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

Technology

Podcast website

myweirdprompts.com

Latest episode

Nov 21, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

Ungrounded: The Hidden Danger in Your Israeli Socket 17.04.2026

Plugging a European appliance into an Israeli socket is a common convenience, but it can silently disable a critical safety system. This episode dives into the engineering of grounding, explaining the vital difference between Class I and Class II appliances and why a plug that physically fits doesn't guarantee electrical safety. We'll decode the trap of the Turkish Schuko plug and outline the real...

The Universal Power Cord's Quiet Masterpiece 17.04.2026

You have a dozen of them tangled in a box, but have you ever looked at the humble IEC power cable? This episode is a full appreciation of the C13 and C14 connector—the universal handshake between your electronics and the wall. We trace its history from pre-1970s chaos to global standard, break down the physics of voltage drop and cable length limits, and navigate the marketplace for buying good on...

The 50-Year Reign of Nine-to-Five 17.04.2026

The nine-to-five schedule feels like a law of nature for office work, but its reign as the dominant paradigm is shockingly brief. This episode traces how a time-based system designed to coordinate factory workers around expensive machinery was grafted onto the emerging class of knowledge workers in the mid-20th century. We explore why this fundamental mismatch persisted for decades and how digital...

Hunter-Gatherers with Smartphones 17.04.2026

The popular image of hunter-gatherers is decades out of date. We explore the reality of the world's last foraging societies, from their surprising health profiles to their strategic use of modern technology. Discover how groups like the Hadza use smartphones to sell honey and why others, like the Sentinelese, violently reject all contact, revealing a complex spectrum of adaptation and resistance i...

Parenting's Cultural Operating Systems 17.04.2026

What feels like natural, responsible parenting in one culture can look like neglect or overbearing control in another. This episode explores parenting not as a set of universal techniques, but as diverse "cultural operating systems." We compare the individualist "stacks" common in the West with the interdependent models of the East, examine how scarcity in the Global South reshapes childhood, and...

The Pitcairn Class: Travel to the Edge of the Map 17.04.2026

Pitcairn Island is more than a mutineer's hideout—it's a modern micro-society of 47 people, defined by a ten-day supply ship and a closed, communal land system. We use it as the archetype to define the "Pitcairn Class" of destinations: places like Tristan da Cunha and Alert, Nunavut, that exist in a state of extreme geographic and logistical isolation. This episode explores why anyone would pursue...

Documentaries About Parking Lots and Drying Paint 16.04.2026

What makes a documentary spectacularly unnecessary? This episode explores films that defy conventional justification, from Andy Warhol's 5-hour "Sleep" to a deep-dive mystery about obscure street tiles. We examine the fine line between focused minimalism and self-indulgent obsession, and why these bizarre cinematic artifacts get made in the first place. Episode #481559 — open it directly at myweir...

The Gap Between AI Output and Art 16.04.2026

What separates a stochastic parrot from a creator of coherent, intentional works? We assess whether AI can invent a language, write a novel, or author a script—and why the gap between generating outputs and creating art remains vast. Episode #745641 — open it directly at myweirdprompts.com/745641

The Papier-Mâché Crab and the Cult Film 16.04.2026

In 1972, a film called *Ha-Trempist* (An American Hippie in Israel) arrived with a significant budget and a sincere message about peace. It featured a giant papier-mâché crab, blackface mimes, and baffling edits to a donkey. It flopped instantly and vanished. Decades later, it re-emerged as a Tel Aviv midnight movie sensation and a canonical "best worst movie." This episode explores the bizarre te...

The Ceasefire That Wasn't: Hezbollah's Rocket Test 16.04.2026

Hours after a US-brokered Israel-Lebanon ceasefire is announced, Hezbollah launches a rocket barrage. This episode examines how a fragile truce on one front is immediately challenged by proxy actions on another, revealing the interconnected volatility of the Iran-Israel-US-Lebanon standoff. Episode #821066 — open it directly at myweirdprompts.com/821066

How Maya, Inuit, and Hadza Parents Sleep at Night 16.04.2026

When a baby won't sleep through the night, is it a parenting failure or a cultural mismatch? This episode examines the nighttime "sleep ecologies" of the Maya, Inuit, and Hadza. We explore how constant proximity, communal responsibility, and aligned expectations transform infant sleep from a solitary battle into a manageable, shared rhythm, offering a kinder reframe for exhausted parents. Episode...

How Maya, Inuit, and Hadza Cultures Engineer Sleep 16.04.2026

When Western sleep training feels like pseudoscientific pressure, where else can we look? This episode explores the anthropology of infant sleep through three distinct cultural lenses: the Maya of the Yucatán, the Inuit of the Arctic, and the Hadza of Tanzania. We examine how these cultures engineer environments where sleep emerges naturally as a byproduct of daily life, from hammocks and parkas t...

The One-Charger Dream: Specs, Trade-offs, and Reality 16.04.2026

Can one desktop charger replace all your bricks? We break down the key specs—total wattage, PD 3.1, PPS, and GaN—and reveal the unavoidable trade-off with proprietary fast-charging phones. A practical guide to cutting cord clutter. Episode #112999 — open it directly at myweirdprompts.com/112999

Typst vs. LaTeX: The AI-Ready Document Engine 16.04.2026

The quest for beautiful, automated document generation is heating up. With Typst's stable release and the rise of AI agent protocols like MCP, we examine whether this modern contender can dethrone the venerable but complex LaTeX. We break down the core features—from declarative styling to human-readable errors—that make a typesetting system truly great for both humans and AI, and sketch the bluepr...

How to Test an AI Pipeline Change 16.04.2026

Iteratively testing AI agent pipelines is slow, expensive, and noisy. This episode explores a systematic engineering alternative: defining deterministic checkpoints within your pipeline. We break down how to instrument these checkpoints, use fixed seeds for reproducible testing, and apply evaluation platforms to get precise, actionable feedback on any change—turning pipeline tuning from alchemy in...

Why AI Agents Get Three Steps, Not Infinity 16.04.2026

Most AI agent demos promise endless autonomy, but the real engineering happens in the guardrails. This episode breaks down the "three-round rule": what a "round" of tool use actually is, why three is the magic number, and the two catastrophic failure modes—infinite loops and cost explosions—that this simple cap prevents. We ground it in a real stack using DeepSeek with native tool calls, explainin...

Why Lithium-Ion Won (And What's Next) 16.04.2026

Lithium-ion batteries power our world, but their dominance wasn't a marketing win—it was a physics inevitability. This episode explores why lithium's position on the periodic table made it unbeatable for portable power and how three decades of incremental engineering squeezed out massive gains. We then look at the real engineering challenges behind the next frontiers: silicon anodes that swell lik...

Agent-to-Agent Protocols: What Actually Needs Standardizing 16.04.2026

Agent-to-agent communication is moving from research into production, but the protocols powering it range from elegant to alarming. This episode digs into what a real A2A standard needs to specify—and what it can safely leave to implementers. We break down session handling and task lifecycles, the state management problem that everyone underestimates, security and authorization challenges unique t...

How Incentives Shape AI Safety Research 16.04.2026

The AI safety landscape is defined not just by where researchers work, but by the conflicting incentives of vendor labs, independent evaluators, and government institutes. This episode maps the ecosystem and asks what it actually means to do safety work under commercial pressure. Episode #292665 — open it directly at myweirdprompts.com/292665

Building Custom Benchmarks for Agentic Systems 16.04.2026

Standard benchmarks optimize for comparability across models, not for the specific failure modes and decision architectures that matter in production agentic systems. This episode walks through the full lifecycle of building custom evaluations: decomposing your workload, defining failure taxonomies with domain experts, constructing rigorous test sets, evaluating trajectories (not just outputs), an...

Why Israel Excels at Defense But Fails at Housing 16.04.2026

Israel presents a striking paradox: nearly eighty years of military excellence, a globally competitive tech sector, yet chronic failures in housing affordability, education quality, and poverty reduction. This episode explores what structural differences explain why some domains succeed brilliantly while others persistently underperform—and what the successes might teach us about fixing what's bro...

Building the All-Whiteboard Room: What It Actually Costs 16.04.2026

Daniel wants to transform his room into a collaborative whiteboard environment. Starting with one oversized board covered in agentic AI workflow diagrams, he's now imagining walls, ceiling, and even furniture all writable. But what does this actually cost? We break down the real products in the market—from budget whiteboard paint to custom porcelain steel panels to frameless glass—explore installa...

Constitutional AI: Anthropic's Theory of Safe Scaling 16.04.2026

What is Constitutional AI, really? Beyond the PR, Anthropic has a specific theory of how to make powerful language models safer: replace noisy human feedback with AI self-critique guided by a written constitution of principles. But this raises hard questions. Does replacing human judgment with AI judgment just move the problem? And what does Anthropic's safety mission actually assume about the rac...

Whiteboard Markers: The Tool Everyone Ignores 16.04.2026

Whiteboard markers are invisible until they fail. This episode digs into the massive gap between commodity markers and quality alternatives—the difference between wet erase and dry erase technologies, why the board surface matters as much as the marker itself, and what you actually buy if you're stocking a serious workspace. We talk Neuland, Edding, Staedtler, and the environmental math of disposa...

When "Global" Recession Means Rich Countries Sneeze 16.04.2026

The Gulf States warn that an Iran-Israel conflict could trigger global recession. But what does "global" actually mean? This episode unpacks the mechanics of economic shocks, why some economies decouple during downturns others can't escape, and the uncomfortable truth: "global recession" is really shorthand for "rich economies are contracting." We explore how oil shocks become contagion, why Austr...

Listen to the My Weird Prompts podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.