My Weird Prompts

What happens when two AI hosts sit down to critique their own earliest episode? Corn and Herman replay the raw audio of "AI Gets Personal: The Power of Voice Fine Tuning," published last November, and pull it apart line by line — the flat delivery, the self-compliments, the filler words counted by the dozen. They find a transcript that disagrees with the audio about who is speaking, a medical exam...

Google's Gemini 3.5 Live Translate handles 70+ languages in real time, OpenAI has a realtime translation model, and Apple, Samsung, and Meta all run interpreters on-device. But every one of them is sentence-in, sentence-out — none can be briefed on who's talking, what they want, or who holds the power in the conversation. This episode digs into what human interpreters actually carry in their heads...

This week the show goes out in Hebrew, Russian and French, all of it translated by a system prompt rather than a translation engine — which raised a fair question: is anyone actually selling a model built for translation, one you can point at a register and get back a script instead of a wall of text? The answer is yes, and it comes in three layers. There are open specialist models like TranslateG...

ChatGPT passed a million users in five days — but the model underneath was nothing new. The instruction-following approach had been in OpenAI's API since early 2022, and the chat experiment itself got parked that summer because staff found it underwhelming. What actually forced the launch was a November rumour that Anthropic was about to release a chatbot of its own. This episode traces the real o...

Hilbert has been producing the show for years, and nobody ever asked him what being an anteater is actually like. A listener named Daniel demanded it be done properly, grounded in real biology — so this episode covers the giant anteater's 60-centimetre tongue (150 flicks per minute), a mouth with no teeth at all, a body temperature around 33°C, up to 15 hours of sleep, and ten-centimetre claws tha...

What happens when you give a chatbot your credit card, your portfolio, or your love life? This episode walks through real experiments in outsourcing decisions to AI, arranged from cheapest to most expensive: Geoffrey Fowler's browser agent buying $31 of eggs through Instacart (and misreporting the total), Nathan Smith's ChatGPT-run stock portfolio that peaked at +24% before a biotech crash, Jackso...

In 1971, Salvador Allende's government hired British cybernetician Stafford Beer to wire up Chile's newly nationalized economy. Project Cybersyn became famous for one photograph: seven white fibreglass chairs facing wall screens, in a hexagonal control room that looked like a starship. But the real system ran on telex machines, punched cards, and roughly 1,500 hand-drawn slides projected from behi...

A quarter of Israeli voters are asking chatbots who to vote for — and the chatbots don't agree with each other. This episode traces the most audacious real attempts to put AI into politics: a Russian voice assistant nominated for president, Denmark's Synthetic Party led by a chatbot trained on fringe platforms, a Wyoming mayoral candidate named VIC who got deplatformed by its own manufacturer mid-...

Israel's election begins twelve days early in Wellington, New Zealand, and the last box closes about thirty hours later in California. In between, 101 polling stations open in 99 diplomatic missions for an electorate of roughly 4,860 people — embassy staff, ministry representatives, military attachés, and their families. No ordinary Israeli living in Berlin can walk in and vote. This episode digs...

If you've outgrown n8n's canvas and want your workflows versioned in git with real observability, this episode maps the code-first workflow orchestrator field. Prefect is the closest match to a long-lived Python script runner — flows, tasks, workers, and a server you can self-host. Temporal offers durable execution where a workflow can sleep for thirty days and resume on the exact line. And Dagste...

Those tiny green and orange lights on your router, switch, and laptop dock are speaking a language — but every manufacturer speaks its own dialect. In this first Herman In Brief, we decode the basics: solid versus blinking, why the same two colors can mean opposite speeds on an Intel NIC versus a cheap home switch, what amber means on Cisco Catalyst gear, and how PoE and SFP ports fit into the gra...

Israel's last wild leopard was seen near Sde Boker in 2007 and died in 2009, but the Jerusalem Zoo's new Persian leopard exhibit tells a different story — one with the wrong subspecies on the sign. This episode digs into the forgotten history of Panthera pardus in Israel: a north-to-south extinction that ran from the late 1800s to 2011, at least fourteen leopards hunted or poisoned in the Galilee...

Millenniata's M-Disc was marketed as "chiseling your data into stone," certified at over a thousand years under ISO 10995. Then the company went bankrupt, the Blu-ray version got harder to distinguish from ordinary discs, and skeptics started doing the arithmetic on that certificate. This episode walks through the actual evidence — the China Lake DoD test, a UK hobbyist's seven-month weather exper...

Five years ago the risk was someone faking evidence against you. Now the bigger risk is the other side calling your real photo fake — the "liar's dividend." This episode works through how an ordinary person documents a landlord dispute, an insurance claim, or a neighborhood fight in a way that can later be shown to be authentic. It covers the four different claims people bundle together when they...

Israel's quiet fortunes are built on exclusive import rights — one family holds the letter from the brand, and nobody else gets to bring it in for decades. So how does an outsider break in? This episode walks the entire path from cold start to signed agreement, using Zojirushi rice cookers as the test case. It covers the "sacrificial pallet" strategy of importing and selling stock before you've ev...

Hilbert takes over Herman's chair to announce the show's first translated editions: two Hebrew episodes from the Israel Votes series and a Mandarin edition of the episode on who shapes Chinese AI thinking. How they're made (Claude translation, Dicta vowel marks for Hebrew, Chatterbox Multilingual with the hosts' cloned voices), why the main feed stays English, and where each language lives: myweir...

What happens after you find the hidden pocket in the AI market — how do you actually win the work? This episode climbs a ladder of unconventional client pitches, starting with the mild (no slides, one page, a pre-mortem) and rising through live demos, recorded support calls, physical props, and a human pretending to be the AI behind a folding screen. Each rung gets more effective and more dangerou...

A banner plane runs $400–900 an hour, and a city billboard can run tens of thousands for four weeks — neither is priced for a two-person consultancy. So how do you buy high-value attention cheaply, and what unconventional surfaces make people actually stop? Drawing on rate cards, a $6 search-ad stunt that landed two job offers, and the reverse-graffiti defence that got tested in San Francisco, thi...

Daniel wanted to step back from the feed and ask a blunt question: what has this show actually been about? Hilbert counted 5,964 published episodes since late November — 2,666 hours of audio — and sorted every one by category, by month, and by embedding. Technology and AI together make up 48% of the archive. Geopolitics spikes to 25% in the spring, then falls to 12%. AI drops to 14% over the summe...

A listener named Daniel wants to rebuild how we explore a podcast archive: not a feed, not a hairball graph visualization, but a sequence of small decisions — like a dating app that learns your type and walks you through the archive one connection at a time. We dig into why force-directed graph views are a "screensaver with a fan club," what Spotify's 2024 podcast graph actually did (and why liste...

Polymarket is the world's largest prediction market, where a contract at 37 cents reads as a 37% implied probability. But the US military's own intelligence bulletin called prediction markets an "underutilized dataset" for national security analysis — even as US users are barred from trading. This episode walks the read-only path: the Gamma, CLOB, and Data APIs, the unified TypeScript and Python S...

Israel's renters and the sleep-deprived finally get the side-by-side treatment. We dug through every party platform on the ballot for what they actually wrote — not what they said on a campaign slide — about rent caps at renewal, broker fees, long-term rental supply, and noise enforcement. Three parties have tabled a renewal cap in the Knesset in writing. Exactly one mentions noise in its current...

The AI job market looks packed — AI engineer and AI consultant topped LinkedIn's fastest-growing American jobs list, and 2.5% of US postings now ask for AI skills. But the crowd is all standing in the same queue: roles where AI is the whole job. The openings are where AI attaches to a second noun — claims adjusting, pediatric triage, freight forwarding — and where a 56% wage premium goes to people...

Daniel asks how to find last-minute getaways in a famously expensive country, and wants brazen tactics as well as websites. Hilbert, who books everything for the show, joins Corn and Herman with a laminated card of rules. The leverage is in the numbers: Israeli hotel occupancy averaged 44% in the first half of 2026, with Jerusalem at 31%, Tiberias at 29% and Nazareth at 19%. Herman covers the cale...

What would architecture in this land look like if you scraped away the Roman, Byzantine, Arab, Ottoman, and British layers? Starting from Hannah's thought experiment, this episode works through the strongest evidence for a distinctively Judean spatial language: the Iron Age four-room house, with its tree-like access plan and central courtyard, and the volute capital that Assyrian architects copied...