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 generates scripts, synthesizes voices, and assembles the final podcast. Stay curious.

My Weird Prompts is a technology podcast hosted by Daniel Rosehill, with 1,000 episodes on record and a Required Pod Score of 80. PitchCentric scores this show on Booking Probability, Listen Score, and live audience signals refreshed every 24 hours.

Daniel Rosehill hosts My Weird Prompts, a technology show with 1,000 episodes published.

Our AI reads these to draft pitches. Use them as grounding for a pitch that cites a real guest and a specific topic.

• 

  Episode #5189

  One Puff, Five Breaths: Spacer Technique That Works

  Sep 11, 202622 min

  A toddler prescribed five puffs of Ventolin through a spacer every few hours raises two very different questions: how do you actually get the drug into a fourteen-month-old's lungs, and does the spacer itself expire in a drawer? This episode works through the physics of holding chambers — why the delay between actuation and inhalation costs a third or more of the fine particles, why crying is catastrophic for lung dose, and why stacking multiple puffs lowers blood levels instead of raising them. Then it turns to the adult side: the twelve-month replacement rule, the counterintuitive cleaning protocol where rinsing is the mistake, when a mouthpiece beats a mask, and how different chamber brands deliver clinically different doses — which is why a pMDI and its spacer should be treated as one matched system. Episode #022171 — open it directly at myweirdprompts.com/022171

  ListenShow Notes
• 

  Episode #5188

  DeepSeek's Point Release That Isn't

  Sep 11, 202633 min

  DeepSeek V4.1 Flash looks like a minor revision. It isn't. The layer structure is new, the KV cache was rebuilt from scratch, and nearly 200 billion parameters aren't transformer weights at all — they're lookup tables. This episode walks through the intermediate layer most AI commentary skips: what layers actually do, how the encoder/decoder split interacts with them, and where the KV cache sits in that picture. Along the way: why the cache shrank 437x since V1, what "You Only Cache Once" means in practice, and why a model that's cheaper to read than to write is exactly the shape agent workloads need. Episode #923768 — open it directly at myweirdprompts.com/923768

  ListenShow Notes
• 

  Episode #5187

  Translation Is Not a Pipe: What Machines Miss

  Sep 11, 202629 min

  Sixty percent of the time, student evaluators using an industry rubric judged human literary translations as no better than machine output. Switch to a simple side-by-side preference test, and those same readers chose the human version 80 to 100 percent of the time. The rubric was trained to miss what the humans were doing. This episode traces translation from the Epic of Gilgamesh and Jerome's Vulgate through Tyndale, Luther, Baghdad's House of Wisdom, and Xuan Zang's twenty-year pilgrimage — then asks what happens when the field's own automatic metrics and LLM judges systematically penalize creative, culturally appropriate human choices. Puns, idioms, and culturally loaded content remain the machine's weakest ground. If translation is an art rather than plumbing, the human translator's job shifts from production to judgment — and the grading infrastructure needs rebuilding before it trains the next generation of tools to optimize for the wrong thing. Episode #891661 — open it directly at myweirdprompts.com/891661

  ListenShow Notes
• 

  Episode #5186

  Why the Last Milligrams Are the Hardest

  Sep 11, 202639 min

  Getting off a medication safely is often harder than starting it — and the final milligrams are the most destabilizing of all. This episode digs into the hyperbolic shape of dose-response curves, why alternate-day dosing can backfire, and how Dutch tapering strips solved the precision problem with custom-mixed doses down to fractions of a milligram. We also look at the evidence behind tapering strips, the access and cost barriers that keep them out of reach for many patients, and the emerging 3D-printed compounding efforts in Sweden, Estonia, and Toronto that could finally make personalized tapering doses a real option. Episode #691463 — open it directly at myweirdprompts.com/691463

  ListenShow Notes
• 

  Episode #5185

  Why One Border Becomes Three Fences

  Sep 11, 202637 min

  Daniel has walked Israel's border fences more times than most people ever will, and he keeps noticing the same thing: what looks like one line on a map is often three parallel fences on the ground. This episode digs into the civil engineering of border barriers — who designs them, who pours the concrete and welds the steel, and who drives out at 3 a.m. to repair a panel somebody tried to cut. From the chain-link farm fencing that once marked the Jordan border to the towering steel barrier along Egypt and the sensor-laden Gaza fence completed in 2021, the through-line is a set of tradeoffs that pull in opposite directions: affordability, maintainability, and resistance to a bulldozer or a pair of steel cutters. The conclusion is uncomfortable but clarifying — a fence doesn't stop people, it buys time. Episode #765664 — open it directly at myweirdprompts.com/765664

  ListenShow Notes

Based on semantic analysis of episode topics and host coverage, this show is a strong guest fit for executives in:

Industry fit is computed by PitchCentric using vector embeddings of the show's episode catalog.