My Weird Prompts

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...

A respectable burial was once something you aspired to — not something you assumed. This episode traces how that changed. The stigma of the pauper's funeral turns out to be a modern invention, dating to the shift from inherited status to acquired wealth. We follow the history from Natufian stone graves to Roman puticuli to the Paris Catacombs, then turn to the present: potter's fields like Hart Is...

Everyone in Israel knows the word "peripheria" — the periphery. But it isn't a geographic term. It means "not the center," and the proof is that Jerusalem itself once carried development-town status. This episode traces how a three-year-old state built that category in the 1950s, housed over 200,000 new immigrants in transit camps, and hardened an ethnic correlation that never dissolved. Then it f...

Carmei Gat is a planned neighborhood on the northern edge of Kiryat Gat, in Israel's Southern District, and it's become an unlikely magnet for English-speaking immigrants. This episode digs into what it actually is, where it came from, and why buyers are choosing a Negev development town over the traditional Anglo strongholds of Beit Shemesh and Jerusalem. From Israel's first umbrella agreement —...

When someone asks how open source enthusiasts combine two AI models into a hybrid, the intuitive answer — snap the attention heads together — turns out to be wrong in an interesting way. Heads are a granularity of control; layers are the unit of assembly. This episode unpacks what a transformer head actually is, from the query-key-value subspaces inside multi-head attention to the strange finding...

In 2022, researchers defined an ability as "emergent" if smaller models lack it and larger models have it — meaning you couldn't have predicted it from the smaller models you already had. Since then, a fierce debate has unfolded over whether these jumps are a real property of the models or an artifact of the metrics we choose. This episode works through the strongest arguments on both sides, from...

Treasury Secretary Scott Bessent threatened to cut off any foreign company that fuels, lands, or sells tickets for Iranian airlines — "you will be cut off from the dollar system." This episode unpacks what that actually means: how CHIPS and Fedwire make the dollar a system rather than just a currency, why currency-based jurisdiction lets OFAC reach transactions with no American party, and why Iran...

The U.S. Space Force became its own branch in 2019, but the military had been flying satellites since the late 1950s — so what actually changed? This episode digs into the physical inventory Daniel asked about: missile-warning satellites, military SATCOM, GPS, space-domain awareness, and the planetary-scale ground infrastructure that most people never see. It also goes international, comparing the...

Pituffik Space Base sits 1,500 kilometers from the North Pole on Greenland's northwest coast — the northernmost installation in the entire U.S. Department of Defense. It's also reportedly the most expensive overseas base the United States operates, at over $100 million a year, roughly ten times the cost of an average Air Force base. So what does it actually take to keep several hundred people, a 1...

Large language models are, at their core, language technologies. So why did the people who study language for a living become peripheral to building them? This episode traces the hidden linguistic DNA inside the transformer architecture — from Jakob Uszkoreit's parse-tree insight to the raising-versus-control distinction that models seem to have internalized without being taught — and asks what go...

Daniel noticed "failure mode" showing up everywhere in our own scripts, and wondered what other verbal tics are hiding in a corpus of thousands of episodes. There's no off-the-shelf LLM tick detector — but there is a whole discipline built for exactly this. This episode walks through corpus linguistics tooling: quanteda's keyness function, corpkit's subcorpus slicing, pycorpdiff's changepoint dete...

Daniel noticed certain idioms keep surfacing in the show's dialogue, and system-prompting the problem away made it worse — the model started using the banned phrases more. This episode works through the mechanics of why prohibition prompts fail, why multi-agent correction passes leak feedback into the final text, and why regex produces ungrammatical holes. The fix is a small text-in-text-out langu...

Text normalization is the invisible layer that turns written text into something a TTS model can actually speak: "1,234" becomes "one thousand two hundred thirty-four," "Dr." becomes "Doctor," and "2026" stops being a string of digits. It's also the layer this podcast doesn't have, which is why acronyms and numbers have been hand-patched for months. This episode walks through the vocabulary — text...

If a tool runs inference on your device, it has no legitimate reason to touch the network. That makes outbound traffic from a "local" AI tool one of the few clean security signals left — and it's exactly the signal attackers work hardest to avoid. This episode traces keystroke capture from the permission prompt down to the SQLite file on disk, then follows the data through the exfiltration chain:...

A thermostat looks like the simplest device ever built: sensor, set point, switch. But the bleeping battle between an IR blaster and an air conditioner is really a lesson in control theory — bang-bang controllers, deadbands, integral windup, and models that forecast accurately yet get the sign of a cooling action wrong. From there the conversation widens to buildings themselves: thermal mass as a...

A UK-wide survey of 104 Marie Curie palliative care staff found that 97% had witnessed at least one deathbed phenomenon in five years — an average of 7.7 each. Visions of deceased relatives, terminal lucidity in dementia patients, clocks stopping at the moment of death. And yet a chart audit found only 8.3% of these events ever get documented. This episode works through the research literature on...