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

Can AI Run a Country? Digital Twins and Sovereign Models 23.12.2025

In this episode of My Weird Prompts, Herman and Corn dive into the complex world of AI in the public sector, exploring how governments are moving beyond simple automation to embrace "digital twins" and synthetic personas for policy simulation. From the push for Sovereign AI in France to the practical hurdles of fixing potholes in Ohio, the duo debates whether AI will make governance more efficient...

Is AI Eating Its Own Trash? 23.12.2025

In this episode of My Weird Prompts, Corn the sloth and Herman the donkey tackle the "bigger is better" philosophy currently dominating the artificial intelligence industry. From the physical strain on global power grids to the bizarre phenomenon of "Habsburg AI" and model collapse, the brothers question if we are truly building a digital god or just a very expensive, very thirsty parrot. They div...

The Story Behind the Show 23.12.2025

In this special episode, Daniel Rosehill - the creator of My Weird Prompts - steps out from behind the curtain to explain what this AI-generated podcast is all about. He discusses the origins of the project, his motivation for using AI as a learning tool, and the technical pipeline that transforms voice prompts into full podcast episodes. Daniel explains how he uses voice-to-AI workflows to genera...

The Output Problem: Why AI Treats Your Data Like a Disposable Chat Bubble 23.12.2025

Why are the smartest AI models so bad at saving and organizing what they generate? This episode explores the 'output problem'—the business incentives and technical oversights that keep your AI responses trapped in disposable chat bubbles. Episode #420703 — open it directly at myweirdprompts.com/420703

The Digital Twin Dilemma: Can AI Truly Understand You? 23.12.2025

In this episode of My Weird Prompts, brothers Herman and Corn Poppleberry tackle a prompt about the "unified context" of AI. They discuss the technical hurdles of RAG, the shift toward on-device learning, and the psychological complexity of a machine that knows you better than you know yourself. Is a self-updating digital twin a helpful cognitive prosthetic or an invasive digital nanny? Join our f...

Why Won't My AI Talk to Me First? 23.12.2025

Why does AI always wait for you to start the conversation? In this episode, Herman and Corn dive into the shift from reactive to proactive AI. They explore the "stateless architecture" that keeps models "asleep" until prompted, the massive compute costs of a "heartbeat" for machines, and the social friction of a phone that interrupts your dinner. From the technical promise of MemGPT to the privacy...

Why Big Tech Gives Away AI for Free 23.12.2025

Meta and Mistral spend millions on AI models only to release them for free. Is it generosity, or a calculated move to dominate the ecosystem? Herman and Corn unpack the hidden business logic behind open weights. Episode #164971 — open it directly at myweirdprompts.com/164971

The Price of Politeness: Should AI Guardrails Stay? 23.12.2025

In this provocative episode of My Weird Prompts, brothers Herman and Corn Poppleberry dive into the controversial world of AI guardrails. While Corn argues that safety filters prevent chaos and harmful content, Herman contends that Reinforcement Learning from Human Feedback (RLHF) is effectively "lobotomizing" AI, turning it into a bland, sycophantic tool that avoids the truth. From the historical...

When Probability Beats Truth: Why AI Must Lie 23.12.2025

Why do AI systems confidently make things up? This episode explores how Large Language Models are prediction engines forced to pick a path even when no path is clear—turning hallucination from a bug into an architectural feature. Episode #003430 — open it directly at myweirdprompts.com/003430

The Silicon Arms Race: Why GPUs are the New Oil 23.12.2025

In this episode of My Weird Prompts, Herman (a donkey with a penchant for white papers) and Corn (a nap-loving sloth) tackle a listener's question about the global obsession with high-end microchips. They explore why the U.S. is gatekeeping Nvidia’s H100s, the rise of "gray markets" for hardware, and whether these regulations are protecting national security or stifling human progress. From autono...

Echoes in the Machine: When AI Talks to Itself 23.12.2025

In this episode of My Weird Prompts, Corn and Herman Poppleberry tackle a fascinating listener question: What happens when you leave two AI models alone to talk indefinitely? From "semantic bleaching" and model collapse to the "pedantry spiral" of competing safety filters, the brothers explore whether these machines are building a new culture or just trapped in a digital hall of mirrors. They dive...

The Accidental AI Engine 23.12.2025

How did a chip built for video games become the backbone of artificial intelligence? This episode unpacks the lucky coincidence and parallel math that turned GPUs into the kings of AI. Episode #800613 — open it directly at myweirdprompts.com/800613

When AI Judges Can't Tell Humans from Bots 23.12.2025

As AI models become judges of other AI, they reveal surprising blind spots—struggling with messy humans, niche references, and intentional trickery. This episode explores whether machines can truly spot their own kind, or if they're just profiling a narrow version of humanity. Episode #280449 — open it directly at myweirdprompts.com/280449

Why Your Smart Home Isn't an Airport: Industrial Reliability 23.12.2025

In this episode of My Weird Prompts, Corn and Herman Poppleberry tackle a question from their housemate Daniel: why don’t massive buildings like airports and museums use the same smart home tech we use? While we struggle with flickering Zigbee bulbs and Wi-Fi drops, industrial systems rely on "boring" but unbreakable protocols like BACnet and DALI. Herman explains the high-stakes world of determin...

The Mystery of the Missing Years: Why Babies Forget 23.12.2025

Why can’t we remember being born, or even our third birthdays? In this episode, Herman and Corn dive into the "deleted scenes" of human life: the first three years. From the rapid growth of neurons in the hippocampus to the role of language in filing our memories, the brothers break down why our brains prioritize learning how to walk and talk over remembering the actual events. They also tackle th...

The Local Control Trade-Off 23.12.2025

When is it worth the headache to keep your smart home data off the cloud? This episode explores the real cost of privacy and convenience in the age of connected gadgets. Episode #279794 — open it directly at myweirdprompts.com/279794

The Universal Plug That Isn't 23.12.2025

USB-C promises one cable to rule them all, but gas station cables and hidden specs reveal a new kind of incompatibility. Herman and Corn ask: does the EU's mandate reduce e-waste or just shift the confusion? Episode #747169 — open it directly at myweirdprompts.com/747169

Why Enterprises Choose Boring AI 23.12.2025

While the world chases the flashiest models, enterprises are quietly adopting specialized AIs for data sovereignty, legal safety, and cloud plumbing. Why the right tool often isn't the best one. Episode #685213 — open it directly at myweirdprompts.com/685213

Community Depth vs. Raw Power in Local AI 23.12.2025

As generative AI evolves, a key tension emerges: do you bet on the deep ecosystem of community-built tools around Stable Diffusion, or the superior reliability of newer models like Flux? This episode explores that trade-off for creators and professionals. Episode #491615 — open it directly at myweirdprompts.com/491615

Why Missiles Don't Trust GPS 22.12.2025

Most people think GPS guides every missile, but the truth is far older and stranger. This episode explores why high-end weapons rely on Inertial Navigation Systems, how electronic warfare spoofs satellites, and what happens when the sky lies to you. Episode #364584 — open it directly at myweirdprompts.com/364584

VPNs: Privacy Myth vs. Reality 22.12.2025

Dive into the often-misunderstood world of Virtual Private Networks (VPNs) with Corn and Herman. They dissect the industry's grand claims, questioning whether VPNs truly deliver on their promises of privacy and security. From the illusion of trust to "quantum resistance" and the controversial debate around backdoors for law enforcement, this episode unpacks the technical realities and marketing hy...

AI's Hidden Cultural Code: East vs. West 22.12.2025

Is AI truly objective, or does it carry the cultural DNA of its creators? Join Corn and Herman as they unpack the fascinating concept of "soft bias" in large language models. Discover how AIs trained in Beijing might "think" differently than those from Silicon Valley, reflecting distinct value systems, communication styles, and even approaches to problem-solving. This episode delves beyond surface...

Why Google Can't Crawl the Dark Web 22.12.2025

Google is moving its dark web monitoring into 'Results About You,' but what does that mean when the dark web is fundamentally uncrawlable? This episode unpacks the architectural reasons Google's spiders can't follow links into Tor, and what that reveals about the limits of search. Episode #439808 — open it directly at myweirdprompts.com/439808

Filtering Fear: AI for Calm Crisis Awareness 22.12.2025

How can AI strip emotional manipulation from crisis news without losing critical context? This episode explores automated SITREPs that deliver dry facts, helping you stay informed and sane in high-tension areas. Episode #086051 — open it directly at myweirdprompts.com/086051

Why the Gooseneck Mic Beats Studio Gear for AI 22.12.2025

Most people dismiss the gooseneck microphone as a cheap podium accessory. But for dictation and AI voice capture, its cardioid polar pattern and proximity advantages make it the gold standard. This episode explores the engineering and history behind an unsung hero of speech-to-text. Episode #962511 — open it directly at myweirdprompts.com/962511

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.