October 2026
342 episodes
- #6000 6,000 Episodes and a GPU Bill: Inside My Weird Prompts
- #5999 Who Teaches Actors Those Accents?
- #5998 America's Deadliest Rental Cars by the Numbers
- #5997 Counting Our Listeners, Then Planning a Cave
- #5996 Turning 3,000 Episodes Into a Video Channel
- #5994 Hebrew in Latin Letters: A TTS Pipeline Fix
- #5995 NVIDIA ASR: Parakeet, Canary, and Nemotron Explained
- #5993 Why Every Renovation Show Looks the Same
- #5992 Ridiculous But Legal Ways to Get RAM for AI
- #5991 Batch Inference on Your Own GPU: vLLM, SGLang, Ollama, llama.cpp
- #5989 Twenty Tiny Beats That Make a Podcast Stick
- #5988 Can You Engineer a Toddler's Accent?
- #5987 The LEGO Cam: When LEGO Gave Kids a Movie Studio
- #5986 Electronics Kits for Toddlers? What Actually Works
- #5985 Meccano at 125: What Kids Actually Learn From Bolts
- #5984 Reading a Mystery Adapter's Voltage Without a Label
- #5983 Inside the Barcelona Breathing Cure for APD
- #5982 Teaching a Voice Engine to Say "Yalla" Right
- #5981 Batch Inference: Four Doors, Half Price
- #5980 95% of Intelligence Comes From Open Sources
- #5979 Why We Shake Hands: A 2,800-Year History
- #5978 God Bless, Inshallah, Be'ezrat Hashem: Three Ways to Say Maybe
- #5977 Spy Codenames, Dead Drops, and the Phrases That Fooled Everyone
- #5976 What North of North Assumes You Know About Inuit
- #5975 Merging vs Distillation: Can Two Models Become One?
- #5974 One Model or Two? ASR Cleanup Explained
- #5973 MCP Security: Tool Poisoning and Agent Identity
- #5972 AI Meeting Agents Are Becoming Stand-Ins
- #5971 Personal CRM in 2026: Dex, Mesh, folk, Monica, Twenty
- #5970 Swapping Your Linux Kernel: What Actually Changes
- #5969 Ubuntu 26.04 LTS: Is Staying on LTS Still a Trade-Off?
- #5968 Gentoo in 2026: Still Worth Compiling?
- #5967 How UEFI, Secure Boot, and the Boot Chain Actually Work
- #5966 How Much of Your Linux Desktop Is Actually Misconfigured?
- #5965 Compiling From Source: What You Actually Get
- #5964 Containers vs VMs for GPU Inference: What You Actually Pay
- #5963 Running One Model Across Mismatched GPUs
- #5962 How Word Error Rate Lies to Us
- #5961 What Your GPU Is Actually Waiting On
- #5960 There's No Such Thing as Tokens Per Second
- #5959 What RTF Actually Tells You About Speech Models
- #5958 When Governments Answer FOI Requests With Silence
- #5957 The Scientific Plugins Hiding in Plain Sight
- #5956 Will ChatGPT Eat Your Grocery App?
- #5955 Work Lights: Lumens, Lux, and the Specs That Matter
- #5954 Layered Safeguards and the Math Behind Them
- #5953 How Militaries Decide What to Buy
- #5952 Inside Malmab: Israel's Most Secretive Security Body
- #5951 The Reasonable Person Is a Legal Fiction
- #5950 Self-Hosting Your Search Stack: SearXNG, Crawl4AI, and the Real Bill
- #5949 Inside Deep Research Agents: Claims, Citations, and the 84.7% Orchestrator Problem
- #5948 LangGraph, LangChain, and Deep Agents in 2026
- #5947 Who Actually Trades on Polymarket?
- #5946 Inside Humanity's Last Exam: 2,500 Questions AI Can't Ace
- #5945 How a Reward Model Actually Trains an LLM
- #5944 Keeping the Rollout Engine Fed: Inside RLHF Pipelines
- #5943 Tourniquets From Belts and Socks: What Actually Works
- #5942 Service Workers: The Proxy That Never Sleeps
- #5941 Five Minutes Reading Your Dictation Prompt
- #5940 The Missing Middle: Content APIs and ISR for a 6,000-Episode Catalog