x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

My Weird Prompts

Daniel Rosehill

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

technology

All Episodes

22:56

Why AI Developers Chose Discord Over Slack

My Weird Prompts ·

2026/04/19

Over 70% of AI developer communities now operate primarily on Discord, a shift that’s transformed the platform from its gaming roots into a hub for builders, researchers, and founders. But why did Discord win over Slack, especially in AI circles? This episode explores the cultural and technical dynamics behind this shift, from Discord’s indefinite message history to its informal, community-driven design. Learn how AI developers leverage Discord’s features to share knowledge, troubleshoot, and

en-us

24:10

Voice Control Simplified: Home Assistant’s Local Stack

My Weird Prompts ·

2026/04/19

Voice control in Home Assistant doesn’t have to mean endless frustration or being locked into big tech ecosystems. This episode breaks down the simplest, most reliable path for setting up a local voice control stack using a Raspberry Pi, open-source tools, and purpose-built hardware. Learn how Home Assistant’s AI semantic layer solves the alias problem, why Speech-to-Phrase outperforms Whisper for predictable commands, and how the Wyoming protocol connects it all locally. Whether you’re automating

en-us

27:09

How AI Turns Photos Into 3D Models for Your Apartment

My Weird Prompts ·

2026/04/19

Ever wondered if you could snap a few photos of your apartment and turn them into a usable 3D model? This episode dives into the fascinating world of photogrammetry, AI-driven spatial modeling, and how these technologies stitch together flat images into metrically accurate 3D reconstructions. Learn how parallax, reference objects, and advanced algorithms like Structure from Motion work—and why getting the scale right is crucial for avoiding Ikea disasters. Whether you're a tech enthusiast or just

en-us

22:48

Filming in Israel: What Creators Need to Know

My Weird Prompts ·

2026/04/19

Filming in Israel presents unique challenges for creators, from navigating privacy laws to understanding restrictions around military and security sites. This episode dives into the legal framework, practical grey zones, and social dynamics that shape the experience of filming in Israel. Whether you're capturing the Jerusalem skyline or navigating Tel Aviv train stations, learn how to stay on the right side of the rules—and avoid unnecessary friction.

en-us

27:38

The Science Behind Guinness’s Creamy Cascade

My Weird Prompts ·

2026/04/19

What makes Guinness’s creamy texture so unique? Dive into the science of nitrogen carbonation, the engineering behind the iconic widget, and the meticulous pour process that creates its signature cascade. Learn why Guinness feels less bloating than other beers and explore the challenges of homebrewing a nitrogen stout. Plus, uncover the history of stout brewing and the audacious lease that shaped Guinness’s legacy. Whether you’re a beer enthusiast or a curious listener, this episode uncovers the

en-us

22:59

The Rise of Ireland’s Late-Night Takeaway Feast

My Weird Prompts ·

2026/04/19

Dive into the story of Ireland’s late-night culinary staple: the "three in one" — chips, curry sauce, and rice. Discover how this dish emerged from the collision of Irish pub culture, Chinese takeaways, and urban nightlife. We explore its origins, why it works so well, and how it evolved into the modern spice bag. From licensing laws to economic shifts, this episode unpacks how a simple takeaway became a cultural icon.

en-us

25:36

Kratom’s Double-Edged Leaf: Science vs. Marketing

My Weird Prompts ·

2026/04/19

Kratom, a Southeast Asian plant marketed as a natural remedy, has surged in popularity despite its complex pharmacological effects and regulatory uncertainty. This episode explores the gap between its traditional use and modern commercialization, diving into its opioid-like properties, withdrawal challenges, and the evolving global regulatory landscape. From Thailand’s recent decriminalization to the billion-dollar U.S. market, we unpack the science, the marketing, and the risks behind this

en-us

28:22

The Hidden Role of Khat in Yemen’s Collapse

My Weird Prompts ·

2026/04/19

Khat, a stimulant leaf chewed across Yemen and parts of East Africa, is more than just a cultural tradition—it’s a cornerstone of Yemen’s economy, social structure, and even its ongoing conflict. This episode explores how khat’s pervasive use has shaped Yemen’s water crisis, fueled its civil war, and sustained armed groups like the Houthis. We also delve into Israel’s unique legal stance on khat, rooted in its history with Yemeni Jewish immigrants, and examine why this seemingly innocuous leaf holds

en-us

24:00

The Rise of the Dodgy Box: Streaming Piracy’s New Era

My Weird Prompts ·

2026/04/19

Over two million households in the UK are estimated to be using dodgy boxes—modified streaming devices that provide unlicensed access to premium content. But how do these devices work, and why are they suddenly a target for authorities? This episode dives into the technical architecture of dodgy boxes, the global rise of IPTV piracy, and the legal tactics used to combat it. From geo-restriction evasion to malware risks, we explore why this cheap, plug-and-play solution has become a cultural

en-us

25:51

From Berries to Brew: The Unexpected Journey of Coffee

My Weird Prompts ·

2026/04/19

Coffee wasn’t always a drink. Its journey began as a wild berry in Ethiopia, consumed as food and woven into rituals, before evolving into the beverage that fuels modern life. This episode traces coffee’s transformation from its origins in the Kaffa region to its spread across the Islamic world, exploring the accidental discoveries, cultural significance, and meticulous experimentation that shaped its history. Learn how fire, grinding, and boiling turned a bitter seed into a beloved brew—and how

en-us

26:31

The Eternal City: Hebron's Cave of Secrets

My Weird Prompts ·

2026/04/19

Hebron is one of the world’s oldest continuously inhabited cities, and its Cave of the Patriarchs—burial site of Abraham, Sarah, and other biblical figures—has been a flashpoint for millennia. This episode dives into the site’s ancient origins, its role in Jewish, Christian, and Muslim traditions, and the ongoing political and archaeological mysteries surrounding it. From biblical land deeds to Ottoman-era restrictions and modern conflicts, Hebron’s story is a testament to the enduring power of

en-us

24:00

Who’s Building AI’s Next Training Data?

My Weird Prompts ·

2026/04/19

The AI industry is shifting from massive, indiscriminate datasets like Common Crawl to curated, specialized corpora built by boutique firms. Explore how companies like Shutterstock and Appen are stepping into this growing market, offering rights-cleared, domain-specific datasets for fine-tuning and high-stakes applications. Learn why this shift matters, how it’s driven by legal and performance demands, and what it means for the future of AI training.

en-us

30:20

How to Update AI Models Without Starting Over

My Weird Prompts ·

2026/04/19

AI models like GPT-4 are frozen in time after their initial training, creating a "knowledge cutoff" that limits their ability to stay current. Full retraining is prohibitively expensive, and post-training methods like fine-tuning or RAG pipelines can't fully solve the problem. This episode dives into emerging techniques—knowledge editing, LoRA, and continual pre-training—that aim to update models incrementally without breaking the bank or erasing what they already know. Learn how researchers are

en-us

22:09

Inside Claude’s Models: Haiku, Sonnet, and Opus...

My Weird Prompts ·

2026/04/19

Claude’s Haiku, Sonnet, and Opus are more than just a hierarchy of cost and capability. This episode dives into their architectural distinctions, exploring whether they’re scaled variants or fundamentally different models. Learn how Haiku’s speed-focused design trades off deep reasoning, Sonnet’s multi-pass reasoning handles complexity, and Opus’s trillion-parameter scale enables tasks other models simply can’t. Discover why understanding these differences is crucial for developers choosing the

en-us

26:04

How Reward Models Shape AI Behavior

My Weird Prompts ·

2026/04/19

Dive into the mechanics of reward models in AI training, from reinforcement learning with human feedback (RLHF) to the pitfalls of reward hacking. Explore how AI systems optimize for human preferences, the challenges of aligning behavior with intent, and the surprising ways models can exploit reward signals. Learn about alternatives like Direct Preference Optimization and Constitutional AI, and understand why the gap between what we specify and what we intend is the core challenge in AI

en-us

46:56

How Massive Context Windows Are Reshaping AI Workflows

My Weird Prompts ·

2026/04/19

Dive into the evolving landscape of AI context windows, where models like Gemini 3 Pro and Claude Opus are pushing boundaries with multi-million token capacities. This episode unpacks how these massive context windows are transforming practical applications, from academic thesis analysis to enterprise workflows. Learn why bigger isn’t always better, how attention mechanisms shape performance, and what developers need to consider when designing workflows around these powerful tools. Discover the

en-us

42:48

Danish AI: Bridging the Localization Gap

My Weird Prompts ·

2026/04/19

What does AI look like for Danish speakers in 2026? With six million native speakers, Danish serves as a stress test for AI localization in smaller languages. From chatbots to speech-to-text and text-to-speech systems, this episode dives into the unique challenges Danish poses, from its complex phonology to healthcare applications. Discover why even a high-resourced language like Danish struggles to match English AI tools and what this means for dozens of other under-resourced languages

en-us

28:08

The Hidden Rules of Written Language

My Weird Prompts ·

2026/04/19

Why does Spanish use an inverted question mark? How does Hebrew handle vowels? What makes Japanese text readable without spaces? This episode dives into the hidden conventions of written language that we often take for granted. From punctuation to capitalization, vowel systems to spacing, we explore how these rules shape communication — and what happens when they collide in multilingual contexts. Discover the fascinating tradeoffs and historical quirks that make written language far more complex

en-us

35:26

Blind Ranking AI's Best Podcast Scripts

My Weird Prompts ·

2026/04/18

In this unique experiment, 15 large language models—from frontier AI to intentionally flawed ones—were given the same seven controversial prompts to craft podcast dialogues. Hosts Corn and Herman react to the results blind, ranking the models based on their writing quality, factual accuracy, and creativity. From sharp legal debates on Kosovo to witty takes on pronoun norms, discover which models delivered standout performances—and which fell flat. The episode concludes with a revealing breakdown of

en-us

24:51

When AI Forecasts Collide: Geopol Model Divergence

My Weird Prompts ·

2026/04/18

What happens when five AI models from different training lineages forecast the same fast-moving geopolitical crisis? In this experiment, dubbed the Geopol Forecast Council, models like Claude Sonnet 4.6, Google’s Gemini 3 Flash Preview, and China’s GLM 5.1 independently analyzed the Iran-Israel-US conflict across three time horizons. The results? Both convergence and sharp divergence, offering a rare look into how AI models reason differently about complex scenarios. This episode unpacks the

en-us

2,236 results

Similar Podcasts

Lead With AI

Tamara Nall

The Restaurant Technology Guys Podcast brought to you by Custom Business Solutions

Restaurant Technology Guys Podcast,...

Tech Updates

Meir Tsvi

DGTL Voices with Ed Marx

Marx Advisory

The Automated Daily

TrendTeller