My Weird Prompts

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...

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...

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...

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...

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...

When Hebrew words are written in Latin characters inside otherwise English text, standard language identification fails: it returns the dominant label and the Hebrew vanishes. This episode works through the terminology (LID, CS-LID, transliteration, diacritization, G2P, text and script normalization), why romanized Hebrew defeats script-based heuristics, and what the literature actually offers — M...

Daniel has a working podcast pipeline: a language model writes scripts, retrieval tools feed it, and text-to-speech reads it out. But the occasional Hebrew word keeps breaking things, and the pipeline itself is trapped in his head. This episode digs into two questions at once — how to handle Hebrew code-switching in TTS, and how to package a chained AI workflow so it survives past the project that...

Android keyboards quietly accumulate months of your typing habits — your email address, your common phrases, your personal words — and lock most of it inside vendor cloud silos you can't export or back up. This episode unpacks how the components actually work under the hood: the InputMethodService plumbing, the learned frequency model, the surprisingly portable UserDictionary, and the two very dif...

When you connect ChatGPT's email plugin to a workspace address and a Gmail address, you tick a few scope boxes and everything just works. But what's actually happening in that moment — and who holds the credential that sends your mail? This episode walks through the OAuth 2.0 authorization code flow with PKCE, explains why you never see a token (it isn't yours to see), and untangles the difference...

A listener with functional dyspepsia asks why dopamine-blocking drugs (like sulpiride and metoclopramide) kill his nausea but leave him exhausted the next day — and why his daily ADHD stimulant never makes him nauseous at all. We trace the area postrema, the brain's blood-barrier-free chemoreceptor trigger zone, and explain why nausea and vomiting aren't the same thing, why D2 blockade is both the...

You pass a language ID to a multilingual TTS model, and every word in that utterance obeys it — including the ones that belong to a different language. That's why "Shabbat" sounds fine and "pinui binui" sounds like a bad impression. This episode unpacks a listener's proposed pipeline for code-switched speech: detect the Hebrew words written in Latin characters, map them to Hebrew script, and re-sy...

Daniel has been replacing typing with voice for two years, and moving from Whisper to Parakeet V2 on Android was a massive step up. But when your dictation pipeline chains a voice activity detector, an ASR model, and one or more cleanup models, how do you know it's actually working — or is the phone just unusually idle? This episode walks the full chain stage by stage: why ASR models are deliberat...

Daniel is sick in bed and has decided the podcast needs a rebuild: bring back audio prompts, add follow-up questions, and give him a push-to-interrupt button so he can grab the floor mid-episode. He thinks the button is the hard part. The research says it's the opposite — turn-taking primitives like push-to-talk have been standardized since walkie-talkies, while the live full-duplex version he's i...

A listener named Daniel asked two questions: who models technology as something playful rather than something to be mastered, and how do you keep the magic when deep technical work stops feeling fun? This episode works through both — comparing Linus Torvalds' invisible, load-bearing infrastructure with Linus Sebastian's filmed, messy process, and examining what actually makes on-camera camaraderie...

Daniel wanted a notification whenever a pigeon landed on his balcony, and he was ready to buy a TPU and hunt for a species-ID model on Hugging Face. Turns out Frigate's default model already has bird as a built-in class, and the leftover work is entirely in configuration. This episode walks through the actual engineering: why YOLOv9-tiny at 320×320 beats a bigger model on a small distant bird, how...

Daniel wants dictation-first speech-to-text running entirely on his phone, and after two years of trying, Whisper still isn't it. NVIDIA's Parakeet family keeps winning — and surprisingly, the English-only v2 beats the multilingual v3. This episode unpacks the three dials that actually matter when running ASR on a phone (version, size, and quantization), why streaming models fall apart on multi-mi...

OpenAI is retiring Custom GPTs, and the migration path has a hole in it: custom Actions don't transfer. This episode walks through what a Custom GPT and its Actions actually are — the system prompt, the lightweight file store, the auth methods, the OpenAPI schema, the TLS and header constraints — and then lays out the published retirement timeline, including the December 11 date for affected Enter...

A listener wrote in with two building-temperature puzzles that seem to contradict each other: a parking garage four floors underground in a hot country during wartime was unbearably hot, while a concrete core on the twentieth floor of a residential tower—buried inside the building, no sunlight—roasts every summer. What actually determines temperature at different heights and depths in a building?...

What actually ends a friendship when politics gets involved? This episode starts with Ed Sheeran's rough week — pulling Macklemore from his tour over anti-Israel remarks, then losing friends and relatives over the decision itself. From there, a listener's story takes over: an Irish Jew who ended a friendship with someone who had attended his wedding in Israel, then went home and posted that all Is...

The bland food rules you grew up with are being formally retired, and the mechanism behind a stomach bug explains why. But there's a second layer: for anyone living with bile reflux gastritis after gallbladder removal, fasting does something specific and unpleasant. This episode works through what viral gastroenteritis actually does to the body, why BRAT is no longer recommended, what to eat inste...

When Israel grants a developer extra building rights through pinui binui, the project's profit is appraised and capped — the state knows it just handed over value created by a planning decision. When the government cuts tariffs, reforms standards, opens parallel imports, or introduces port competition, the importer's landed cost drops and nobody asks where the savings went. This episode compares t...

A viral clip claims two air-gapped machines can talk through CPU heat, and technically that's true — BitWhisper demonstrated it in 2015. But at one to eight bits per hour and a range of forty centimeters, the demo barely moves a toy missile launcher. So why does the air-gap exfiltration literature keep growing? We walk through Dr. Mordechai Guri's Offensive Cyber Research Lab at Ben-Gurion Univers...

The stereotype of the anxious, overanalytical Jewish personality is persistent enough that it feels like common knowledge. But where did it actually come from? Not from outside hostility, as it turns out — the neurotic Jew as a clinical category was built largely by Jewish psychoanalysts, starting with Freud and his circle in Vienna. This episode traces that origin story, then asks the harder ques...

A fifteen-month-old has become intensely, specifically mom-focused — and it started right after a daycare transition and a long grandparents stay. Is this normal, does it pass, and can the other parent actually do anything about it? This episode walks through the attachment science behind why less mom-time can produce more clinging, not less, and why the pattern becomes self-reinforcing once dad's...

Not every model is trying to talk to you. This episode looks at discriminative models — the quiet, non-generative side of the Hugging Face ecosystem that reads text and returns labels, probabilities, and decisions. Starting from Daniel's point that "non-text-generating" is a misnomer, we dig into two very different model cards: Nox, a 4.2B decision model from the Semantic Router project that retur...