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.
#4301: How to Channel Trump's Rhetorical Style (Without the Baggage)
Reverse-engineering the linguistic mechanisms behind commanding attention — extracted for everyday use.
#4296: Auto-Splitting AI Threads: Smarter Context Management
How to build a system that automatically detects topic shifts and routes messages to the right thread.
#4282: Beyond the Tourist Trail: Finding Cities Worth the Trip
How to find well-connected cities that aren't overrun with tourists — Bilbao, Gdańsk, Turin, and Plovdiv.
#4274: Fixing Loop-Damaged Podcasts with AI and FFmpeg
Can an AI agent detect repeated audio, generate FFmpeg commands, and overwrite files in cloud storage without breaking RSS?
#4268: When AI Trains on AI: The Model Collapse Problem
What happens when AI trains only on AI-generated content? The answer is model collapse — and it's already happening.
#4267: The World's Most Dangerous Airline and Airspace
Yeti Airlines tops the fatal accident rate. But the real hazard may be the airspace it flies through.
#4208: The Awkward Honesty of AI Attribution
Why admitting AI helped feels like a confession — and what emerging norms actually work.
#4194: Custom GPTs: When to Build, When to Skip
A decision framework for knowing when a custom GPT is worth the overhead — and when to just open a fresh chat.
#4186: Alibaba’s B2B Engine: The $200B Trade You’ve Never Heard Of
Alibaba.com moves 2-3x more value than AliExpress, quietly becoming global trade’s operating system.
#4185: LiFePO4 Batteries: The Workhorse Chemistry for DIY Projects
LiFePO4 lasts 10x longer than lithium-ion. Here's how to choose, connect, and charge it for your build.
#4181: From Phone Typing to Direct Agent: Fixing Headless Server AI Access
ChatGPT saved his OS, but the copy-paste bottleneck from phone to server took hours. Here's how to fix it.
#4180: Translation-Safe Writing for Global Supply Chains
How to write English that survives machine translation without losing critical specs.
#4170: Obfuscation as Risk Management with AI
How AI can protect whistleblowers and trauma survivors by intelligently obscuring identities while preserving story integrity.
#4169: Change Detection AI for Construction Sites
How AI catches what experts miss in construction site photos — from Siamese networks to transformer models.
#4167: Why AI Can’t Read Your Gmail (Yet)
Your AI misses emails and fails to send replies. It’s not dumb—the pipes are leaky.
#4165: Living in the Gap: High-Rise Satire as Social Experiment
One man weaponizes luxury marketing by treating his apartment tower as an actual sanctuary above the city.
#4160: Why That "Dry" Wine Tasted Like Flat Coke
The chemistry of why "dry" on a label doesn't mean what you think — and which grapes deliver the real deal.
#4157: Prompt Engineering Is a Misnomer — Managing Ambiguity in AI
Why the best AI outputs come not from tighter prompts, but from knowing where to leave room for surprise.
#4145: Does Getting Things Done Actually Work?
Stress-testing David Allen’s GTD claims against real cognitive science. Does writing things down really free your brain?
#4143: How Screwdrivers Became a Museum of Bad Decisions
Why are there so many incompatible screw types? The surprising history of Phillips, Robertson, and the design that won by failing.