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...
Vizitează neapărat site-ul podcastului și susține-i creatorul: myweirdprompts.com
Autor
Daniel Rosehill
Categorie
Site-ul podcastului
Cel mai nou episod
22 nov. 2026
Unde asculți?
Podcasturi în aplicație Replaio Radio În curândPodcasturile ajung în curând în aplicație. Instaleaz-o acum și fii primul care descoperă o abordare complet nouă a podcasturilor
Episoade
Sloth Leaf Medicine: What's Real and What Isn't 11.10.2026 21:56
Can a healing tradition exist without anyone writing it down? This episode gives sloth leaf medicine the serious treatment it keeps being denied: the Cecropia cornerstone and its real anti-inflammatory pharmacology, the six-to-twelve tree rotation as a delivery protocol, thirty-day digestion as a dosing mechanism, and mother-to-infant leaf sampling as the only transmission channel a solitary anima...
The Laminated Card Doctrine 11.10.2026 20:57
We've been reaching for the same object every time we want to make a point about doing something properly, and a listener finally called us out on it. So this episode is the honest audit: what lamination actually is, what it buys you, and whether there's a real technical case underneath the habit. It turns out the strongest evidence isn't about plastic at all — it's about checklists, starting with...
Who Actually Builds a City's Housing Crisis? 11.10.2026 30:01
Jerusalem keeps building, and residents keep getting priced out. This episode works through an argument that the city's callousness toward its own residents isn't a character flaw — it's fiscal design. Residential Arnona doesn't cover the services those residents consume, commercial property pays roughly four times more per square meter, and the city runs a deep operating deficit. Put those togeth...
Abliteration: How $5 Undoes a Model's Guardrails 11.10.2026 27:20
Open-weight models ship with safety training baked in, and thousands of people quietly take it back out. This episode traces the technical arc from a single paper finding that refusal lives in one direction of activation space, through a $5 rank-one weight edit, to Heretic — an AGPL tool with 34,000 GitHub stars that automates the whole process and outperforms skilled human operators. Along the wa...
When Citizen Engagement Becomes Paperwork Theater 11.10.2026 23:17
A Jerusalem resident spent a decade watching objection processes collect hundreds of signatures and change nothing. It turns out planning scholarship has been documenting this since 1969 — and it has four competing names, none as famous as "greenwashing." This episode traces the vocabulary from Arnstein's ladder of citizen participation through participation-washing, engagement theatre, and partic...
Why Your USB-C Charger Won't Talk to Cheap Devices 11.10.2026 19:35
Daniel has a 300W GaN charging brick with ten ports, and one of them refuses to charge his pocket speaker. USB-A works fine. USB-C to USB-C just makes the light flash red. Is the speaker damaged? Did the charger fry it? Not even close. This episode unpacks the two completely different philosophies behind USB-A and USB-C power delivery: one is a dumb pipe that hands out five volts unconditionally,...
Homebox Fork's Two Backend Scripts Need a Real Job Runner 11.10.2026 24:27
Daniel's Homebox fork added two backend scripts the upstream project was never designed to host: one converts new images to WebP and rewrites database references, the other sends images through a vision model to extract serial numbers without overwriting existing data. Both are incremental and both are deferred so the fast path stays fast. The problem is what runs them. Upstream Homebox ships a ba...
Scraping AliExpress Specs: Selectors, Agents, or Neither? 11.10.2026 22:52
Daniel has a home inventory system that tracks where things physically are, and he wants to add a snapshot function: save an AliExpress URL, pull the page, keep only the technical sheet. No reviews, no price. The obvious plan — define the divs, extract them — runs into a problem that has already happened: AliExpress product pages are client-side rendered, the inline params object is now an empty o...
Fine-Tuning Parakeet for Um-Free, Hebrish Speech 11.10.2026 27:36
Daniel wants to bend Parakeet to his will: strip the ums, catch niche words, and handle the Hebrew he sprinkles into his English. He's done this before with Whisper, so he knows the shape of the job — but Parakeet is a different animal. This episode walks through what Parakeet TDT 0.6B v3 actually is, why a small model is a better inference candidate but not an easier fine-tune, and the real workf...
Toddler Meltdowns After Daycare, Explained 11.10.2026 22:54
Your toddler is a delight all day at daycare, then melts down the moment you arrive for pickup. It has a name — after-school restraint collapse — and there's real cortisol research behind it. This episode digs into the Drugli 2023 study of 113 toddlers, the Ahnert 2004 cortisol findings on fifteen-month-olds, and what attachment research says about why kids save their worst behavior for the people...
When Asking About a Leaky Roof Ends Your Lease 11.10.2026 29:48
Israel's Fair Rental Law bars landlords from waiving tenant protections, caps deposits, and makes lock-changing a criminal offense. So why do tenants with flawless records still move every fourteen months? This episode unpacks the gap between a protected lease and a protected home — rent control that was never written in, a 2011 eviction that put 400,000 people in the streets, and why institutiona...
Four Pocket Players That Won't Sell You a Device Today 11.10.2026 34:14
Daniel wants an iPod-shaped appliance that holds a hundred gigabytes of podcast archive, plays it over Bluetooth at the beach, and never sends him a notification. The hardware exists — Mono, Fonix One, Sudo, and DuRoBo Krono are all building some version of it — but the market is stuck between waitlists, deposits, and concept reveals. This episode works through the real fork in the build: an ESP32...
Inside a 15-Month-Old's Head: What Ezra's Brain Is Doing 11.10.2026 27:24
Ezra is fifteen months old. He says "Dada," "Mamma," and "Up." He's taken a few faltering steps. And he will sit on the floor handling a wire stripper for twenty minutes. In this episode, we triangulate three angles — the CDC's developmental milestones, the neuroscience of infant attention, and one father's observations — to paint a vivid picture of what's actually going on inside a toddler's head...
What Shabbat Does to Your Brain That Sleep Can't 11.10.2026 20:51
The jackhammer returns at 7 a.m. Sunday, and with it the whiplash Daniel wrote in about: 25 hours of quiet, then the world snaps back. This episode digs into what that quiet day is actually doing at the level of the brain — and why sleep is only part of the answer. Drawing on Sabine Sonnentag's research on psychological detachment, a 38,000-person meta-analysis, sleep-timing data from 473 older Is...
One Show, Eighteen Feeds: Apple's Duplicate Content Rules 11.10.2026 21:06
Daniel wants to submit eighteen topic-channel RSS feeds of a single podcast to Apple and Spotify. The problem: Apple's data model has shows and episodes, nothing in between — so eighteen feeds isn't eighteen views of one show, it's eighteen shows. This episode walks through Apple's duplicate content guidelines (1.9, 1.4, 4.2), the RSS requirements that make duplicate enclosure URLs silently ignore...
Inside Cloudflare's Bot Check: TLS, JA4, and the Sand-Timer 11.10.2026 30:01
That grey page with the spinning circle — "Checking your browser before accessing" — hides a two-layer detection system that has usually made up its mind before the page even renders. This episode walks through how Cloudflare's anti-bot machinery actually works: the TLS handshake fingerprints (JA3, and how Chrome 110 broke it, and how JA4 fixed it), the HTTP/2 SETTINGS-frame fingerprint Akamai fig...
Who Can Actually Train an LLM From Scratch? 11.10.2026 32:55
Daniel asked a simple question: how many organizations worldwide have trained a large language model completely from scratch? The answer turns out to be two questions wearing the same coat. At the frontier, the count is unverifiable — labs have stopped disclosing training compute. At the 1–70B parameter scale, the count is rising fast as sovereign initiatives in Korea, Switzerland, Brazil, Denmark...
Slow Labs, Fast Ships: What Release Cadence Actually Tells Us 11.10.2026 28:34
Everyone assumes the careful labs release slowly and the hype-driven ones ship constantly. The data says the opposite. Drawing on Suprmind's AI Models Index and ARK Investment Management's frontier-gap analysis, this episode digs into real release medians across Anthropic, OpenAI, Google, DeepSeek, Mistral, xAI, and Meta — and finds a lab most associated with pacing is actually the fastest shipper...
Routing AI Models: When 3 Rules Beat a Trained Router 11.10.2026 32:28
Daniel wants to stop randomly assigning podcast episodes to AI models and start routing them intelligently. But the routing literature has a trapdoor: the famous "85% cost reduction" headline compares learned routers against always using the most expensive model — a baseline nobody with a budget actually runs. This episode walks through the router toolbox (RouteLLM's matrix factorization, RoRF's r...
Building a Scorecard for Our Own AI Writers 11.10.2026 32:57
Every episode of this show is written by an agentic pipeline, and for most of the archive that script-writing agent has been DeepSeek V4, with Gemini, Claude, and a stretch of OpenRouter randomization in the mix. So when Daniel asked how to build a bespoke benchmark for it, the answer couldn't be vibes and one careful listen. This episode works through the three things he wants measured — mid-epis...
ADHD Is Not One Thing: What the Data Says 11.10.2026 21:58
Two people with the same ADHD diagnosis and the same medication can struggle with entirely different parts of life — and the research explains why. This episode digs into what adults with ADHD actually struggle with, why there's no single ranking, and how wide the variance really runs. From a 2026 study showing ADHD symptoms account for 42% of functional cognition variance (with emotional distress...
Spaghetti Hands: The Science of First Steps 11.10.2026 28:36
Daniel's fifteen-month-old son Ezra is taking his first wobbly steps, and his grandmother wants to hold his hands and walk him along. Is that helping, or is it wasted effort? This episode digs into the surprising research on supported walking: which kinds of help actually predict earlier independent walking (and which kinds do absolutely nothing), why "spaghetti hands" beats full hand-holding, and...
Why Quiet Weekends Make the Jackhammer Worse 11.10.2026 31:13
Every Saturday, the construction site next to Daniel's Jerusalem apartment goes quiet — and every Sunday at 7 a.m., the jackhammer feels worse than it should. He has ADHD, and the noise derails his morning planning, his focus, and even his spelling. What's actually happening in his brain? This episode digs into the neuroscience of habituation and sensitization, the spacing paradox (why crammed-tog...
Who Actually Competes With Hugging Face? 11.10.2026 27:00
Hugging Face hosts 2.96 million public model repositories — and 85.6% of them have fewer than 200 lifetime downloads, while 1.5% of repos account for 99.2% of all downloads. So what are ModelScope, Kaggle Models, and Ollama's library actually for, and when would a team pick one over the Hub? This episode works through the catalog, community, licensing, and deployment differences, including the fac...
What "Free of Ordnance" Actually Means 11.10.2026 30:37
Gary Toombs spent sixteen years as a Royal Engineer bomb disposal officer and now directs land release and EOD operations for Humanity and Inclusion. In September he was one of seven HI staff awarded the UK's Humanitarian Medal — the first EOD team ever to receive it. But the ceremony implies a finished job, and the ground truth is the opposite. This episode unpacks what "declaring an area free of...
Podcasturi asemănătoare
Replaio nu este editorul podcasturilor; numele emisiunilor, coperțile și materialul audio aparțin autorilor lor și sunt distribuite prin fluxuri RSS publice