July 2026
Former Japanese national security adviser Shigeru Kitamura argues that Japan must treat military deterrence, economic resilience, technological protection and alliance coordination as parts of a single strategy against coercion that begins well below the threshold of war. With China’s military expansion and economic leverage reshaping the regional balance, he says Japan should reduce one-sided dependencies while building technological and industrial capabilities that make it strategically indispensable. The US-Japan alliance, in his account, must turn that approach into coordinated action on supply chains, critical technologies, energy and defense capacity.
OpenAI’s Dominik Kundel presents the Codex Micro, built with Work Louder, as a customizable hardware control surface for directing and monitoring Codex work. In a demo using GPT-5.6 Sol to build a browser word game, he uses dedicated controls for voice prompts, Plan mode, reasoning effort, task switching, permission approvals and queued follow-up requests. Kundel’s central claim is that users can map those actions to physical inputs around their own workflow rather than rely on a fixed keyboard layout.
A reported preliminary Stripe evaluation of a bid for PayPal has prompted Jason Calacanis to imagine a merger that combines PayPal’s distribution and cash flow with Stripe’s infrastructure, then cuts deeply into PayPal’s cost base. Alex Wilhelm argues that the same transaction could saddle the faster-growing company with legacy systems and an unwieldy workforce, undermining the focus that made Stripe valuable. Their dispute turns less on whether a share swap or leveraged deal can be structured than on whether PayPal’s reach can be separated from the machinery required to sustain it.
Texas is building a statewide commercial-space industry around NASA talent in Houston, launch sites on the coast and in West Texas, and manufacturing and testing operations in Central Texas. Bloomberg reports that state grants are reinforcing a model in which NASA contracts help companies finance early development, while Texas offers industrial capacity and a business-friendly environment to keep them expanding locally. Loren Grush, Bloomberg’s space reporter, says SpaceX’s scale has made the strategy more visible—and its environmental and local costs around Boca Chica harder to ignore.
Admiral James O. Ellis argues that Iran’s prolonged closure of the Strait of Hormuz has exposed an energy transition driven less by fuels than by vulnerability: access now depends on geography, military protection and commercial confidence. Replacement oil and gas can ease an immediate shock, he says, but cannot reopen a route that shipowners and crews consider unsafe. Ellis calls for greater naval capacity, allied cooperation and advance planning with Asian partners whose energy supplies depend heavily on Gulf transit.
ElevenLabs presents its Voice Changer as a way to preserve a recorded performance—its cadence, timing and emphasis—while replacing its vocal identity with a selected voice from its library of more than 10,000 options. The tutorial argues that the strongest results depend less on aggressive settings adjustments than on clean input, default controls and an original performance that already approximates the target character’s pitch and tone.
Anthropic researchers Gurnee, Ameisen and Batson argue that a language model trained only on token sequences learned an internal, approximate way to track line length and predict whether a word will fit before a line break. Their analysis traces that decision to features representing token length, position, inferred line width and distance from the boundary, arranged not as a simple counter but as a curved, spiral-like geometry analogous to biological place cells.
Space has become a civilian and military dependency whose security architecture has not kept pace with the ways adversaries can disrupt it, argues Kari Bingen of the Center for Strategic and International Studies. The panel’s broader case is that securing space now means protecting an interconnected orbital and terrestrial system: proliferated constellations may make satellites harder to disable, but ground networks, terminals, data links and layered suppliers remain vulnerable to attack or compromise. As commercial activity expands, Heather Pringle of the Space Foundation argues, the rules and norms for managing this increasingly congested and contested domain have lagged behind.
TBPN’s John Coogan argues that the AI buildout is concentrating spending and power in the infrastructure layer, leaving companies such as IBM exposed even when their existing businesses remain profitable. The show examines DeepMind chief Demis Hassabis’s call for mandatory frontier-model testing, with Coogan and Jordi Hays questioning how such a regime would define covered models, govern foreign and open systems, and avoid favoring the largest labs. New York’s pause on new AI data centers brings the same dispute to the local level: who bears the grid, water, and siting costs of the industry’s expansion.
OpenAI’s Romain Huet argues that Codex is evolving from a code-generation tool into a workspace for delegating and coordinating software work across planning, implementation, testing, deployment and pull-request review. The update centers on GPT-5.6 Sol and its higher-budget Ultra mode, which can split broad goals into parallel tasks, alongside visual browser and computer controls, inline edits, Sites deployment, and task management across desktop and mobile. Huet also notes that Ultra’s larger reasoning budget consumes token limits faster.
Anja Manuel, executive director of the Aspen Strategy Group and Aspen Security Forum, argued that rapid shifts in artificial intelligence, conflict and economic power require leaders to test “too hard, audacious” ideas rather than merely react to events. Opening the forum, she said adaptation must remain anchored in the ideals of free societies, as technology, wars and new growth centres reshape the international order.
Nicholas Burns, co-chair of the Aspen Strategy Group and former U.S. ambassador to China, framed the Aspen Security Forum as the annual culmination of work conducted throughout the year on foreign policy, defense, military affairs and homeland security. He said the group’s model links off-the-record discussions with U.S. military services, sustained homeland-security work and focused deliberation on U.S.-China relations and America’s wider position in East Asia.
Norman Joshua argues that Indonesia’s 2025 expansion of the military’s role into cybersecurity, border management and disaster response reflects a broader model of “governance through security,” in which the armed forces compensate for weak civilian administration. While Indonesia faces legitimate defense and regional-security pressures, he contends that assigning civilian functions to security institutions blurs democratic lines of accountability and can entrench the military in domestic governance. His proposed remedy is stronger civilian capacity, not a diminished defense posture.
Google DeepMind staff engineer Philipp Schmid argues that agent skills should be treated as production dependencies: versioned, tested, and retained only when they measurably improve user outcomes. He says manual checks conceal failures in customer-facing agents, where skills can misfire, over-trigger, or quietly degrade plausible outputs; a lightweight evaluation harness should test routing and task completion repeatedly in clean environments, with and without the skill loaded.
Corey Ching presents Sites as a ChatGPT plugin that turns a conversational brief into a functional web app, then lets users review, revise and publish it without leaving the interface. In the conference-site example, users give feedback in plain language or annotate the rendered page, while Sites handles implementation; Ching says built-in hosting and storage allow the finished app to be deployed directly. A companion Build Web Apps tool extends the same brief-driven approach to interactive software, illustrated with a locally running pixel-art game.
Katie Paris argues that opting out of politics does not remove politics from a person’s life; it cedes power over decisions that shape it. With anti-career coach Danielle Roberts, she makes the case that civic participation begins in local institutions and trusted relationships, while Roberts argues that time, rest, joy and community are necessary to sustain that engagement.
H.R. McMaster argues that sanctions are effective only when they are tied to a realistic political objective and deployed alongside diplomacy, military power, and allied cooperation. Economic damage alone will not force compliance, he says: policymakers must enforce restrictions, preserve humanitarian access, act before targets adapt, and offer calibrated relief for verifiable changes in behavior.
Chris Williamson reads Homer’s Sirens as a warning about the pursuit of information that feels too valuable to ignore: the promise of one more insight can become an endless intake that prevents people from returning to what they need to do. He argues that doomscrolling works similarly, overwhelming users with purportedly urgent material until they lose the time and capacity to reflect or reach settled judgments. Against that saturation, Williamson presents long narrative as a durable form for holding complexity and revisiting it when judgment is required.
Legora’s Max Junestrand and ElevenLabs’ Mati Staniszewski argue that AI’s economic impact will be determined less by access to frontier models than by the systems built around them. Junestrand says legal AI can shift firms away from billing junior-lawyer hours by combining complete legal research, firm data and workflow tools; Staniszewski says voice AI is becoming a customer interface whose viability depends on orchestration, industry integrations and consent over voices treated as identity and intellectual property.
Apple’s lawsuit, California’s challenge to Paramount’s Warner Bros. Discovery acquisition, and a new AI warning letter each concern how institutions respond to technological or market disruption. Apple alleges document theft and improper recruiting as OpenAI develops consumer hardware, while the Paramount case turns on whether Hollywood is a distinct antitrust market or competes for attention across media. The letter, signed by more than 200 researchers and economists, does not prescribe a fixed intervention but calls for research and institutional readiness for possible AI-driven economic change.
Ali Ghodsi of Databricks argues that enterprise AI is constrained less by model capability than by the organizational context models lack: the accumulated knowledge, processes, and exceptions that govern how companies actually work. In a Stanford MS&E435 seminar with investor and lecturer Apoorv Agrawal, Ghodsi says productivity gains require companies to redesign workflows around AI rather than insert models into existing processes. As AI lowers the cost of building software, he argues, durable advantages will depend more on proprietary data, workflow ownership, customer relationships, and trust.
Apple’s trade-secrets lawsuit against OpenAI could complicate the AI company’s effort to build a consumer device by making former Apple hardware talent more cautious about joining, Bloomberg’s Mark Gurman argues. Apple alleges that OpenAI’s recruiting, including under hardware chief and former Apple executive Tang Tan, involved confidential information and prototypes; OpenAI denies any interest in other companies’ trade secrets. Gurman reports that OpenAI remains on track to announce a device this year and ship it in 2027, but says the litigation may reshape its hiring environment well before the facts are tested in discovery.
Engram co-founder and CEO Dan Biderman argues that larger context windows and retrieval systems cannot give AI the accumulated understanding needed to work reliably across an organization’s expanding knowledge base. Models that must reread documents, histories and decisions on every query are costly and prone to “context rot,” he says; Engram’s answer is a trainable memory layer that compresses recurring knowledge into learned representations. The longer-term challenge is deciding what a model should internalize, keep in explicit records and update over time without degrading performance.
Ranjan Roy and Alex Kantrowitz argue that AI products are converging on a common agentic workspace just as Meta moves to challenge the premium pricing of OpenAI and Anthropic. Roy says the durable advantage may lie in the organizational context, integrations, and domain expertise needed to make agents useful at scale; Kantrowitz counters that more capable models could eventually absorb much of that implementation work. Meta’s low-cost API strategy sharpens the question of whether frontier labs can retain pricing power when model capabilities and interfaces increasingly resemble one another.