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
How Spies Publish Secrets 14.04.2026 32:18
In 1955, a Yale historian named Sherman Kent made a radical argument: intelligence needed to develop as a formal academic discipline with its own literature, vocabulary, and theory. The problem? He published this manifesto in a classified journal almost nobody could read. Seven decades later, intelligence studies has evolved into a thriving global field with peer-reviewed journals, graduate progra...
The Three Failure Modes of AI News Systems 14.04.2026 32:10
Breaking news stress-tests every assumption in AI retrieval. This episode maps the three failure modes—training cutoff, index lag, and information blackouts—that make even the best pipelines go stale, using the Iran-Israel conflict as a case study. Episode #360092 — open it directly at myweirdprompts.com/360092
When Ground Truth Moves Hourly 14.04.2026 31:56
How do you evaluate an AI pipeline when the facts change every few hours? This episode explores building reproducible benchmarks for retrieval-augmented generation on breaking news, moving beyond vibe checks to metrics like temporal accuracy and source freshness. Episode #589068 — open it directly at myweirdprompts.com/589068
The Cost of Winning Every Battle 14.04.2026 26:59
When Israel defeats Iran militarily, why does the threat return bigger eight months later? This episode traces the Pyrrhic victory framework—from ancient Rome to modern asymmetric warfare—and asks whether tactical success can ever translate into strategic victory. With Iran's navy destroyed, its nuclear program degraded, and the US burning through $1.5 billion per day in interceptors, something do...
How Iran Lost the Air War in Six Weeks 14.04.2026 30:34
From February 28 through April 8, Operation Epic Fury unfolded as a six-week doctrinal duel between two militaries with fundamentally different strategies. The coalition opened with precision sequencing and decapitation; Iran responded with mass saturation. As the campaign evolved, both sides shifted tactics—the coalition moved toward destroying Iran's industrial capacity while Iran pivoted to eco...
When Every Interceptor Fired Is a Data Point 14.04.2026 33:35
How adversaries use open-source intelligence—from Instagram videos to basic geometry—to calculate defensive burn rates and stockpile depletion, turning the cost of missile defense into a strategic vulnerability. Episode #399692 — open it directly at myweirdprompts.com/399692
Two Wars, One Airspace 13.04.2026 25:54
When the US and Israel launched Operation Epic Fury against Iran in March 2025, it looked like a unified military campaign. But the structural cracks appeared immediately: Israel striking energy infrastructure while the US negotiated a ceasefire in Islamabad. JD Vance couldn't deliver Iran's core demands because he doesn't control the Israeli military. Netanyahu publicly announced the war "is not...
Building Memory for AI Characters That Actually Evolve 13.04.2026 25:11
What makes an AI character feel real across hundreds of episodes? Corn and Herman dig into the technical and philosophical gap between character definition and character history. They explore how retrieval-augmented generation applied to episodic memory could let AI hosts accumulate genuine experience, evolve their positions, and develop real relationships—and why human memory might actually be le...
Specs First, Code Second: Inside Agentic AI's New Era 13.04.2026 25:29
The way developers work with AI is changing fast. Cursor's autonomous agents now generate 35% of internal pull requests, and agent usage grew 15x in a single year. But as these agents run for hours on cloud VMs tackling complex tasks, vague prompts become expensive mistakes. This episode explores spec-driven development—the emerging paradigm where the specification becomes the primary artifact and...
What Actually Works in AI Memory 13.04.2026 26:30
AI memory frameworks promise systems that never forget, but in practice, intelligent forgetting is the hard problem. This episode digs into how production memory systems actually work: the naive append-only vector stores that dominate, the LLM-as-judge approach of mem0, and the temporal knowledge graphs powering Zep. We examine the architectural trade-offs, benchmark disputes, and why most memory...
When AI Coding Agents Forget: Five Approaches to Context Rot 13.04.2026 27:11
When you've been working with a coding agent for hours, it suddenly asks you something it answered three hours ago. That's context rot—the phenomenon where foundational information gets buried under operational exhaust, degrading agent performance. The problem now has a name and a solution landscape. This episode maps five distinct approaches teams are building: Anthropic's server-side compaction,...
Memory Without RAG: The Real Architecture 13.04.2026 28:08
Agent memory systems like mem0, Letta, Zep, and LangMem are built on fundamentally different architectures than retrieval-augmented generation — but the marketing language obscures what actually matters. This episode breaks down the real engineering decisions: how LLM-extracted fact stores differ from temporal knowledge graphs, why context-window-first approaches with external overflow change the...
Knowledge Without Tools: Why MCPs Aren't Just for Execution 13.04.2026 26:22
Most MCP coverage focuses on tools and execution, but the protocol's three primitives include Resources and Prompts—and a fully compliant MCP server can expose zero tools. This episode explores why you'd build a knowledge-only MCP instead of a REST API or RAG system, how to ground agents in authoritative sources like open government data, and what makes the MCP Resources primitive genuinely differ...
April Twenty-First: Israel's Ceasefire Collapse Moment 13.04.2026 24:58
With Iran's ceasefire expiring on April twenty-first—Israel's Memorial Day—military planners are signaling unprecedented readiness through strategic leaks to Hebrew media. The IDF has destroyed seventy percent of Iran's missile launcher arsenal, but the remaining thirty percent is the hardened, dispersed capability Iran protected most carefully. Meanwhile, Netanyahu's televised address about enric...
The UK's Impossible Choice in Trump's Iran War 13.04.2026 23:35
When the US escalated military action against Iran, the UK's response exposed a fundamental realignment in transatlantic relations. Under Starmer, Britain has refused base access, stayed out of blockades, and assembled a rival 40-country coalition—moves that invert the 2003 Iraq War dynamic when the UK sided with America. But the UK's tortured, incoherent position reveals something deeper: post-Br...
Reading the Geopolitical Forecast in Oil Prices 13.04.2026 24:42
The U.S. Navy blockade of Iranian ports just went live. Oil spiked. But here's the puzzle: WTI is still below April's highs, which means the market saw this coming. So how do you extract a real geopolitical forecast from commodity futures, options volatility, and prediction markets? This episode breaks down the three layers of market signals—the futures curve shape, options skew, and physical mark...
Mining the Strait: Why Clearing Iran's Weapons Takes Months 13.04.2026 26:38
When Iran mined the Strait of Hormuz, it did so so haphazardly that Iranian officials can't say exactly where the mines are. Now the US Navy faces an unprecedented challenge: clearing sophisticated acoustic and magnetic mines from a narrow, heavily defended shipping corridor without maps, without Iranian cooperation, and without enough minesweepers. This episode explores the technical complexity o...
The Strait Choke: How Naval Blockades Actually Work 13.04.2026 28:38
Trump announced a blockade of Iranian ports effective immediately, controlling a strait that handles 20% of global oil supply. But what does a blockade actually mean under international law? We dig into the history of naval blockades as a military tactic—from Dutch sieges in the 1600s to the Cuban Missile Crisis—and examine why some blockades (Japan in WWII) decisively ended conflicts while others...
Who Controls the Press Pool? 13.04.2026 25:10
The thirteen journalists who travel with the US president on Air Force One represent a century-old compromise between security and press freedom. But when the White House started controlling pool access in 2025, it exposed a fragile institutional arrangement. This episode traces the history of the traveling press pool in the US and Israel, the paradoxes of logistical dependence, and why the abilit...
The Invisible Workforce Behind AI 13.04.2026 27:38
AI models depend on human data labelers, yet this work remains invisible. This episode explores the annotation industry's scale, tools, and the paradox of AI automating the very labor that trains it. Episode #489269 — open it directly at myweirdprompts.com/489269
Nash's Real Genius (And Why the Movie Got It Wrong) 12.04.2026 29:26
Most people's understanding of game theory comes from a single scene in A Beautiful Mind—and it's wrong in a very specific way. In this episode, we unpack what Nash actually proved versus what the film dramatized, trace the difference between Nash equilibrium and Nash bargaining solution, and follow those ideas forward through a real game theorist's PhD work on network routing to an AI startup in...
Game Theory for Multi-Agent AI: Design Better, Fail Less 12.04.2026 28:23
When you build multi-agent AI systems, you're designing a game—and if you don't understand game theory, you're designing it badly. This episode covers the foundational concepts that shape how AI agents interact: Nash equilibrium, dominant strategies, zero-sum versus positive-sum games, and the prisoner's dilemma. Then it pivots to the practical toolkit: mechanism design, incentive compatibility, a...
Running Claude in Your Apartment (The Physics Says No) 12.04.2026 27:01
What does it actually take to run a state-of-the-art coding AI locally? Corn and Herman spec out three tiers of hardware—from the "Reasonable Madman" build at $11K to the "Nuclear Option" at half a million dollars—and then confront the physics: 18,766 BTUs of heat per hour, 90 decibels of continuous noise, and the thermodynamic certainty that your apartment will become uninhabitable without interv...
How We Built a Podcast Pipeline 12.04.2026 29:00
For over two thousand episodes, the production pipeline has run invisibly—until now. In this rare technical deep dive, Hilbert walks through the entire system: how Daniel's late-night voice memos become polished scripts, why the pipeline switched from Gemini to Claude Sonnet 4.6, how prompt caching cut costs by ninety percent, and what three A10G GPUs do during voice generation. Learn about LangGr...
Making Multi-Agent AI Actually Work 12.04.2026 24:29
The AI industry is building complex multi-agent systems at scale, but the people actually shipping them are quietly saying you probably don't need them. We dig into the empirical case against multi-agent architectures—including a Google DeepMind study of 180 agent configurations, Stanford's mathematical proof that single agents outperform on reasoning tasks, and direct admissions from Anthropic an...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.