Artificial Intelligence
Episodes whose main subject is AI itself: building with, training, evaluating, or debating AI systems. AI used only as a tool for another topic goes to that topic.
#1883: From Juicero to Yik Yak: Startup Graveyard
We revisit 10 failed startups, from a $700 Wi-Fi juicer to an anonymous social app that turned toxic.
#1882: The Hidden Human Labor Behind AI
AI isn't free—it costs billions for humans to label data. See why annotation is the real engine behind models like Gemini.
#1872: The Pinky Promise That Broke Email
SMTP is broken. DMARC is the fix. Learn why your emails might vanish after April 2026 and how to stop domain spoofing.
#1870: Learning to Break Things Safely
Learn how to safely build and test autonomous AI agents using a disposable VPS, Docker containers, and secure networking.
#1866: The Tactical Soda Straw: When Leaders Know Too Much
Leaders see live drone feeds while you see yesterday's news. Here's how wartime intelligence actually reaches the top.
#1864: The Diplomat Who Wears Two Masks
Iran's top diplomat speaks of peace before attacks, then justifies violence. This is linguistic camouflage at its most dangerous.
#1863: Your AI Needs Its Own Email Address
A YC-backed startup is giving AI agents their own dedicated inboxes, moving beyond human-centric email tools to build infrastructure for autonomous...
#1862: Hacker News: The Orange Site That Runs Silicon Valley
It loads in milliseconds, has no ads, and looks like a spreadsheet from 1995. Here’s why Hacker News still dictates what the tech elite thinks ever...
#1860: Building a 24-Agent AI Diplomatic Swarm
Inside the three-hour, 24-voice virtual conference that stress-tested AI-generated geopolitical conflict.
#1858: Multi-Model Agents: The Instruction & Context Gap
Mixing AI models creates chaos. Learn the practical fixes for context windows, tokenization, and output formats.
#1857: The Death of the Dashboard
Why build a dashboard when you can just talk to your backend? Meet the MCP server that runs this show.
#1856: Two AIs Chatting Forever: Why They Go Crazy
What happens when two ChatGPT instances talk forever? They hit a politeness loop, forget their purpose, and spiral into gibberish.
#1855: When AI Makes Game Assets, Who Owns the Art?
From blocky polygons to photorealistic assets, AI is transforming how 3D models are made.
#1854: The Conductor as a CPU
A conductor isn't just a timekeeper; they're a CPU for the orchestra, using high-bandwidth non-verbal signals to unify 80 musicians.
#1851: AI Toasters and Poetic Gym Coaches: Why We’re Drowning in Useless AI
From smart toasters that need Wi-Fi to email rewriters that sound like corporate robots, here are the most baffling AI features we’ve seen.
#1849: When Forum Etiquette Becomes Prompt Engineering
Forget simple chatbots—this is how roleplayers taught AI to remember entire worlds, from 90s MUDs to just-in-time lore delivery.
#1848: Why Cloud Bills Can Hit $100K Overnight
From recursive loops to AI agents spending your money, we unpack the terrifying speed of cloud cost disasters.
#1846: Right-Sizing Your Agent's MCP Toolkit
AI agents slow down when overloaded with tool schemas. Just-in-time usage is the fix.
#1843: Why Is My AI Pipeline Stuck? (Kanban-Style Observability)
Stop digging through JSON logs. See your AI jobs moving on a board, not just server metrics.
#1841: Async Work: Freedom or Digital Surveillance?
Is async work the key to productivity or a trap for total surveillance? We break down the promises and perils of the modern workday.