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...

Bezoek zeker de website van de podcast en steun de maker: myweirdprompts.com

Auteur

Daniel Rosehill

Categorie

Technology

Website van de podcast

myweirdprompts.com

Nieuwste aflevering

2 okt. 2026

Waar luisteren?

Podcasts in de app Replaio Radio Binnenkort beschikbaar

Podcasts komen binnenkort naar de app. Installeer nu en zie als eerste een compleet nieuwe kijk op podcasts

Download het op Google Play Gratis installeren Android bijna 10 mln downloads · beoordeling 4,8 iOS binnenkort

Afleveringen

The Night the Temple Courtyard Glowed 23.09.2026

Every Sukkot, the Temple courtyard filled with towering lamps, torch dances, and all-night music. But what does the earliest source actually claim — and where do the juggling rabbis and impossible light come from? This episode reads Mishnah Sukkah chapter five line by line, tracking how the description of Simchat Beit HaShoeva grows louder with each layer of tradition. We separate the terse, concr...

Why Screen Protectors Bubble Every Time 23.09.2026

Almost everyone has tried to install a tempered glass screen protector, and almost everyone has ended up with bubbles. The frustrating part is that it looks trivial — a flat sheet of glass on a flat sheet of glass — yet it defeats a huge fraction of the population. This episode digs into why. The answer turns out to be a dust-management problem wearing a glass costume: pressure-sensitive adhesive...

When Your Toddler Swallows a Screw 23.09.2026

A fifteen-month-old, a flat-pack wardrobe, and a screw that went missing — that's the scenario a listener wrote in about, and it turns out the answer splits in a way most parents never expect. A screw is a sharp object and gets you to the ER. A small smooth washer gets you a chair and a three-day wait. This episode walks through the actual pediatric foreign-body protocol: the swallow test, the siz...

How Emoji Went From 176 Characters to 3,600 23.09.2026

Emoji didn't start as decoration. In 1999, NTT DoCoMo's Shigetaka Kurita built 176 tiny pictures to carry tone that plain text on a tiny screen couldn't — and named them "picture characters," not after the English word emotion. This episode traces the whole arc: carrier incompatibility, the Unicode Consortium's standardization starting in 2010, the two-to-three-year proposal pipeline, and why the...

Why Your Spreadsheet Mangles José's Name 23.09.2026

Ever opened a UTF-8 CSV in Excel and watched José turn into "José"? That garbled text is called mojibake, and it's the visible symptom of a character set mismatch hiding beneath every keyboard layout, font, and file format you touch. This episode unpacks the three layers people constantly collapse into one — code points, encodings, and graphemes — and shows why the encoding layer being wrong pois...

Why Hebrew URLs Turn Into Percent-Sign Gibberish 23.09.2026

A listener noticed something odd: Hebrew in a URL's domain renders beautifully in the address bar, but Hebrew in the path collapses into six lines of percent-sign hex. It turns out the domain and the path are governed by two completely separate internationalization regimes — IDN and Punycode on one side, IRI and percent-encoding on the other — and only one of them comes with a display mandate. Thi...

Fine-Tuning Parakeet for Hebrew and Your Own Jargon 23.09.2026

Daniel runs NVIDIA's Parakeet V2 on Android for dictation and wants two things: a Hebrew fine-tune, and a personal-vocabulary tune to catch tech jargon and Hebrew loanwords like "makolet." We dig into what Parakeet actually is under the hood — FastConformer encoders with CTC, RNN-T, and TDT decoders, shipped through NVIDIA NeMo — and why its transducer architecture sidesteps the hallucination loop...

When Governments Own the Pipes: Telecom's Open-Access Model 23.09.2026

What if the government owned every fiber line and cell tower, and every carrier simply rented space on the state's pipes? This week we dig into a listener's provocative proposal to centralize physical telecom infrastructure while keeping the retail market fully competitive. We trace the idea back to its real name — open-access networks — and examine the three-layer model that forbids the infrastru...

One Network: Israel's Deregulation and the Case for State-Fiber 23.09.2026

Israel's 2009 telecom reforms forced incumbents to host virtual operators and cut mobile prices by 60–80%. So why not go further — one physical network owned by the state, with every retail provider renting equal access? This episode unpacks that proposal, then tests it against real examples: Liechtenstein's LKW, Singapore's NetLink Trust, Ireland's SIRO, Italy's FiberCop and Open Fiber. The key d...

When AI Edits Your Words: The Off Switch Problem 23.09.2026

Daniel built an AI agent to lightly edit his podcast prompts, and it works. So why does he keep turning it off? This episode digs into the measurable mechanics of AI over-editing — from a 2026 coding-model study showing reasoning models rewrite more by default, to brevity bias and context collapse that erode a prompt across iterations. We walk through the draft system prompt in full, find the brok...

Small Models, Big Guardrails: PII Detection in ChatGPT 23.09.2026

When ChatGPT asks you to approve a tool call, something has already scanned the outgoing data for usernames, addresses, and other PII — and that something is probably a small language model. This episode digs into the "guardian" class of compact models doing narrow, high-volume security work: PII-Tracer, OpenAI Privacy Filter, GLiNER2-PII, and the consistency problem that makes partial detection w...

Writing a Personal Instruction for ChatGPT 23.09.2026

Most advice about custom instructions says make them longer. The evidence says the opposite: a leaner prompt can be functionally equivalent, four and a half times cheaper, and faster to first token — because every added rule dilutes the attention paid to the others. This episode takes apart a real listener's general-purpose ChatGPT instruction line by line, separating what earns its tokens from wh...

Why Number Porting Takes 30 Minutes 23.09.2026

Mobile number porting is a legally mandated right, standardized by 3GPP and enforced in Israel since the mid-2000s. The consumer version is one sentence: disconnect the old SIM and wait thirty minutes. The technical version is a signalling relay, a portability database, and a synchronization problem that has nothing to do with routing speed. We trace what actually happens when a number moves betwe...

When AI Hands Out Your Phone Number 23.09.2026

A single 2015 forum post, one scraped phone number, and a chatbot that confidently hands it to strangers over a decade later. This episode digs into "AI doxxing" — the documented cases where Gemini, ChatGPT, Claude, and Grok surfaced real people's phone numbers — and the uncomfortable mechanics underneath. We trace how a number gets into training data, why one mention is enough, and what labs can...

Who Owns the Antennas? Israel's MVNO Puzzle 23.09.2026

Israel deregulated its mobile market to multiply competitors, but the antennas collapsed into two shared networks — PHI and S-Plus — and virtual operators aren't required to disclose which one they ride. A listener's phone migration saga raises two questions: can you detect the host network from the outside, and do MVNO subscribers get the same service as direct ones? This episode walks through th...

When Login Systems Lock Out Their Own Users 23.09.2026

Daniel bought a data-only eSIM, then discovered the provider's portal only accepts SMS one-time codes — which a data-only plan can't receive. A second case: a switched phone number left him permanently locked out of his Israel Post account, because changing the number required authenticating with the old one. This episode unpacks why these lockouts aren't bugs but failures of imagination, tracing...

Why Salad Is Breakfast in Israel and Punishment in America 23.09.2026

A country that eats chopped salad at seven in the morning, and a country where the same dish signals joyless dieting. How did raw vegetables become the backbone of the Israeli and Turkish breakfast table — and rabbit food in America? This episode traces the Israeli salad from Levantine shepherd's salad to kibbutz dining hall to contested national dish, then builds the global list of cultures that...

Why Tardive Dyskinesia Becomes Permanent 22.09.2026

Tardive dyskinesia affects roughly 20-25% of patients on long-term dopamine-blocking drugs, yet the mechanism behind its permanence is still debated. This episode digs into D2 receptor supersensitivity, the maladaptive synaptic plasticity theory, and why removing the drug often doesn't remove the movement. Then we get into the numbers: how much have second-generation antipsychotics actually reduce...

The Kindle Refund Trick and the Return Policy Arms Race 22.09.2026

A listener's email about Amazon's tightening return policy sends us down a rabbit hole of consumer overreach, from petty market grazing to industrial-scale refund fraud. We trace the spectrum from a single grape at a date stall — governed by nothing but eye contact and shame — to the woman who returned over a hundred Kindle books while reading every one of them, and the wardrobers, home-stagers, a...

Can Anyone Scan a QR Code From a Landing Plane? 22.09.2026

A friend of the show wants to launch a printing business in New York, and his marketing plan involves an airplane towing a QR code banner along the approach path into the airport. We take the idea seriously enough to ask the obvious questions: can a passenger actually scan a code while landing, what are the legal limits around airports and highways, and where does physical advertising in extraordi...

Your News Feed Is Filtering for Failure 22.09.2026

Around 40% of people worldwide now say they sometimes or often avoid the news, up from 29% in 2017. It's not fragility — it's a rational response to a feed that filters for failure. This episode unpacks why every individual story can be true while the composite is a lie, what constructive journalism actually means (it isn't positive news), and how the ad model itself shapes what you're allowed to...

What a Hot Bath Actually Does for You 22.09.2026

Two offhand comments — one about hygiene, one about water use — convinced Daniel that baths were pointless. He's been a shower person ever since. But when he finally climbed back into a tub with frankincense and myrrh salts, sick and achy, he wrote in to ask what the science really says. It turns out the research on immersion bathing is stronger than the folklore ever was, and he was robbed. This...

Open Source's New Map: India, Croatia, Ethiopia 22.09.2026

India has overtaken the US as the largest contributor base to public open source projects, and one in three new GitHub developers now joins from a country that wasn't in the global top ten in 2020. Starting from a Croatian-built offline dictation app called Whisperian, this episode digs into GitHub's Octoverse data: quadrupling developer populations in India, Brazil, and Indonesia, triple-digit gr...

Why Nobody Stops the Candy Bin Grazers 22.09.2026

A grown man reaches into a bin of Haribo at Mahane Yehuda, eats a fistful, and walks on — and almost nobody stops him. This episode uses that small, gross moment as a lens on how social norms actually work: why vendors tolerate the loss, why the rare owner who enforces hygiene gets punished for it, and how descriptive norms quietly eat injunctive ones. Along the way: food-safety microbiology on op...

Small Models, Big Schemas: When JSON Constraints Backfire 22.09.2026

Everyone building agents reaches for the biggest model and wraps every endpoint as a tool. But there's a quieter pattern: tiny text-to-text models doing one narrow structured job. Daniel wrote in asking whether small models doing predictable structured output inside MCP pipelines actually ship in production, or whether everyone just lets a general-purpose model emit tool calls. The answer runs thr...

Luister naar de podcast My Weird Prompts in Replaio

Radio en podcasts in één app - gratis en zonder account. Installeer vandaag nog en mis de lancering niet

Download het op Google Play

Replaio is geen uitgever van podcasts; namen van shows, covers en audio zijn eigendom van hun makers en worden verspreid via openbare RSS-feeds