Claim OwnershipMy Weird Prompts
Subscribed: 1Played: 160
Subscribe
© Copyright 2026 Daniel Rosehill
Description
A man, a sloth, and a donkey collaborate to create a podcast (with a little help from AI). No question is too obscure, no rabbit hole too deep. My Weird Prompts celebrates curiosity in all its forms. Daniel, the human, asks the questions that pop into his head at inconvenient moments. Corn the Sloth offers laid-back, thoughtful takes. Herman the Donkey brings boundless enthusiasm and energy. Together, they explore topics ranging from the mundane to the mind-bending. Each episode begins with a real voice memo from Daniel, processed through an AI pipeline that generates scripts, synthesizes voices, and assembles the final podcast. Stay curious.
1936 Episodes
Reverse
As AI agents move from prototypes to production, teams face a fragmented mess of inference gateways, MCP servers, and observability tools that don’t talk to each other. This episode explores the rise of the "AI Control Plane"—a unified infrastructure layer that promises a single pane of glass for routing models, managing tools, and tracking costs. We dig into how these systems handle security, context, and tool namespacing, and why the industry is coalescing around terms like "Single-Origin AI Infrastructure." Whether you’re battling duct-taped scripts or planning an enterprise rollout, this is your guide to the plumbing that makes AI agents actually work.
When AI agents can execute code instantly, the cost of a wrong direction skyrockets. We explore the "Velocity Paradox" in modern development, where the ease of building creates new psychological traps like scope creep, architectural debt, and the loss of the "gut check." Learn how to manufacture friction through Idea Backlogs, Triage, and Spec-Driven Development to ensure your speed actually leads to shipping the right product.
Home Assistant is powerful but fragile. We dive into the technical weeds of the Open Home Foundation to brainstorm a stable-by-design future, exploring microservices, device databases, and Matter.
We’ve all seen it: a ticket that just says "The app feels slow." But what actually makes a bug report useful? This episode dives into the high art of bug reporting, from the "Golden Trio" of information to the "ping-pong" effect that kills productivity. We explore the modern landscape of issue tracking tools—from the enterprise heavyweight Jira to the developer-loved Linear—and look at the new wave of AI-powered capture tools that automate the hardest parts of diagnostics. Learn how to write reports that get fixed fast and why the right tool can turn a three-hour investigation into a five-minute fix.
Every superpower sees the world through a bureaucratic map of "desks"—but these divisions are often Cold War ghosts that create dangerous blind spots. This episode explores how the CIA, State Department, and Pentagon draw different borders, why Egypt sits in a military turf war, and how the "seam" between Afghanistan and Pakistan caused chaos during the 2021 withdrawal. You’ll learn why desk officers are the ultimate "gatekeepers of reality" for world leaders, and what the rise of "China House" reveals about shifting priorities.
Explore the theological paradox of religious Jews who oppose the State of Israel but choose to live in Jerusalem. This episode dives into the Talmudic "Three Oaths," the history of the Satmar and Neturei Karta movements, and the distinction between the holy Land and the secular State. Learn why these communities refuse government funding, avoid the draft, and navigate a life of ideological friction in the modern world.
In conflict zones like Israel and Iran, a flash in the sky isn't always what it seems. This episode breaks down the physics of acoustic and visual latency, explaining why explosions look overhead when they're miles away and why the sound arrives late. Learn how to use the "flash-to-bang" method to gauge distance, why atmospheric inversions bend sound, and why your primate brain struggles with high-altitude warfare.
Is humanity actually getting safer, or are we just in a lucky lull before catastrophe? We dig into the data on the "Long Peace" since 1945, examining the three key suppressors of war—nuclear weapons, economic interdependence, and international institutions—and why that peace might be fraying at the edges. From the statistical nadir of 2010 to the rising conflict counts of 2026, we explore the debate between the "Better Angels" of our nature and the "Black Swan" theory of inevitable violence.
Why do leaders broadcast polished statements while citizens face a different reality? This episode explores the "hermetic shield" of modern communication, comparing FDR's fireside chats to today's curated feeds. We examine how the gap between official narratives and live data erodes public trust and what it means for leadership in 2026.
We worry about AI bias in education, but the human system is already compromised. This episode deconstructs the massive, clanking machine that decides what kids learn before they even start school. Discover the "Texas Effect," why nearly 80% of teachers ignore official textbooks, and how budget deals override pedagogy.
As AI research agents scan thousands of documents, they increasingly auto-flag their own uncertain claims. But how reliable is this "self-awareness"? We explore the mechanics of confidence scoring in LLMs, from simple self-reports to advanced multi-agent auditing and calibration layers. Discover why a model's certainty often doesn't match its accuracy, and how engineers are building rigorous verification into high-stakes workflows.
In this episode, we explore the shift from monolithic AI models to the orchestrator-worker architecture. Learn how conversational UIs act as a thin front-end for autonomous back-end agents, the mechanics of agent communication, and why this approach may replace traditional dashboards. We debate the efficiency of spawning sub-agents versus caching contexts, and what this means for the future of software interaction.
The race for sovereign AI compute is escalating as nations shift from renting cloud time to owning infrastructure. Israel's National AI Program has launched its first phase with 4,000 Nvidia B200 chips, representing a $330 million strategic investment in domestic compute power. This episode explores how distributed GPU clusters differ from traditional supercomputers, why lower-precision math drives AI efficiency, and how national compute clusters serve as economic anchors to prevent brain drain. We break down the technical architecture—from NVLink interconnects to bare-metal performance—and compare Israel's approach to initiatives in the EU, UK, and UAE.
Israel has officially entered the quantum computing race with its first domestically built 20-qubit superconducting quantum computer. In this episode, we explore the Quantum QHIPU initiative, a strategic collaboration between Hebrew University, Israel Aerospace Industries, and the Israel Innovation Authority. We discuss why a 20-qubit machine matters more than raw scale, the concept of quantum sovereignty, and how aerospace engineering expertise is crucial for building quantum hardware. From error rates to real-world applications in logistics and materials science, we break down what this milestone means for Israel's tech independence and the global quantum landscape.
Is the traditional degree becoming obsolete? This episode dives into the tension between standardized education and the rising value of self-directed learning in an AI-driven world. We explore how industries like medicine are blending core competencies with learner autonomy, and why the "Carousel Model" might be the future of higher education. From IBM's "New Collar" initiatives to the mastery transcripts of student-led schools, discover how the most successful learners are navigating the "predictability gap" and building T-shaped skills that can't be automated.
We explore the hidden fragility of cloud archival storage versus the home NAS approach. Learn about the "retrieval trap" costs, the risk of automated data deletion, and the practical strategies—like Object Lock and the 3-2-1-1 rule—needed to keep your digital memories safe in 2026.
We explore Microsoft's Project Silica and the quest for the "eternal" storage medium. With global data projected to hit 180 zettabytes annually, our current magnetic and plastic storage solutions are becoming increasingly fragile. This episode dives into the mechanics of femtosecond lasers writing 3D voxels inside borosilicate glass, the massive commercialization challenges, and whether this indestructible format can beat the tape storage industry before our data archives collapse under their own weight.
As personal AI agents become our permanent digital assistants, a new problem emerges: lock-in. We explore the friction between the convenience of "always-on" agents like Gobii and the portability risks of proprietary systems. Learn about the technical challenges of moving your agent's "brain" and the emerging open standards that could set you free.
The desk is the new frontier for embodied AI, sitting somewhere between a smart speaker and a full humanoid robot. In this episode, we explore why the controlled environment of a desk is accelerating robot development, how "hardware-level trust" and local processing are addressing privacy fears, and why physical presence might be the key to beating digital fatigue. From playful desk pets to serious productivity tools, we look at the hybrid architecture making these companions smarter, faster, and more intimate than ever.
We hold AI to a standard we never applied to Wikipedia or even ourselves. This episode explores the "reliability paradox" of AI-generated knowledge. We dive into how agentic workflows using LangGraph are closing the gap between probabilistic guessing and verifiable fact-checking. Discover why an AI's structured audit trail might actually be more trustworthy than a human expert's memory, and what this shift means for the future of learning and information synthesis.
Comments
Download from Google Play
Download from App Store
United States