Daniel Rosehill
My Weird Prompts
The human-AI collaboration podcast. 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...
Be sure to visit the podcast's website and support the creator: myweirdprompts.com
Author
Daniel Rosehill
Category
Podcast website
Latest episode
Nov 21, 2026
Where to listen?
Podcasts in the app Replaio Radio Coming soonPodcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts
Episodes
The End of the Fiction: Mapping the New World Order 15.03.2026 19:11
For decades, the West operated under the "fiction" that economic engagement would inevitably lead to political liberalization. In 2026, that consensus has collapsed, replaced by a fragmented global landscape where high-speed rail and 5G networks often coexist with authoritarian control. This episode breaks down the structural mechanics of modern governance, using a new coordinate system to map the...
The Fraying Bond: Israel and the Global Diaspora 15.03.2026 19:58
From the secret networks of 1945 to the "Nevertheless" immigration plan of 2026, the relationship between Israel and the global Jewish diaspora is undergoing a radical transformation. This episode examines the growing friction over political representation and religious rights alongside the surprising data behind the modern "brain drain" of Israelis moving abroad. Discover how rising antisemitism...
The Three-Minute Gap: Israel's Volunteer Lifeline 15.03.2026 22:43
Why does Israel have some of the fastest emergency response times in the world? This episode examines the friction and synergy between a state-mandated service and a grassroots volunteer network, and what intentional redundancy teaches us about resilience. Episode #242206 — open it directly at myweirdprompts.com/242206
How to Hack a Smart Home for the Sabbath 15.03.2026 20:19
In an era of instant responsiveness and "always-on" sensors, how does an ancient tradition of rest adapt to the digital age? This episode dives into the fascinating world of halachic engineering, where innovators design complex workarounds for everything from high-rise elevators to motion-activated security cameras. We explore the legal philosophy of "indirect causation," the hidden electrical imp...
Why AI Is Rewiring the Internet's Plumbing 15.03.2026 19:39
The AI surge is pushing the internet's physical infrastructure to its breaking point. This episode explores how hyperscalers are building private backbones, why hollow-core fiber matters, and what the shift from user downloads to server-to-server AI workloads means for the web's future. Episode #033688 — open it directly at myweirdprompts.com/033688
The Friday Scramble: When a Nation Runs Out of Time 15.03.2026 22:19
Why does the Startup Nation still operate on a Sunday-to-Thursday workweek? This episode explores the visceral experience of the 'Friday scramble' and the cultural, religious, and economic forces that keep Israel out of sync with the global economy. Episode #890495 — open it directly at myweirdprompts.com/890495
Why Germany Works Less and Earns More Than You 15.03.2026 21:10
Across the globe, the definition of a "hard day's work" varies wildly, from Mexico’s 2,200 annual hours to Germany’s 1,340. This episode dives into the staggering data behind global labor trends, examining how different geopolitical blocs treat human labor as either a raw resource to be extracted or a finite cognitive asset to be managed. We analyze the success of the European Union's Working Time...
Why Can't We All Use the Same Screw? 15.03.2026 16:42
Behind every functional piece of technology lies a complex web of international agreements that most of us never see. This episode explores the fascinating, often contentious history of standardization, starting with the mismatched screw threads that hampered WWII efforts and moving through the birth of the metric system. We examine how technical specifications are far more than just engineering c...
Broken Maps: Why Global Labels No Longer Fit the World 15.03.2026 20:25
For decades, the world was neatly divided into First, Second, and Third Worlds, but those labels are now relics of a bygone era. This episode explores the "Turkey Paradox," China’s strategic use of its "developing" status, and the rise of middle powers like Indonesia and Brazil that are rewriting the rules of global engagement. We dive into how financial institutions and political blocs use these...
Ghost Flights and Legacy Code: Why Travel Tech is Broken 15.03.2026 31:04
Behind the sleek interface of your favorite travel app lies a fractured world of 1960s mainframes, cryptic UN-standardized messaging protocols, and a mountain of technical debt that makes modern flight booking a digital ghost hunt. This episode explores the "Big Three" Global Distribution Systems—Amadeus, Sabre, and Travelport—uncovering how decades-old Transaction Processing Facilities still dict...
Why Life-Saving Alerts Still Use XML 15.03.2026 26:47
Japan's J-Alert and Israel's Red Alert rely on decades-old XML standards and hardware data diodes, not modern apps. This episode explores why the most high-stakes notifications are built on the least trendy tech—and what that means for reliability engineering. Episode #972833 — open it directly at myweirdprompts.com/972833
Beyond "No Training": Securing the New Agentic AI Stack 15.03.2026 30:57
As we move from simple chatbots to autonomous agents with long-term memory, the standard "we do not train on your data" marketing promise is no longer a sufficient guarantee of enterprise security. This episode deconstructs the "agentic stack," revealing how sensitive information flows through vector databases, orchestration layers, and observability tools that often lack the rigorous protections...
Why Hashing Fails: Building Context-Aware Redaction Pipelines 15.03.2026 31:22
Traditional data masking and hashing can't protect against quasi-identifiers in 2026. This episode explores the architecture of modern redaction pipelines that maintain data utility while scrubbing PII from structured and unstructured data. Episode #761864 — open it directly at myweirdprompts.com/761864
Why "Just Use Postgres" Isn't Always Enough 15.03.2026 25:06
In this episode of My Weird Prompts, we dive into the "Just Use Postgres" movement and ask a critical question: is the era of specialized databases finally over? While Postgres has become a Swiss Army knife for modern engineering, physical constraints and hardware architecture eventually force a divide between transactional and analytical workloads. We break down the fundamental differences betwee...
The Art of War as a Mental Operating System 15.03.2026 23:35
Why does a 2,500-year-old military treatise dominate Silicon Valley and modern strategy? This episode deconstructs Sun Tzu's clinical efficiency and its surprising alignment with frameworks like the OODA loop, revealing how timeless principles of psychology and competition outlast any technology. Episode #317761 — open it directly at myweirdprompts.com/317761
The Agentic Shift: 5 Bold AI Predictions for 2026 15.03.2026 25:14
Forget the plateau—AI development is entering a transformative new phase where raw benchmarks matter less than agentic reliability and execution. In this episode, we move past "prediction debt" to deliver specific, falsifiable milestones for the end of 2026, ranging from self-correcting code to massive model distillation. Discover why the transition from fast intuition to deliberate reasoning will...
Hackers Lived in Your Account for 200 Days Before You Knew 15.03.2026 25:03
Most users rely on public notification services to tell them when their personal information has been compromised, but these alerts are often just the "leftovers" of a crime committed months or even years ago. This episode explores the concept of the "silent breach," a reality where hackers exploit misconfigured APIs to mirror entire databases without ever triggering a traditional alarm. We dive i...
The 39 Million Leak: Why Your .env File Is a Pinky-Promise 15.03.2026 21:25
Why do 39 million secrets leak annually, and how can developers move beyond fragile .env files? This episode traces the maturity progression from hardcoded strings to zero-trust infrastructure, revealing the automated bots that harvest credentials in seconds. Episode #278144 — open it directly at myweirdprompts.com/278144
The $30 Billion Blog Post: Can AI Finally Kill COBOL? 15.03.2026 18:27
In early 2026, a technical announcement from Anthropic triggered a massive market sell-off for IBM, proving that a 60-year-old programming language still dictates global financial stability. This episode explores the "load-bearing walls" of the global economy—the 220 billion lines of COBOL that power everything from ATMs to tax systems—and why its unique decimal precision makes it nearly impossibl...
Mojo 1.0: Can Chris Lattner Fix the AI Performance Gap? 15.03.2026 18:26
For years, AI developers have been forced to navigate a fractured world: writing high-level logic in the approachable syntax of Python, while relying on the complex, low-level power of C++ or CUDA for performance. Mojo, the ambitious new language from LLVM creator Chris Lattner and the team at Modular, promises to finally bridge this gap. By functioning as a superset of Python that speaks directly...
The Polyglot Shift: Why Python is Losing Ground 15.03.2026 21:02
For years, Python has been the undisputed king of data science, but 2026 market data reveals a significant shift as specialized languages like R and Julia carve out deep, high-stakes niches. This episode explores the "regulatory moat" protecting R in the pharmaceutical industry and the performance breakthroughs of Julia in aerospace, challenging the long-held "one language to rule them all" narrat...
Why AI Coders Made TypeScript Unstoppable 15.03.2026 19:52
TypeScript is now the most-used language on GitHub, driven by its symbiotic relationship with AI coding assistants. This episode explores how type safety became essential for the AI application layer and what it means for the future of web development. Episode #368520 — open it directly at myweirdprompts.com/368520
Cracking the CUDA Code: NVIDIA’s Software Dominance 15.03.2026 19:24
While the world focuses on NVIDIA’s powerful H100 and Blackwell chips, the real secret to their market dominance is CUDA—a proprietary software layer two decades in the making. This episode explores why this "invisible" language has become the industry standard, making it incredibly difficult for rivals like AMD and Intel to gain a foothold despite impressive hardware specs. We break down the tech...
The Compiler as Truth Machine 15.03.2026 24:44
Why the Rust compiler is uniquely positioned to catch AI hallucinations and enforce memory safety, turning high-risk rewrites into automated, high-confidence sprints. Episode #131099 — open it directly at myweirdprompts.com/131099
Beyond Migrations: Breaking the SQL Straitjacket with AI 15.03.2026 22:17
For decades, database migrations have been the ultimate bottleneck in software development—a manual, high-stakes process that often acts as a straitjacket for new ideas. In this episode, we explore how AI agents like Claude Code are achieving staggering success rates in automating these transformations, shifting the developer’s focus from imperative instructions to declarative intent. We dive into...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.