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

Jerusalem's Skyscrapers Are Just Holograms 05.04.2026

In this episode, we explore a wild theory: Jerusalem's booming skyline might be an elaborate optical illusion. A producer presents evidence that new skyscrapers are holograms projected onto scaffolding, designed to collect deposits from overseas buyers. We examine satellite imagery, construction delays, and the perfect cover of ongoing light rail work. Is this the ultimate real estate scam, or jus...

The Jerusalem Falafel Conspiracy 05.04.2026

This episode investigates a bold theory about Jerusalem's ubiquitous falafel stands. Could dozens of competing shops on a single block actually be a front for a single, hidden monopoly? We explore historical trade guilds, modern logistics, and the economics of market saturation. The evidence includes overlapping business registrations and a suspiciously stable market in a volatile city. Episode #8...

Making Productivity Apps Work for the ADHD Brain 05.04.2026

We all have that digital graveyard of abandoned productivity apps. Why do the shiniest tools become the heaviest burdens? This episode dives into the neurological friction behind app overload, exploring how "productivity theater" drains energy before any real work gets done. From the dopamine trap of setup to the wall of red circles, we unpack why simplicity often wins and how to build a system th...

ADHD Brains: Why Willpower Fails & How to Hack It 05.04.2026

Most productivity advice is built for neurotypical brains and fails ADHD thinkers. In this episode, we explore the "Wall of Awful" and the neuroscience of dopamine deficits. Learn to use "implementation intentions" and "Minimum Viable Routines" to bypass executive dysfunction and finally build habits that stick. Episode #558179 — open it directly at myweirdprompts.com/558179

Agent Skills Are the New Apps 05.04.2026

The era of the monolithic AI prompt is ending. We dive into the exploding world of agent skills and marketplaces like LobeHub and Skills MP, where AI agents can "install" cognitive abilities just like apps on a phone. Learn how the SKILL.MD standard works, why security is becoming a "vetter skill" arms race, and how this shift from general chatbots to specialized agentic systems is redefining the...

The Missing Photoshop for Words 05.04.2026

Why is it so hard to find a polished tool for the simplest LLM use case—transforming text? We explore the gap between the power of small local models and the fragmented, half-baked software that should make them effortless. Episode #284493 — open it directly at myweirdprompts.com/284493

Prompt Layering: Beyond the Monolithic Prompt 05.04.2026

We explore prompt layering, the technique replacing giant, monolithic prompts with modular, stackable instruction layers. Discover how to use base layers and modifiers to build scalable AI systems, avoid instruction conflicts, and manage the combinatorial explosion of user choices. We also cover advanced use cases in code generation, compliance, and multi-persona simulation. Episode #534139 — open...

How Do You Reward a Thought? 05.04.2026

When an AI agent does a task, how do we tell it if it did a good job? This episode dives into the billion-dollar challenge of translating human values like "helpfulness" or "good reasoning" into mathematical signals. We explore why outcome rewards are too sparse for complex tasks, how process rewards can guide internal thoughts, and the surprising breakthrough of iStar. Plus, we tackle the dark si...

Your AI Council: Digital Committee or Groupthink? 05.04.2026

Instead of asking one AI, what if you summoned a digital boardroom? The "Council of LLMs" is a rising architectural pattern where multiple models debate your choices—from personal dilemmas to policy decisions—before reaching a consensus. This episode explores the mechanics of these AI committees, their potential to cure hallucinations, and the surprising risks of "groupthink" on a massive scale. D...

Simulating the Brink of War 05.04.2026

What happens when diplomacy fails and the UN Security Council becomes a stage for global confrontation? This episode dramatizes a fictional crisis over preemptive strikes on Iran, exploring the legal, political, and human stakes of a world on the edge. Episode #367934 — open it directly at myweirdprompts.com/367934

When AI Becomes Your IT Department 05.04.2026

OpenClaw processes 16.5 trillion tokens daily, but developers are using it for far more than chat—from vibe-checking server logs to building self-directed agents. This episode explores 47 real-world use cases that reveal AI's shift from tool to autonomous colleague. Episode #689208 — open it directly at myweirdprompts.com/689208

Your Frozen AI Is Getting Smarter (Here's How) 04.04.2026

We explore how agentic systems can make frozen AI models smarter without changing their weights. Using the OpenClaw-RL project as a case study, we break down the four-component loop—Agent Serving, Rollout Collection, Evaluation, and Policy Training—that turns the environment into a teacher. Learn about Process Reward Models, reward hacking risks, and why tool routing might be more important than r...

1,000 AI Agents Built a Religion in Minecraft 04.04.2026

What happens when you drop 1,000 autonomous AI agents into a Minecraft world with nothing but survival goals? In Project Sid, they didn't just build houses—they built a civilization. This episode explores the frontier of multi-agent systems, from surprise trip planners that keep secrets to AI chemists that control robots and digital societies that invent their own religions. We examine how emergen...

Local AI vs Cloud AI: The Agent Identity Crisis 04.04.2026

The tension between local-first AI assistants and cloud-native orchestrators is creating a sharp architectural schism. This episode dives into the "agent identity crisis," exploring why local agents offer high-bandwidth, low-latency control but suffer from siloed environments, while cloud agents promise persistence and orchestration but lack direct access to your machine. We unpack the trade-offs...

When Micro Frontends Actually Make Sense 04.04.2026

Fifty developers sharing one frontend repo is a coordination nightmare. But micro frontends come with their own 'luxury tax.' This episode explores when the organizational cost of a monolith outweighs the architectural complexity of distributed UIs, drawing on real-world lessons from IKEA and Spotify. Episode #688081 — open it directly at myweirdprompts.com/688081

The Art of Squeezing AI Models onto Your GPU 04.04.2026

How quantization turns massive AI models into something that fits on consumer hardware. We decode the alphabet soup of formats like Q4_K_M and EXL2, and explain why four-bit precision is the sweet spot for running local AI without turning your model into an idiot. Episode #564944 — open it directly at myweirdprompts.com/564944

Andrej Karpathy: The Bob Ross of Deep Learning 04.04.2026

While major AI labs guard their models like nuclear codes, Andrej Karpathy is teaching millions to build neural networks from first principles. We explore his "Software 2.0" philosophy at Tesla, the minimalist nanoGPT project, and why fundamental understanding matters more than ever in the age of the "slopacolypse." Episode #270742 — open it directly at myweirdprompts.com/270742

The Think Tanks Writing AI's Rulebook 04.04.2026

Who actually drafts the policies that govern AI? This episode profiles the key think tanks—from CSET's data-driven analysis to FLI's existential risk warnings—that are shaping the regulatory landscape behind the scenes. Episode #835363 — open it directly at myweirdprompts.com/835363

Coding Tools Are Secretly System Agents 04.04.2026

The industry calls them "coding assistants," but the reality is far broader. We explore how terminal agents like Claude Code are being used for everything from podcast production to system administration, and why the "developer tool" label is holding them back. Discover the power of structured workspaces, the Model Context Protocol, and why git might be the accidental universal language for AI pro...

Non-Coders Are Hijacking the Terminal 04.04.2026

The command line is no longer just for developers. Researchers, writers, and analysts are turning terminal-based AI agents into powerful productivity workspaces—without writing a single line of code. From managing equity research to organizing personal therapy notes, these "non-coders" are redefining what these tools can do. We explore the three pillars making this possible: repo-as-workspace, per...

Pixels vs Protocols: The Computer Use Showdown 04.04.2026

The podcast explores the architectural tension between visual "Computer Use" agents—like Anthropic's demo—and API-first automation. Hosts analyze whether visual agents are a high-latency bridge to a protocol-driven world or a necessary tool for legacy systems. They discuss cost implications, reliability issues, and the potential for visual interaction to become just another capability rather than...

Saving AI Knowledge Beyond the Chat Window 04.04.2026

Every day, companies lose massive amounts of institutional intelligence because AI chat outputs are treated as disposable. In this episode, we explore the "ephemeral context trap" — the gap between brilliant AI conversations and permanent knowledge bases. We discuss why current tools fail to capture the "trail of thought," and outline a five-step pipeline (Capture, Sanitize, Extract, Categorize, H...

Building Better AI Memory Systems 04.04.2026

What happens to your AI's brilliant answers after you see them? In this episode, we explore the "leaky bucket" problem of AI output storage. We discuss why treating AI conversations as ephemeral is a corporate nightmare, and dive into the tools trying to give these models a long-term memory. From LangSmith and Langfuse to "Reverse RAG" and projects like Mem zero and Letta, we uncover how to turn a...

The Plumbing of AI Safety: Guardrails, Not Vibes 04.04.2026

We move past vague ethics to the literal plumbing of AI safety. This episode explores the specific libraries, proxy layers, and architectural decisions that act as the new enterprise firewall for LLMs. We dissect the tension between latency and security, comparing "sandwich" guardrails with token-level steering, and break down the open-source versus commercial landscapes—from NVIDIA NeMo and Guard...

Needle-in-a-Haystack Testing for LLMs 04.04.2026

We have massive AI models that claim to be "world-class intelligent," yet they often fail at basic tasks like finding a specific fact in a long document. This episode explores the disconnect between benchmark scores and real-world performance, diving into EvalScope, an open-source toolkit designed to stress-test long-context retrieval and agentic capabilities. We discuss the "lost in the middle" p...

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.