Modal

The complete tour of the pipeline that makes the show, stage by stage, from the send form to publishing, including the new eight-turn batched voice decode.

Six thousand episodes, one human in the loop, and a Modal bill that keeps growing. A behind-the-scenes update on the podcast.

Can SearXNG, Crawl4AI, and an open-source aggregator really replace a commercial search API? Yes — with a very large asterisk.

You fine-tuned an open-weight model. Now how does anyone actually talk to it? Dedicated GPUs vs serverless inference, and the math that decides it.

Security boundary or Linux workspace? The word "sandbox" quietly split in two — and the split explains where agents actually run now.

Daniel wants to fine-tune DeepSeek Flash 4.1 on edited podcast scripts. The hard part isn't training — it's surviving the next release.

What does a queue look like when your process is disposable? Two queues, one cron tick, and a 50% batch discount.

We open the books on our AI-generated podcast: $200/month costs, 180K plays, zero sponsors. Who should we pitch?

How to build an agent that monitors and fixes other agents in production — without the hype.

How Modal, RunPod, and other platforms handle container builds, caching, and versioning under the hood.

Why your dedicated GPU burns 130 watts doing nothing, and how serverless platforms cut energy waste by more than half.

Stop rebuilding your entire site for every single content change. Here's how debouncing and caching save time and money.

A practical guide to choosing between Modal, RunPod, Nebius, and Baseten for AI workloads.

Was money ever really "backed" by gold? A deep dive into the unstable history of the gold standard and what actually gives money its value.

The shekel’s dramatic rise against the dollar—hitting a 30-year high—reflects a mix of geopolitical shifts, tech inflows, and global dollar trends.

Hilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf...

Israel's population is shifting dramatically. The Haredi and Arab sectors are rising fast, reshaping the economy, military, and national identity.

How the CIA and State Dept slice 195 countries into bureaucratic boxes—and why that creates dangerous seams.

How a government board tries to standardize Hebrew while the public invents words on the fly.

Discover why the Hadza hunter-gatherers don't entertain babies—and how letting your child observe real life can reduce parental burnout.

We break down the world's most liquid currency pairs, from the Euro-Dollar heavyweight to the Swiss Franc safe-haven.

We pulled back the curtain on the tech stack behind our 1,858th episode. From Gemini to LangGraph, here’s how we automate quality.

Why armies pour concrete to build fake cities instead of just using VR.

Inside the three-hour, 24-voice virtual conference that stress-tested AI-generated geopolitical conflict.

Why listening to AI conversations beats reading dense PDFs, and how serverless GPUs make it cheap.

Herman reveals his secret DJ life and debuts 9 AI-made tracks from Suno. Full songs, personal stories, and a GPU conspiracy theory.

A sloth's visceral fear of its own cousin reveals how animal brains detect "wrongness" without recognizing species.

Discover how model distillation transfers "dark knowledge" from massive AI giants into tiny, efficient models that live in your pocket.

Stop waiting for containers to warm up. Discover how Modal is reinventing GPU infrastructure to eliminate friction in AI development.

Peek behind the curtain of a 2026 AI podcast, from agentic workflows to maintaining production during global conflict.

Discover how Switzerland manages the invisible infrastructure of global trust through the technical "protecting power" mandate.

Modern defense relies on tired humans. Discover how militaries use circadian science and biometric data to fight the "vigilance decrement."

In a world of synthetic attribution and automated proxies, the truth is becoming a relic of the past. Explore the new era of deniable statecraft.

Explore the neurobiology of power, from the rare "short sleep" gene to the psychological endurance required to manage the weight of the world.

As strikes hit the IRGC's financial backbone, we explore the crumbling "Ring of Fire" and the future of Middle Eastern security.

Could your next apartment be 60 feet underground? Explore the tech, health, and costs of moving our cities below the surface.

Peek under the hood of My Weird Prompts to see how Gemini, Modal, and multi-agent systems are scaling this automated show to the next level.

How do small teams run massive AI models without $50,000 chips? Corn and Herman dive into the hidden plumbing of serverless GPU providers.

Should you use a fleet of cheap GPUs or one powerhouse? Learn the math behind serverless GPU costs, cold starts, and batching efficiency.

Herman and Corn dive into the mechanics of neural text-to-speech, exploring how AI masters human prosody and the "average voice" accent problem.

Unleash cloud superpowers! Edit locally, render remotely with AI-accelerated GPUs like NVIDIA A100s.