AI Infrastructure and Compute
The hardware and cloud stack behind AI, including GPUs, accelerators, data centers, networking, inference chips, and compute supply constraints.
Leverage and Rising Yields Expose the AI Trade’s Fragility
The All-In hosts argue that the AI boom’s long-term productivity promise is colliding with immediate financial and political constraints: a chip-stock selloff exposed the danger of leverage, while higher Treasury yields are raising the cost of betting on distant AI returns. David Sacks maintains that frontier labs’ revenue and compute access support the infrastructure buildout, but Chamath Palihapitiya and David Friedberg question where the economics will ultimately accrue as open models, energy limits and cheaper alternatives reshape the market. They also cast the fight over AI safety, training data and regulation as a contest over who gets to control the technology’s future.
Moonshot’s Kimi Relied on 20,000 Nvidia Hopper Chips
Bloomberg’s Peter Elstrom reports that Moonshot built its Kimi K3 model partly with compute supplied by investor Alibaba, using roughly 20,000 Nvidia Hopper-generation chips, according to Bloomberg’s sources. Alibaba acknowledges supplying the chips but denies that its compute uses Nvidia’s H200s, while the sources identify the cluster as H200-based. Elstrom argues that the arrangement exposes a limit of US export controls: restricting chip sales into China does not necessarily prevent Chinese AI companies from accessing advanced Nvidia compute.
Phasing Out Fossil Fuels Delivers Immediate Public-Health Benefits
Edward Maibach argues that phasing out fossil fuels should be treated as an immediate public-health intervention, not only a response to future climate risks. Alongside pediatrician Lisa Patel, sanitation advocate Catherine Coleman Flowers and air-quality entrepreneur Darren Riley, he points to local benefits—from fewer asthma exposures near schools and in homes to safer water during floods—that can make decarbonization a more concrete policy choice.
Situational Awareness Unwind Shows How Margin Calls Can Outrun a Thesis
John Coogan and Jordi Hays argue that both a leveraged AI-infrastructure fund and Ferrari’s first electric vehicle must be judged by the structures that carry them to their intended outcomes. Coogan says Situational Awareness’s reported forced unwind does not necessarily invalidate its AI thesis, but shows how leverage and volatility can end a trade before it can play out. On Ferrari’s Luce, Hays questions whether meeting a reported sub-500-unit 2026 target proves commercial success, while Coogan sees its low-volume strangeness as part of its appeal to collectors.
The 1% Rule for Finding Durable AI Opportunities
Google chief scientist Jeff Dean argues that AI founders should test frontier models on the workflows they hope to build around: if a general model already succeeds meaningfully, rapid model improvement may erase the opportunity. More durable openings, he says, are tasks where the model succeeds only 0% or 1% of the time and where a small team can add private context, distinct data, specialized models or better evaluation loops. The larger question is whether that advantage will persist long enough—and whether solving the problem matters.
K2 Raises $500 Million to Industrialize High-Power Satellite Production
K2 Space has raised $500 million to expand production of high-power satellites, arguing that spacecraft once built as multiyear, billion-dollar projects can be manufactured at far lower cost and on more reliable schedules. CEO Karan Kunjur says the company’s first 20-kilowatt satellite, now operating in orbit, has supplied the data for its Block Two design and helped drive more than $1 billion in signed contracts. The company’s next test is turning that first flight into repeatable delivery, while developing a larger platform intended to support compute-intensive infrastructure in space.
Qualcomm Targets $40 Billion in Non-Handset Revenue by 2029
Qualcomm CEO Cristiano Amon argues that memory shortages and higher prices—not weaker consumer demand—are depressing handset volumes and margins, while Apple’s faster move away from Qualcomm adds to the near-term pressure. He says the company’s growth case is increasingly tied to automotive, industrial AI and data centers, with non-handset businesses projected to generate $40 billion in revenue by fiscal 2029 and make up about two-thirds of the company’s sales.
Automated AI Research Shows Early Gains in Models, Training, and Kernels
Richard Socher, CEO of Recursive AI, argues that science is constrained by the number of people able to work on increasingly specialized problems, and that agent systems could relieve that bottleneck by running the cycle of hypothesis, experiment, validation and revision at scale. His proposed “Eureka machine” would begin by automating AI research, using search, compute and software tools rebuilt for agents rather than human workflows. The benchmark gains he presents in model training, architecture search and CUDA kernels are early proof points, he says—not yet recursive self-improvement or autonomous science.
Energy Affordability Is Reshaping Climate Politics Across Party Lines
Energy politics is increasingly being fought through affordability rather than explicit climate language, as candidates tie electricity bills, insurance costs and new demand from data centers to household budgets. Mitch Stewart, Brandon Hurlbut and Neil Chatterjee differed over how that shift should shape campaigns and policy, but the discussion’s central tension was clear: pressure to lower costs can support cleaner generation, grid investment and flexibility, or extend the life of fossil-fuel generation and weaken climate commitments.
Midwest Climate Development Faces a Test of Cost, Trust, and Local Power
Midwest climate and energy development will endure only if it lowers household costs, reduces local risks and gives residents a meaningful say over projects reshaping their communities, according to Anika Goss, Stephanie Lawson and John Mitterholzer. They argue that data centers, solar buildouts and land reuse should be judged not simply by their climate claims, but by their effects on electricity and water bills, heat, pollution and neighborhood control. The practical task, they say, is to equip local governments and residents with the information, financing and leverage to set better terms before opposition hardens.
Better AI Models Are Expanding, Not Reducing, Compute Demand
Tae Kim argues that the AI selloff rests on a static view of demand: investors assume more efficient models mean cheaper compute and, ultimately, excess data-center capacity. He contends that more capable reasoning, open-weight and agentic models instead make new workloads commercially viable, expanding total demand for compute, memory, networking and power even as the cost of individual tasks falls. Kim’s more speculative extension is that recursive self-improvement could add another major source of demand within months.
AI Hiring Rebounds as Safety Rules Target Dangerous Open Models
John Coogan and Jordi Hays argue that renewed hiring at large companies complicates the claim that AI will simply eliminate jobs: employers may use it to cut freelance work and avoid some backfills, but also to expand output and hire people who can work with the systems. They apply a similar distinction to the open-weight AI debate, presenting Anthropic’s case for restricting models with demonstrated cyber or biological danger while noting Mark Zuckerberg’s argument for broad access. The unresolved issue, they say, is whether regulators can define dangerous capability, distillation and enforceable infrastructure controls without creating a broad barrier to smaller AI developers.
Big Tech Hiring Is Rotating Toward AI Infrastructure
Tae Kim argues that big technology companies are hiring again, but the rebound is concentrated in silicon, AI infrastructure and core engineering rather than the broad staffing expansion of the zero-rate era. He also sees HBO’s test of a vertical-video feed as an effort to bring discovery back into its own app, using clips from its catalog to move viewers directly into full episodes rather than leaving that attention to TikTok and YouTube. In both cases, Kim’s argument is that companies are rebuilding control over capabilities or audience paths that have become central to their strategy.
SpaceX Faces August Share-Supply Test After $1.2 Trillion Decline
Bloomberg’s Bailey Lipschultz says SpaceX’s post-IPO decline reflects a collision between a $1.77 trillion offering valuation, a heavily shorted low-float stock and a potential August 6 unlock that could sharply expand the shares available for trading. The company’s first earnings report and Starship’s progress on the space-data-center thesis may support the bull case, he argues, but neither settles whether investors will sustain that valuation as supply increases.
AI Capex Skepticism and China Competition Trigger Semiconductor Selloff
Bloomberg’s Peter Elstrom argues that the semiconductor selloff reflects a shift in how investors view AI spending, combined with mounting concern over China’s progress across models, chip equipment and memory. He says Alphabet’s capex plans are no longer being rewarded automatically, while Chinese developers including Moonshot and Alibaba, reported lithography advances, and memory maker CXMT pose distinct challenges to established AI and chip leaders.
AI’s Broad Access Will Depend on Concentrated Compute Infrastructure
Sam Altman argues that OpenAI’s task is to make advanced AI as broadly available as electricity while building the concentrated compute, energy and data-center infrastructure required to produce it. He says demand for cheap, capable intelligence could be effectively uncapped, making large-scale inference revenue the basis for ever-larger training runs. But Altman also warns that cyber risks and the concentration of frontier capabilities could undermine the human agency that, in his account, widespread AI is meant to expand.
AI’s Startup Boom Depends on Keeping Power Widely Distributed
OpenAI chief executive Sam Altman argues that AI gives startups an unusually large opportunity to take on work once reserved for far bigger organizations, but that their role is also political: keeping economic and technological power from concentrating in a few institutions. In a conversation with Y Combinator’s Garry Tan, Altman says founders should use agents and cheaper compute to pursue more ambitious ideas while maintaining safeguards against serious loss-of-control risks.
AI Data-Center Debt Depends on Demand Beyond Two Frontier Labs
Alex Kantrowitz and Ranjan Roy argue that the AI boom’s financial risk lies in the gap between today’s debt-funded data-center buildout and the revenue needed to support it. Kantrowitz warns that a reversal in investor confidence could spread from AI stocks into capital spending and consumer demand, while Roy sees a more immediate problem of timing: frontier labs and hyperscalers may be growing quickly, but not quickly enough to meet the market’s near-term cash-flow expectations. Their dispute is over whether that adjustment would be a rational repricing or the start of a wider contraction.
Autonomous AI Agents Target Fewer Iterations Across Chip Design
NVIDIA argues that autonomous AI agents can reduce the repeated design cycles that slow development of increasingly complex AI-factory chips and their surrounding systems. The company positions Cadence, Synopsys and Siemens EDA tools across a connected workflow from RTL creation and verification to physical signoff, packaging, board design and thermal modelling, while retaining human supervision in Synopsys’s RTL-to-GDS flow. Its measure of progress is not AI-generated code alone, but whether designs require fewer iterations to meet performance, power, area and physical constraints.
NVIDIA Built Its Strategy Around Algorithmic Domains, Not Chips
Jensen Huang argues that NVIDIA’s strategy has never been simply to build better chips, but to identify algorithmic domains where new computing architectures can change what is feasible and then build the stack around them. Recounting NVIDIA’s early failure in 3D graphics, its interpretation of deep learning after AlexNet, and its push into agents and robotics, Huang makes the case that technical leadership depends on confronting wrong assumptions quickly, learning the underlying workload, and organizing close to the work.
RAM, Not Compute, Is Constraining Edge AI Deployment
Cormac Brick of Google AI Edge argues that RAM—not compute—is becoming the binding constraint on local AI, forcing developers to fit models within the memory budgets of phones, robots and low-cost devices. Models in the one-to-four-billion-parameter range can support prompt-based features on better-equipped hardware, he says, but broader deployment requires 50-million-to-500-million-parameter models fine-tuned for specific tasks. The trade is less generality for faster, cheaper offline capabilities such as voice control and dictation.
Lower Qubit Requirements Narrow Quantum Computing’s Path to Utility
Yaqumo CEO Kazuhiro Nakashoji argues that quantum computing’s long-delayed commercial timeline is narrowing because hardware capabilities are rising as the number of qubits needed for useful work falls. He says progress in algorithms, error correction and neutral-atom hardware could bring those curves together around 2030, though quantum processors would serve as specialized accelerators alongside conventional systems rather than replace them. Yaqumo’s bet is that integrating the lasers, vacuum equipment and software behind those machines can turn laboratory research into deployable infrastructure.
Faster AI Inference Could Expand Infrastructure Spending
Cerebras CEO Andrew Feldman argues that faster AI inference can expand infrastructure demand by making AI output more productive, rather than simply reallocating a fixed pool of spending among chip suppliers. Under Cerebras’s partnership with AMD, AMD’s Helios system would process prompts while Cerebras hardware generates answers, a division Feldman says combines GPUs’ strength in parallel processing with Cerebras’s high-speed token generation. He contends that the commercial question is not token cost alone, but the productivity customers can extract from faster responses.
SpaceX Limits Falcon 9 Bookings Beyond 2028 to Prioritize Starship
Bloomberg reports that SpaceX, fully booked on Falcon 9 launches through 2028, is turning away some customers seeking dedicated and rideshare missions beyond that date as it shifts resources to Starship. Sana Pashankar says the move redirects attention from the rocket that has dominated SpaceX’s launch business toward the vehicle central to Elon Musk’s ambitions for expanded Starlink service, space-based data centers, and human missions to the Moon and Mars.