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

28:59

Focus-Aware Key Remapping on Linux: The Hard Parts

My Weird Prompts ·

2026/08/10

Daniel's been using a foot pedal for dictation for a year and a half, and it works great — until he needs it to behave differently depending on which app has focus. This episode breaks down the nuts and bolts of focus-conditional key remapping on Linux: where keyd lives in the input stack, how it learns about window focus through keyd-application-mapper, and why the X11 and Wayland paths are completely different beasts. We get into the polling race conditions that can corrupt held key sequences, and

en-us

28:42

Parallel vs Sequential Agent Loops: The Real Tradeoffs

My Weird Prompts ·

2026/08/10

Two diagrams show the same AI workflow: one as a sequential chain, one as a parallel fan-out. But the real difference isn't the shape — it's what happens when results come back. We dig into when parallelization actually wins, when it secretly costs more, and why the join node is where workflows live or die. Plus: where does the loop actually live in a graph, and why most diagrams get it wrong.

en-us

23:51

When Context Windows Grow: What Survives?

My Weird Prompts ·

2026/08/10

We're sitting at roughly a million tokens of context, and the entire field of agentic AI has organized itself around that ceiling. But what happens if that limit jumps an order of magnitude overnight? This episode examines whether bigger context windows actually solve the problems we think they will — or just make them worse. We dig into the research on attention degradation, "lost in the middle" failures, and context rot, then build a diagnostic for separating practices that are load-bearing from

en-us

25:12

Loops vs Workflows: Defining AI's New Unit of Work

My Weird Prompts ·

2026/08/10

Everyone's talking about "loops" in Claude Code, but nobody's defining them. We dig into what actually separates a loop from a prompt, a workflow, or a cron job—and why the model's agency over the cycle is the real differentiator. If you've been wondering whether loops are genuinely new or just agentic workflows with better packaging, this episode draws the line.

en-us

26:15

Inside Amazon's Delivery Machine: From Robot Picking...

My Weird Prompts ·

2026/08/10

Why does a package land on your doorstep in the U.S. while pickup points are the norm elsewhere? We crack open Amazon's U.S. fulfillment network—from chaotic storage and Kiva-style drive units to the unsolved "last inch" problem that keeps humans in the loop. We also dig into the real story behind the robots, the productivity paradox, and the working conditions criticism that won't go away.

en-us

24:41

Inside the Machines: Amazon vs. AliExpress Marketplaces

My Weird Prompts ·

2026/08/10

Ever wonder who's actually selling you that gadget? We pull back the curtain on the two e-commerce giants, comparing Amazon's hybrid retail/FBA model with AliExpress's pure marketplace and escrow-based payment system. From warehouse robots to Shenzhen apartments, from sixty-day buyer protection windows to fourteen-day payout cycles, we explore how payments, refunds, and fulfillment really work—and why the numbers are staggering.

en-us

23:39

How the Chicago Convention Built the Modern Sky

My Weird Prompts ·

2026/08/10

In December 1944, while World War II still raged, 52 nations gathered in Chicago to write the rules for the post-war sky. The result was the Chicago Convention and the creation of ICAO — the International Civil Aviation Organization. This episode explores how that moment drew a legal firewall between military and civilian aviation, why that separation was essential for the commercial airline industry to exist at all, and how the system holds together when a 747 strays into Soviet airspace. From

en-us

25:00

Beyond the Itinerary: Travel Writing That Actually Works

My Weird Prompts ·

2026/08/10

Daniel's been thinking about Bill Bryson and what makes a travel book actually work — not a list of sights, but a functional understanding of how people live. This episode explores Bryson's craft, why his self-deprecating curiosity works so well, and the contemporary writers expanding the genre into communities and places the old model never touched. From Smithsonian's best travel books of 2025 to Book Riot's roundup of diverse travel memoirs, we map the new landscape of place-based writing and what

en-us

25:47

How Airport Lights Speak a Universal Language

My Weird Prompts ·

2026/08/10

Ever wonder why every airport in the world looks the same from the cockpit? This episode decodes the visual language of airfields — the alternating amber strobes, the blue taxiway edges, the red stop bars, and the painted markings the size of swimming pools. We break down how ICAO's Annex 14 standardized this system across the planet, how pilots read it in split seconds, and why a color change in your peripheral vision can mean the difference between a safe landing and a runway incursion. If you've

en-us

24:47

Solar Garden Gimmicks: Glowing Frogs & Rotating Beacons

My Weird Prompts ·

2026/08/10

Daniel wants to know how to turn his yard into a glowing spectacle using solar-powered garden accessories. From glowing frogs to industrial rotating beacons, we break down the ten essential gimmicks, the physics behind their underwhelming performance, and the art of combining them to make the in-laws stare in confusion. Plus, why babies love a slowly rotating amber light and how a tiny photovoltaic cell powers a dim, endearing glow that dies by nine p.m. — and why that's the whole point.

en-us

26:06

Why Earth's Heat Has a Ceiling (And 57°C Is a Lie)

My Weird Prompts ·

2026/08/09

Ever seen your car's dashboard read 57°C and wonder why official records never hit 60? This episode unpacks the physics that cap Earth's surface temperature near 54°C, the suspicious 1913 Death Valley record that may be decertified, and why your car's thermometer lies by 15 degrees. Then we get into the physiology: why heatwaves kill mostly through heart attacks, not heatstroke, and why diabetics and older adults are uniquely vulnerable. A perfect blend of atmospheric science, public health, and

en-us

27:14

What "Feels Like" Really Means on Your Weather App

My Weird Prompts ·

2026/08/09

Ever wondered what "feels like" actually means on your weather app? We break down the science behind apparent temperature — from the 1979 heat index formula to wind chill's Antarctic origins. Learn why different weather networks give different numbers, what the models miss (like direct sunlight), and how thermal comfort research explains why your office thermostat wars are actually a scientific inevitability.

en-us

22:33

How Magic Eraser Tools Actually Work: Segmentation +...

My Weird Prompts ·

2026/08/09

Tapping an object in Google Photos and watching it vanish feels like magic, but it's actually a two-stage machine learning pipeline. This episode breaks down the segmentation phase — where a vision transformer identifies exactly which pixels belong to the object — and the inpainting phase, where a generative model fills the hole with brand-new pixels. We explore why artifacts appear, how models like Meta's SAM and Samsung's LaMa push the limits, and why this same technology is used for privacy

en-us

27:27

Building a Miniature Cloud: Proxmox, MinIO, and the...

My Weird Prompts ·

2026/08/09

Daniel's been wondering if a single physical machine can be carved up into a miniature private cloud. The answer involves more than just a hypervisor. This episode breaks down the software stack—Proxmox, MinIO, and OpenNebula—and the hardware realities that separate a box with VMs from a true cloud with tenants, quotas, and S3-compatible storage.

en-us

22:05

Why AI Weights Are Indecipherable

My Weird Prompts ·

2026/08/09

When you download an AI model, you're getting a file of billions of numbers. But those numbers aren't a readable database of knowledge — they're a tangled, distributed pattern that resists interpretation and editing. In this episode, we break down why neural network weights are so opaque, what dictionary learning has revealed about the hidden structure inside models, and why surgical knowledge editing keeps breaking. If you've ever wondered what's actually inside a safetensors file, this one's for

en-us

25:08

What "Distribution" Really Means in AI Models

My Weird Prompts ·

2026/08/09

When we say AI models sample from a distribution, what does that actually mean? This episode breaks down the mechanics — token probabilities, high-dimensional vector spaces, and how training data shapes the "shape" of a model's confidence. We explore the tradeoff between narrow specialization and broad competence, how Mixture of Experts really works, and why the same dynamics apply to text and TTS models. If you've ever wondered why some models feel like experts while others feel like generalists,

en-us

27:06

Why Podcast AI Voices Sound Too Perfect

My Weird Prompts ·

2026/08/09

Ever notice how AI-generated podcast dialogue feels slightly off—too clean, too polite, with zero interruptions? This episode pulls back the curtain on our own AI voices and the "realism gap" in text-to-speech. We explore why current TTS models are trained on single-speaker studio audio, why human conversation is full of overlaps, backchannels, and two-hundred-millisecond gaps, and how multimodal models might finally teach machines to be convincingly messy.

en-us

21:59

How Transformers Killed the Robot Voice

My Weird Prompts ·

2026/08/09

Remember the robotic voice of old text-to-speech? This episode breaks down exactly how neural TTS works under the hood — from text tokenization to transformer self-attention to vocoders — and why we now deliberately add "ums" and pauses back into near-perfect models. If you've ever wondered how your podcast app reads articles aloud, this is the episode for you.

en-us

22:35

Living Airside: Can You Make an Airport Your Home?

My Weird Prompts ·

2026/08/05

What if you could turn a layover into a lifestyle? This episode dives into the strange appeal of airport terminals and asks whether you can actually live airside—hopping from one transit hotel to the next without ever formally entering a country. We break down the legal limits of transit visas, the booking caps built into airport hotels, and the psychological shift that happens when a temporary space becomes your permanent reality. From Changi's butterfly gardens to Dubai's four-hour hotel blocks,

en-us

22:33

Airport Amenities: Pools, Rinks & Fake Streets

My Weird Prompts ·

2026/08/05

From a rooftop pool at Singapore Changi to an ice rink in Dubai and a replica 1920s Hong Kong street, airports are building the world's strangest civic infrastructure. This episode explores ten transit hubs that treat layovers as hospitality experiences, and what these bizarre amenities reveal about the economics of air travel, dwell time, and the captive audience.

en-us

2,233 results

Similar Podcasts

Reflections

Livewire Labs

Eli the Computer Guy

Eli the Computer Guy

Elon Musk Podcast

Stage Zero

LessWrong (30+ Karma)

LessWrong

My Weird Prompts

Daniel Rosehill