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

The Fine-Tuning Career: Titles, Skills, and What It Pays 13.10.2026

Daniel asked a career question, not a technical one: is there a version of fine-tuning work that sits above the human annotation layer — and can it pay properly? The answer is yes, but the role is a bundle rather than a title, spanning Applied Scientist, Research Engineer, AI Data Curator, and forward deployed engineer postings. This episode maps the actual skill stack, the credential gate nobody...

Training a Model When You Don't Know the Labels Yet 13.10.2026

What happens when you need to train an extraction model but the label set doesn't exist yet? This episode works through a listener's parametric-search project — scraping vendor spec sheets to build a filterable home inventory of adapters, cables, and power supplies — where the schema grows during annotation itself. We dig into attribute value extraction, why standard NER assumes a closed world, an...

How Pressure Actually Bonds VHB Tape 13.10.2026

Most people think mounting tape is peel, stick, press, done — but the bond is actually made in the press, and almost nobody talks about it. This episode digs into what pressure-sensitive adhesive is doing at the microscopic level, why 3M's fifteen psi bond-line target is not the same as fifteen pounds of roll-down force, and how pressure distributes unevenly across a real panel — corners included....

Why Modiin Is Ugly Despite Its Form-Based Code 13.10.2026

Modiin is one of the few Israeli cities built from a master plan, complete with a form-based code — the exact tool New Urbanists say produces coherent, beautiful cities. It still reads as extremely ugly. This episode uses Modiin as a test case against Paris as a success case, asking what a code actually has to regulate if beauty, not just order, is the goal. The answer sits in the gap between regu...

Form-Based Codes and the City That Feels Dead 13.10.2026

Hannah wants to build a mid-sized walkable Israeli city with a new Levantine architectural language — and she's asking what the form-based code underneath it would actually have to say. This episode digs into how form-based codes work (frontage types, regulating plans, the shopfront vs. the stoop), why they regulate the shape of buildings but almost never their style, and what Modi'in — Moshe Safd...

What the 1964 White Paper on the Twin Towers Actually Said 13.10.2026

When a 37-year-old listener asked why the Twin Towers fell, the honest answer turned out to be narrower and stranger than the popular story. The towers were the first structures outside the military and nuclear industries ever designed to resist jet impact — a voluntary act by the Port Authority, documented in a three-page white paper dated February 3, 1964. That paper concluded a Boeing 707 or DC...

What the Council on Vertical Urbanism Actually Decides 13.10.2026

The Council on Tall Buildings and Urban Habitat spent 56 years cataloguing height records — then renamed itself the Council on Vertical Urbanism. Daniel looked up Jerusalem's Marom Tower on its Skyscraper Center database and found a much stranger story underneath: an organisation founded in 1969 by an engineer worried about livability, not records, now handing out trophies that developers put on b...

The World's Greatest Drunk Foods 13.10.2026

The spice bag was invented around 2006 as a staff meal at a Dublin takeaway. Poutine lives or dies on cheese curds less than a day old. Chimaek became a word during the 2002 World Cup. These aren't ancient traditions — they're recent inventions that got old fast, because a generation grew up ordering them at two in the morning. This episode tours the world's greatest drunk foods country by country...

Who Believes God Is Personally Involved? The Data on Divine Providence 13.10.2026

Everything happens for a reason" sounds like one belief. It's actually at least three — God orchestrates every event, God permits events for a purpose, or God neither causes nor permits suffering but good can still come of it. This episode traces the vocabulary of divine providence from Maimonides and Nachmanides through the Baal Shem Tov's 18th-century expansion to hashgachah pratit, then compare...

Believing Without Belonging: The Religion of One 13.10.2026

What do you call someone who believes in God but belongs to no religion? Sociologist Grace Davie named it "believing without belonging" in 1990, and the phenomenon has only grown harder to pin down since. This episode digs into the vocabulary (four competing terms, no consensus), the counts (Pew finds 70% of American "nones" believe in God or a higher power, yet the global picture swings tenfold),...

Where Generalists Get Priced: Inside the FDE Role 13.10.2026

Daniel asked where an intellectually restless generalist actually gets priced — and refused the lazy answers. The answer has a name: Forward Deployed Engineer, a role born at Palantir in the mid-2010s and exported across Anthropic, OpenAI, Scale AI, Sierra, Harvey, Glean, Mistral, and Databricks. It pays a 30–50% premium over equivalent backend or ML engineers, with senior compensation at frontier...

Inside Alibaba's Machine: AliExpress, Guanxi, and the China Daniel Has Never Visited 13.10.2026

Daniel has ordered from AliExpress twice a month for years but has never been to China, never worked with a Chinese team, and wants to know what the other side is actually thinking. This episode traces the machinery behind the storefront — Alibaba's fiscal 2026 filing, the split between Alibaba.com and AliExpress, the Choice rollout that now carries over 70% of retail orders, and why Israel became...

Plus Codes, Geohash, and the Open Addressing Gap 13.10.2026

Google's Open Location Code was designed to work completely offline, with no geocoding service and no proprietary database in the middle. Then the consumer interface shipped a shortened form that needs a locality name — and a locality name needs Google. We trace the mechanics of code shortening, the base-20 alphabet built by testing eight billion combinations against words in thirty languages, and...

Living Among the Dead: Cemetery Housing, Cairo to Manila 13.10.2026

What does it mean when a cemetery becomes a neighbourhood? This episode treats cemetery habitation as its own form of housing insecurity — not a curiosity, not a horror story — and follows the evidence where it actually goes. The City of the Dead in Cairo grew from 35 recorded residents in 1898 to 180,000 by 1986, and is now being bulldozed under Egypt Vision 2030. Manila North Cemetery houses aro...

Plus Codes: Free Addressing Nobody Uses 13.10.2026

Open Location Code gives every square on Earth a short alphanumeric address — free, offline, case-insensitive, precise to about 14 metres. Google published the spec in 2014, developers ported it to a dozen languages, and the Navajo Nation used it to address 3,100 homes for EMS. So why is a proprietary, pronunciation-ambiguous rival the one inside 911 dispatch centres? This episode traces Plus Code...

Teaching a Model Your Voice: SFT vs DPO 13.10.2026

You can't reliably prompt a model into your voice — system prompts plateau. So what actually works? This episode works through three data-generation strategies for style fine-tuning: regenerating transcripts with global comments, hand-editing transcripts and training on the diff, and training a purely negative counterweight against overused phrases. A July arXiv paper by Federico Boggia on epanort...

Israel's Urgent Care Safety Net: What Broke 12.10.2026

A listener in Jerusalem, a decade here and fluent in Hebrew, took his sixteen-month-old son to urgent care twice in two months. Both times the boy was in real respiratory distress. Both times the layer that was supposed to catch him before the hospital didn't. This episode traces what actually failed — a documented oxygen saturation and no doctor for twenty minutes, a health fund phone line that c...

The Psychiatrist in Those 1950s Patient Films 12.10.2026

Dr. Heinz Edgar Lehmann read the chlorpromazine papers in his bathtub in 1953, published the first English-language clinical study on the drug, and helped end the asylum era — then spent his later years warning that the revolution he started had produced cookbook psychiatry. This episode works through his biography, the science, and the black-and-white patient interview films that keep drawing mil...

Why Your Toddler Dunks Crackers in Water 12.10.2026

A fifteen-month-old drops a cracker into his water cup, stirs it, drinks the cloudy water, then eats the cracker. His parents call it raccoon behavior. Pediatric feeding specialists at Solid Starts call it normal exploration — and the research suggests they're right. This episode digs into what's actually driving the behavior: why teething turns out to be the weakest explanation, how the Infant an...

Splitting One Camera's Audio for a Baby Monitor 12.10.2026

Daniel has an IP camera in his son's room doing double duty — Frigate watches the video, but he also wants a continuous audio line piped to his phone so a cry wakes him up. The camera won't hand out an audio-only feed, so something has to split the audio off the RTSP stream. This episode works through the architecture: why go2rtc beats Frigate's embedded restream, how to fan out one camera connect...

The Women Who Were Computers Before Computers Existed 12.10.2026

Before "computer" meant a machine, it was a job title — held for centuries by people, and by the 1940s, mostly by women. This episode reconstructs the actual desk: pre-printed forms, mathematical tables, colored pencils, and mechanical calculators with hand cranks. From the WPA's Mathematical Tables Project, where one or two people in a 450-person workforce could do division, to Los Alamos, where...

Grey Rocking Meets OPSEC: A Family Firewall 12.10.2026

Grey rocking and information restriction are the two most-recommended tactics for people stuck with a toxic parent—yet the phrase traces back to a single 2012 blog post with no clinical research behind it. This episode asks whether the underlying problem was already solved elsewhere: in intelligence work and cybersecurity, where need-to-know, OPSEC, and firewall policy decide in advance what gets...

How Multi-Agent AI Simulations Keep a Shared World State 12.10.2026

What actually holds a simulated world together when multiple AI agents act inside it? This episode opens the repos on three frameworks that answer the question completely differently. Concordia from Google DeepMind makes world state a first-class Game Master component — a plain Python dict whose contents are authored by the model at every step, with a SQLite/Postgres storage protocol that ships as...

Fire Alarms in 40-Story Towers: What Goes Wrong 12.10.2026

A 28-storey walk down a stairwell because someone burnt toast — that's the everyday failure mode of high-rise fire systems. This episode walks the full chain: ionization vs. photoelectric detection, aspirating smoke detection, the addressable fire alarm control panel, wet/dry/pre-action/deluge sprinklers, stairwell pressurization and stack effect, elevator recall, and phased evacuation. Then the d...

Why the Sterile Cockpit Rule Took 7 Years 12.10.2026

On September 11, 1974, Eastern Air Lines Flight 212 crashed 3.3 miles short of the runway in Charlotte. The cockpit voice recorder captured the crew discussing Watergate and used cars. The NTSB recommended a sterile cockpit rule six days later. It took the FAA seven years — and dozens more deaths — to write it down. This episode traces the rule from 14 CFR 121.542 through the crashes that kept re-...

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.