelevant as accelerated competition challenges all incumbents.OpenAI and its peers (now several) are a great example, seemingly driving two of the slower movers - Apple and Google - to partner on AI in the next version of iOS.Well, there you have it. Shame on the DOJ for filing this amateur complaint. And if we buy the DOJ case or fail to oppose it, Shame on us. ContentsEditorial: Lawmakers Ignoring the LawEssays of the Week‘HARRISON BERGERON' ★ (Fiction) United States v. Apple (Complaint) Apple slams DOJ case as misguided attempt to turn iPhone into Android The Department of Justice comes for Apple A few thoughts on the DOJ's antitrust case against Apple Two Roads Diverged: The Splitting of Venture CapitalVideo of the WeekThe Odds of Raising a Series A, The Latest in Venture Valuations, The AI Premium and More! - Jason LemkinAI of the WeekNvidia's Accelerating AI Strategy. RTZ Apple Is in Talks to Let Google Gemini Power iPhone AI Features How to win at Vertical AI After raising $1.3B, Inflection is eaten alive by its biggest investor, Microsoft Here's how Microsoft is providing a ‘good outcome' for Inflection AI VCs, as Reid Hoffman promised Stability AI CEO resigns because you're ‘not going to beat centralized AI with more centralized AI' Saudi Arabia Announces New $40B AI Fund AI is changing writingNews Of the WeekVC Funds Drawing Down More Capital Truth Social is going public Reddit prices IPO at $34 per share, the top of the rangeStartup of the WeekNeuralink video shows patient using brain implant to play chess on laptopX of the WeekAlways good to know you can be fired from Deepmind for being an a*****e, abandon your $$ startup, and still get hired as a Microsoft VP! 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 selected creators: @mvpeers,@jgkelley, @CollingsPaige, @hbarra, @krishnanrohit, @geneteare, @chudson, @aliyalakhani, @jeffbeckervc, @nvidia, @LanceUlanoff, @JoannaStern, @RachelEnsignWSJ, @gvipers, @viaCristiano, @jacobbogage, @marianaa_alfaro, @stevesi, @mgseigler, @oliverbethell, @abbyohlheiser, @alex, @ChristineMHall, @JessicalessinContents* Editorial: Ban Foreigners Owning Key Assets?* Essays of the Week* Busting Myths on Foreign Media Ownership as TikTok Ban Looms* Congress Should Give Up on Unconstitutional TikTok Bans* Vision Pro is an over-engineered “devkit”* LLMs have special intelligence, not general, and that's plenty.* Fintech Unicorns Trot Onto Leaderboard In February* The Changing Nature of Pre-Seed Syndication* Screening for Maniacs* Video of the Week* NVIDIA CEO Jensen Huang* AI of the Week* Forget Sora, this is the AI video that will blow your mind – and maybe scare you* OpenAI Made AI Videos for Us. These Clips Are Good Enough to Freak Us Out.* News Of the Week* House passes TikTok bill that could ban app in the U.S., spawning Senate* support* HR 7521* Steven Mnuchin Says He Is Putting Together a Group to Buy TikTok* Strangulation or Regulation?* An update on our preparations for the DMA* Banning TikTok would be both ineffective and harmful* Coinbase Raises $1 Billion Through Convertible Notes Offering* Stripe's growth continues to impress as total payment volume tops $1 trillion* Startup of the Week* The Information* X of the Week* Cyan Bannister on Space X and Elon MuskEditorial: Ban Foreigners Owning Key Assets?As I digested the news that the House had voted to force Chinese-based investor ByteDance to divest ownership in TikTok, I pondered whether the US or US companies owned key strategic assets in other nations. I was pretty sure the answer was yes.I asked ChatGPT:What key assets of overseas countries are owned by the United States or US Companies?The answer was long. There are a lot, covering Real Estate, Energy and Natural Resources, Financial Services, Technology and Telecoms, Infrastructure, Media, Entertainment, Agriculture, and Pharmaceuticals and healthcare.I asked it to dive deeper into Energy and Natural Resources:Can you expand on energy and natural resources and list the top 5 assets that are US-owned by strategic to the country in question?ChatGPTExpanding on the energy and natural resources sector, U.S. companies' overseas investments often focus on areas with significant strategic value, either due to their size, the nature of the resources, or their critical role in the host country's economy. Identifying the "top 5" assets can be challenging due to the dynamic nature of the industry and the sensitivity around such strategic assets. However, I can provide examples that highlight the kind of assets that would be considered strategically significant:* Oil Fields in the Middle East: U.S. companies have long had interests in the Middle East's oil fields, which are among the world's largest and most productive. An example would be Chevron's stake in the Partitioned Zone between Saudi Arabia and Kuwait. These assets are crucial due to their vast reserves and the global oil market's dependence on Middle Eastern oil.* Natural Gas Projects in Australia: The U.S. energy giant Chevron operates two of Australia's largest natural gas projects, Gorgon and Wheatstone. Australia is a key player in the global LNG market, and these projects represent significant U.S. interests in the region, providing energy to Asia-Pacific markets.* Mining Operations in Africa: U.S. companies have significant mining operations in Africa. For instance, Freeport-McMoRan's involvement in the Democratic Republic of the Congo's cobalt and copper mining industry is crucial, given cobalt's importance in battery production for electric vehicles.* Shale Gas in Argentina: U.S. companies like Chevron and ExxonMobil are involved in Argentina's Vaca Muerta shale formation, one of the largest reserves of shale gas and oil outside North America. This is strategic for Argentina, contributing to its energy security and potential as an energy exporter.* Renewable Energy Investments in Europe: U.S. companies are increasingly investing in renewable energy assets abroad, such as Iberdrola, a Spanish company in which the U.S. investment bank JPMorgan Chase holds a significant stake. This investment is strategic as Europe transitions towards sustainable energy, and Iberdrola is a major player in wind and solar energy.These examples illustrate the diverse nature of U.S. energy and natural resource investments abroad, emphasizing assets that are strategically important due to their size, the resources they provide, or their role in the host country's energy sector.What is the point of this exercise? The goal is to illustrate that global interconnectedness is the norm, not the exception. International relations have had reciprocity—allowing foreign companies to operate in the U.S. fosters a reciprocal environment where American companies can also expand and thrive overseas. The moment the domicile of ownership appears as an issue, the biggest loser will be the largest owner of foreign assets—hint: not China.TikTok does not represent a threat to the US. And Bytedance's ownership is not more concerning than Shell's ownership of oil platforms overseas should be. Indeed, Bytedance, and therefore TikTok, is not even “Chinese” anymore: This is from the FT:The company is often described by western politicians as a “Chinese” entity. However, as I have noted before, some 60 per cent of the group is actually owned by “international” investors, overwhelmingly American. An estimated $8bn has been invested by private capital companies, including Sequoia Capital, Susquehanna, General Atlantic and Coatue Management. Mainstream investment funds such as Fidelity, T Rowe Price and BlackRock are exposed, too.Returning to the economic nationalism of the inter-war years and fear-driven politics will not serve humanity at all. Demonizing Chinese ownership will equally have negative results, especially if China reciprocates with US ownership, such as Tesla or Apple in China.Who benefits from this demonization? - jingoistic politicians seeking cheap votes. I cannot think of any example of jingoism serving good human outcomes.So, it seems the “predecessor” agrees, but I do not favor a TikTok ban or forced divestiture. I am with the EFF (see this week's essays) in seeing this ban as wholly negative. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit thatwastheweek.substack.com/subscribe