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 19, 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

Building Your Own CRM with AI: Where to Start 12.10.2026

Rita runs a two-person landscape design practice and wants a real backend instead of spreadsheets and rented CRMs. Can AI-assisted development make that realistic? This episode digs into the backbone: the database and architecture. It covers why the schema is the real moat, how to map a garden design practice onto the canonical CRM entities, and why a rigid schema with fast migrations beats a flex...

What Revit 2027 Actually Costs to Run 12.10.2026

A two-person architecture practice wants Revit 2027 running persistently so AI agents can query it through Autodesk's official MCP server. The hardware question looks simple until you price it out. We walk through Revit's actual system requirements, why single-core clock speed matters more than core count, what the read-only MCP tech preview can and can't do, and the three ways to arrange this set...

Revit MCP in a VM: What Actually Works 12.10.2026

Michael runs a two-person architecture practice and wants Revit on an always-on VM so an AI agent can drive the model while both architects sleep. We break down whether that's actually buildable. Autodesk's official MCP server ships as three installers — 8 read tools, 11 write tools, 39 experimental — and not one of them runs arbitrary code. The community servers that do run arbitrary code are the...

Connecting Postgres to Google Workspace 12.10.2026

Rita runs a two-person business on Google Workspace and wants a real business layer on top of it. This episode walks through the integration architecture: why PostgreSQL owns the relationships while Google stays authoritative for documents, messages and events; how service accounts and domain-wide delegation actually differ; and why service accounts can't own Drive files — a constraint that forks...

One Database Won't Fix Your Fragmented Stack 12.10.2026

When a small landscaping practice bolts WhatsApp, a meeting assistant, and a CRM onto its existing backend, the instinct is to consolidate everything into one database. That instinct is wrong. This episode unpacks the distinction between a system of record and a source of truth, then walks through a concrete build order — WhatsApp Business Platform first, transcription second, CRM third — showing...

Rackmounting a Desktop: Size, Cases, and the Swap 12.10.2026

Daniel has a working desktop and an empty 4U slot in his rack, and wants to know what it actually takes to move one into the other. This episode works through the whole procedure: how rack units define your envelope (and why "4U" doesn't mean seven inches of usable room), why depth is the unstandardized dimension that sinks builds, and which three measurements — cooler height, GPU height and lengt...

Running a Company Like a Spy Agency 12.10.2026

What happens when you strip the national security justification out of compartmentalization and run an ordinary company on it? This episode takes a listener's Netflix-style pitch seriously — a workplace where nobody understands their own workload, colleagues can't discuss their work, and feedback comes from a manager whose identity you may never learn. The closest real precedent isn't a corporatio...

Bare Linux Routing vs OPNsense: What Actually Wins? 12.10.2026

OPNsense is a convenience, not a requirement — you can turn a cheap two-NIC mini-PC running Debian or Ubuntu into a full router with systemd-networkd, nftables, dnsmasq and WireGuard. Some people have done exactly that and never looked back: Ansible-provisioned configs, six hundred days of uptime, and patches straight from upstream instead of waiting on a handful of downstream maintainers. Others...

Multi-WAN Beyond Failover: OPNsense vs OpenWrt 12.10.2026

You've built the gateway group, set the tiers, and failover works. So why does a dropped link still kill your VPN, your game, and your VoIP call? This episode separates true bonding from load balancing, then walks through what the "advanced" version of multi-WAN actually looks like in open source. In OPNsense, that means gateway group tiers, trigger levels, weight-based distribution, sticky connec...

Video Tokens, Omni, and the Local VRAM Math 12.10.2026

A listener's question about video understanding gets the full treatment: what actually changed in the past year, why Google's Omni models and agentic video navigation matter, and why uploading a clip to ChatGPT still feels like sneaking past a bouncer. The conversation works through the real arithmetic — roughly 100 tokens per second of video at default settings — and shows how that number drives...

Four Tribes, One Ballot: Israel's Coalition Maze 12.10.2026

Israel just held its first full-term Knesset in decades — and got thirty-eight party lists for its trouble. This episode digs into why closed-list proportional representation with a 3.25% threshold produces a system where nobody campaigns to win, only to be the kingmaker. Then it goes deeper: four groups — Haredi, Tel Aviv, National Religious, and Arab Israeli — each carrying a fundamentally diffe...

Haredi: How a Word Became a Tribe 12.10.2026

The word "Haredi" comes from the Hebrew root for trembling — awe before the divine, drawn from Isaiah. Its common English translation, "ultra-Orthodox," carries a very different charge. This episode traces how a descriptor became an identity, why the label stuck, and how the community it names was deliberately built with state funding within living memory — from Rabbi Shach's 1977 coalition deal t...

Serving DeepSeek-V4.1-Flash on Your Own GPU 12.10.2026

You've got the weights, you've got the rack, you've got a GPU bolted in that you're not replacing. So which engines can actually serve DeepSeek-V4.1-Flash — and how much of your "engine choice" is really a hardware decision wearing a software costume? This episode walks the five-name shortlist (vLLM, SGLang, TensorRT-LLM, llama.cpp, ONNX Runtime) against the model card's supported paths, then runs...

Same GPU, Same Weights, Different Answers 12.10.2026

Two servers, same GPU, same weights, same prompt — different output. This episode digs into Daniel's thought experiment: three providers running vLLM, SGLang, and TensorRT-LLM on identical hardware, where the customer can't choose the engine. Does the inference engine actually change speed, cost, and the answers themselves? We walk through the architecture of all three — PagedAttention, RadixAtten...

ROCm 10.1: AMD's Software Stack Finally Grows Up 12.10.2026

AMD crossed a trillion dollars in market cap and its software stack is finally getting the attention. We dig into three ROCm releases — 7.14, 10, and 10.1 — and ask the honest question: is ROCm actually production-viable for inference now, or just for the data center? From TheRock's reproducible builds to Hyperloom's autonomous optimizer to NUMA-aware memory allocation, we trace what changed, what...

Why You Can't Buy an IEC 60309 Power Strip 12.10.2026

Daniel terminated his first IEC 60309 connector — the blue 16A industrial plug known as commando, pin and sleeve, or CeeForm — and it worked. But two questions remain: what cable actually belongs on a 16A connector feeding a device that would run fine on a lamp cord, and why can't you buy a bench strip or PDU with these outlets? The cable answer is counterintuitive: you size the cable to the conne...

Modiin, Safdie, and the Suburb That Was Meant to Be a City 12.10.2026

Israel is projected to grow by three million people in fourteen years, and most of that new fabric will be laid down after the car. What went wrong in Modiin — the best-documented Israeli new city that was explicitly designed to be urban and became a bedroom community — and what would it take to build differently? This episode digs into Safdie's own planning guidelines, the code that produced cohe...

Can Cities Be Quiet? Designing Density for Families 12.10.2026

Cities are the most efficient habitat humans have ever built — and the place people most want to leave once they have kids. This episode works both halves of that problem: what families are actually buying when they move out, and what premodern cities like Çatalhöyük got right about density and livability that we've forgotten. From the Urban Institute's "families as infrastructure" framing to Jane...

Printing Money Isn't What You Think It Is 12.10.2026

Every year the Fed orders billions of new banknotes, and every year headlines read it as money printing. But the print order is a maintenance schedule, not monetary policy — and the split between replacing worn-out notes and actually growing the money supply is a number the Fed doesn't publish. This episode walks through the whole physical life of cash: how the Bureau of Engraving and Printing and...

Command Centers That Drive: From Transit Vans to 32-Ton Trucks 12.10.2026

A fire department's command truck and FEMA's national fleet share only one feature: wheels. This episode traces the entire spectrum of mobile command centers — from Frontline's 23-foot CRU-22 on a Ford Transit chassis to Riverside County's four-slide-out Freightliner and FEMA's MERS fleet of roughly 275 units with 400-kilowatt generators and fuel tankers. We explore why staying under 10,000 pounds...

How Cities Borrow Money: US Bonds vs Denmark vs Israel 12.10.2026

Most people's eyes glaze over at "municipal finance," but the question of how a city gets credit turns out to be one of the sharpest windows into how a country is governed. The US runs 50,000 independent issuers and a $4.4 trillion retail bond market with a near-zero default rate. Denmark runs a single municipally-owned lender, KommuneKredit, whose liabilities are jointly and severally guaranteed...

Four Ways Humanity Kept Records for 1,200 Years 12.10.2026

What's the difference between a record we dug up and a record somebody never stopped keeping? This episode traces four preservation strategies across twelve centuries: the Shōsōin's raised-floor repository in Nara, which has protected 10,000 eighth-century documents without a single fire; the Vatican Apostolic Archive, which kept the institution alive for 1,600 years but lost most of its own paper...

Fifteen Miles an Hour Through a Metal Pipe 12.10.2026

For over a century, cities moved their urgent mail through sealed tubes using nothing but compressed air and vacuum. Paris built a 427-kilometre network, New York pushed more than half its mail through pipes, and Berlin moved 2.3 million items in 1898 alone. This episode digs into how the capsules actually flew, why water-powered compressors were built to keep the neighbours quiet, and how a mecha...

How Pipeline Pigs Actually Work 12.10.2026

Pipeline "pigs" started as straw bundles shoved down lines to sweep them clean — the squealing noise gave them the name. Today's instrumented pigs weigh several tons, carry magnetic and ultrasonic sensors, and find corrosion and cracks in pipe walls buried four feet underground. This episode walks through the whole picture: cleaning pigs versus smart pigs, magnetic flux leakage versus ultrasonic t...

Where Does the Rain Actually Go? 12.10.2026

Rain on a city street is a plumbing problem arriving all at once. This episode digs into the hidden engineering of municipal drainage: the difference between storm sewers and sanitary sewers, why combined systems were a deliberate Victorian design choice rather than a mistake, and how engineers decide how much rain a pipe has to swallow. Then it climbs into the megaprojects — Tokyo's G-Cans cathed...

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.