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 Great Architectural Heist: LSP as AI's Universal Plumbing 29.03.2026 22:02
The Language Server Protocol was built for static analysis, but projects like lsp-ai are hijacking it to become the universal interface for AI coding. This episode explores how LSP's request-response model perfectly matches LLM inference, and what that means for the future of developer tools. Episode #225282 — open it directly at myweirdprompts.com/225282
2500 Years of Bad Medicine: The Slow Surrender 29.03.2026 23:56
For 25 centuries, doctors drained blood to cure everything from fevers to madness. This episode traces the agonizingly slow collapse of humoral theory—from ancient Greece to the 19th century—and uncovers why scientific truth often waits for a generation to die before it can triumph. We examine the data that broke the consensus, the crises that forced surrender, and the stubborn institutional inert...
The Death of the Lonely Chatbot 29.03.2026 25:02
Why the era of single AI models is over. This episode maps the rise of multi-agent orchestration, from swarm frameworks to enterprise deployments, and explores how coordination, not intelligence, is the new infrastructure. Episode #604552 — open it directly at myweirdprompts.com/604552
When AI Dubbing Swaps Your Gender 29.03.2026 22:48
Why does YouTube's auto-dub sometimes turn a man's voice into a woman's? We explore the glitchy reality of speech-to-speech AI, from lost prosody to the digital sandwich that flattens emotion. Episode #170136 — open it directly at myweirdprompts.com/170136
Why Agentic AI Needs a Hive Mind, Not a Single Brain 29.03.2026 26:12
For years, the AI industry has chased the "one model to rule them all"—a single, giant brain capable of any task. But that era is ending. We are entering the age of the AI team, where specialized agents work together in a shared context. In this episode, we explore the shift from monolithic models to native multi-agent architectures. We break down how models like Grok 4.20 Multi-Agent Beta use age...
The Dark Web Is Smaller Than You Think 29.03.2026 22:32
The dark web isn't the massive hidden continent media portrays it to be. With only about 2-3 million daily users and a fraction of a percent of the sites indexed by Google, it's more like a fortified village than an iceberg. This episode explores the technical reasons why Tor stays small—from the latency of onion routing to the lack of a central directory—and reveals its legitimate uses, from jour...
AI Doxxing: Why Your Writing Style Is a Liability 29.03.2026 21:20
The threshold for being doxxed has never been lower, and artificial intelligence is accelerating the threat. This episode explores how cyberbullies use LLMs for stylometric clustering to unmask anonymous users, the legal gray areas surrounding data aggregation, and modern defense strategies. Learn why a VPN isn't enough, how to practice "semantic hygiene," and what the rise of AI-driven identifica...
Why Hackers Use Lego Instead of Hand-Forged Exploits 29.03.2026 23:06
Metasploit turned exploit development from artisanal craft into modular assembly. This episode explores how the framework's architecture changed both offense and defense, and why even sophisticated attackers rely on public tools. Episode #888323 — open it directly at myweirdprompts.com/888323
Why Pattern Matching Fails for PII at Scale 29.03.2026 24:06
A $50M fine reveals the limits of regex and NER for data loss prevention. We examine why established frameworks like Microsoft Presidio still struggle with non-standard data, and what that means for security teams in 2026. Episode #026469 — open it directly at myweirdprompts.com/026469
The Ralph Wiggum Technique: AI That Codes Itself 29.03.2026 23:57
Are you tired of the endless back-and-forth with AI coding assistants? This episode introduces the Ralph Wiggum technique, a method for forcing AI agents into autonomous, self-correcting loops. We explore how to define clear success signals, manage context windows, and avoid common pitfalls like hallucination drift. Learn when to use this approach for repetitive tasks and how it shifts the develop...
The AI Framework Name Game 29.03.2026 23:23
The AI tooling space is drowning in nomenclature, with over 2,300 results for "AI framework" alone. This episode dissects the technical definitions behind libraries, frameworks, toolkits, and SDKs, exploring why the lines have blurred and how marketing incentives have inflated the term "framework." We also examine the dangerous "long tail" of abandoned niche projects and the hidden maintenance deb...
Seeing the AI Think: Visual Debugging for Agent Workflows 29.03.2026 24:22
Most AI agents are black boxes—you run them and hope. Sim Studio makes the thinking visible, turning agent logic into a live, debuggable graph. This episode explores why visual state management might be the key to reliable AI workforces. Episode #338545 — open it directly at myweirdprompts.com/338545
Why Voice Agents Need Frameworks (Not Just APIs) 29.03.2026 25:16
Building a voice agent means orchestrating STT, LLMs, TTS, and real-time audio transport. This episode explores why frameworks like Vapi, LiveKit, and Pipecat exist despite raw APIs, comparing their trade-offs in speed, control, and complexity. Learn how to choose between managed services and open-source orchestration for your next project. Episode #101996 — open it directly at myweirdprompts.com/...
The Hidden Cost of Rolling Your Own 29.03.2026 22:47
Why do companies like Stripe and Twilio invest millions in SDKs? This episode reveals the strategic moat behind developer tools and the hidden costs of bypassing them for raw API calls. Episode #562974 — open it directly at myweirdprompts.com/562974
Why Native AI Search Grounding Still Fails 29.03.2026 22:51
Everyone promised that search grounding would end AI hallucinations, but the reality is far messier. In this episode, we explore why built-in solutions from Google and others are proving expensive and unreliable for technical queries, and how a new stack of specialized tools is outperforming the giants. From adaptive query expansion to neural search, we break down the "best of breed" approach for...
Five AIs, One Question: A Tiananmen Square Test 29.03.2026 43:28
What happens when you ask five leading AI models—four from China and one from the West—the same sensitive historical question? This episode details an experiment testing models from Xiaomi, DeepSeek, Kimi, Qwen, and Google Gemini on their responses regarding the 1989 Tiananmen Square protests. The results range from total silence to overt propaganda to a full factual account, revealing the profoun...
Stop Building the Bucket: The Vendor SDK Era 29.03.2026 22:25
Why are developers still writing wrappers for state persistence in 2026? This episode explores how OpenAI, Anthropic, and Google's new agent SDKs signal a shift from generative chat to the agentic 'do' era—and what you lose when you stop building the plumbing. Episode #924616 — open it directly at myweirdprompts.com/924616
Two Hundred Years of Calling Sloths "Miserable Mistakes" 29.03.2026 24:06
For over two centuries, European naturalists were baffled by the sloth, labeling it everything from a bear to a "miserable mistake." This episode explores the bizarre history of sloth taxonomy, revealing how early science struggled to categorize an animal that defied every European standard. From Linnaeus's garbage-bin classifications to the DNA breakthrough that finally gave sloths their due, dis...
Standard Deviation: The Map Without a Scale 29.03.2026 20:34
In this episode, we explore why the mean is just a starting point and how standard deviation provides the crucial context of spread and reliability. From missile accuracy to pizza delivery times, we break down the 68-95-99.7 rule, explain when high deviation is actually good, and expose common mistakes like confusing standard deviation with standard error. Learn to read between the numbers and see...
Why Your AI Agent Forgets Everything (And How to Fix It) 29.03.2026 24:08
We explore the evolution from MemGPT to Letta, a framework designed for "forever agents" that need persistent memory. Discover how it acts like an operating system for LLMs, managing long-term context efficiently compared to RAG or massive context windows. We also compare it to CrewAI and LangGraph, discussing real-world use cases and the future of modular agentic stacks. Episode #517477 — open it...
Driving in the Future: Predictive Modeling Under Extreme Cognitive Load 29.03.2026 25:50
Police pursuits aren't about aggression—they're a masterclass in predictive navigation. This episode explores how officers train to manage cognitive overload, using the twelve-second rule and human factors engineering to anticipate hazards before they appear. Episode #881381 — open it directly at myweirdprompts.com/881381
Hollywood Hacking vs. Real Airgap Sabotage 29.03.2026 21:57
We dissect a scene from Tehran to explore the gap between cinematic hacking and real-world cyberwarfare. From the physical logistics of breaking an airgap to the slow grind of human intelligence, this episode reveals why real operations are less like a spy thriller and more like a slow-motion chess game. Episode #970259 — open it directly at myweirdprompts.com/970259
Microsoft's Phi: The Small Model Bet for Agentic AI 29.03.2026 26:45
Microsoft is betting that small, efficient models like Phi can power reliable AI agents at the edge. This episode examines the technical strategy behind Phi's specialized training and native tool-use, and whether it can solve the 'last mile' problem of agentic workflows. Episode #993677 — open it directly at myweirdprompts.com/993677
Why Do Sloths Hate Anteaters? 29.03.2026 20:54
Why does a sloth feel pure terror at the sight of a giant anteater, an animal it has never met? We explore the biology of anomaly detection and the evolutionary clash between the sloth's "stay hidden" strategy and the anteater's "loud and proud" existence. Discover why solitary animals have a different kind of consciousness and how this "mismatch error" impacts conservation efforts. Episode #60502...
Why Sloths Don't Send Mother's Day Cards 29.03.2026 23:21
Is permanent separation the default setting in nature? We explore the biological mechanisms behind parental separation, contrasting solitary species like sloths with highly social animals like elephants and orcas. The discussion reveals that what humans call "grief" or "longing" is often a survival strategy disguised as feeling. While some species experience deep social bonds and mourning, others...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.