
My Weird Prompts
6,581 episodes — Page 14 of 132
Inside the Decode Loop: How LLMs Generate One Token at a Time
Oct 15, 202626 min
Inside LLM Inference: Prefill, Decode, and the KV Cache
Oct 15, 202634 min
Ten Ridiculous Wearables, Ranked by Sincerity
Oct 15, 202624 min
Vertex AI Is Now the Gemini Agent Platform
Oct 15, 202626 min
Why Codex Writes Code for a Dead API
Oct 15, 202616 min
What a $1M AI Inference Contract Actually Contains
Oct 15, 202626 min
Data Residency vs. Inference Residency: What the Law Actually Says
Oct 15, 202629 min
What's Actually Behind a Government AI Chatbot
Oct 15, 202624 min
Nobody Can Buy Unlimited AI Inference
Oct 15, 202621 min
What Enterprises Actually Pay for AI Inference
Oct 15, 202625 min
Claude on AWS: Three Doors, One Rate Card
Oct 15, 202626 min
What Do Inference Providers Actually Sell?
Oct 15, 202626 min
6,000 Episodes and a GPU Bill: Inside My Weird Prompts
Oct 15, 202620 min
Who Teaches Actors Those Accents?
Oct 15, 202619 min
America's Deadliest Rental Cars by the Numbers
Oct 15, 202621 min
Counting Our Listeners, Then Planning a Cave
Oct 15, 202634 min
Turning 3,000 Episodes Into a Video Channel
Oct 15, 202630 min
Hebrew in Latin Letters: A TTS Pipeline Fix
Oct 15, 202633 min
NVIDIA ASR: Parakeet, Canary, and Nemotron Explained
Oct 15, 202632 min
Why Every Renovation Show Looks the Same
Oct 15, 202634 min
Ridiculous But Legal Ways to Get RAM for AI
Oct 15, 202620 min
Batch Inference on Your Own GPU: vLLM, SGLang, Ollama, llama.cpp
Oct 15, 202621 min
Twenty Tiny Beats That Make a Podcast Stick
Oct 15, 202620 min
Can You Engineer a Toddler's Accent?
Oct 15, 202625 min
The LEGO Cam: When LEGO Gave Kids a Movie Studio
Oct 15, 202622 min
Electronics Kits for Toddlers? What Actually Works
Oct 15, 202628 min
Meccano at 125: What Kids Actually Learn From Bolts
Oct 15, 202622 min
Reading a Mystery Adapter's Voltage Without a Label
Oct 15, 202622 min
Inside the Barcelona Breathing Cure for APD
Oct 15, 202638 min
Teaching a Voice Engine to Say "Yalla" Right
Oct 15, 202627 min
Batch Inference: Four Doors, Half Price
Oct 15, 202634 min
95% of Intelligence Comes From Open Sources
Oct 14, 202628 min
Why We Shake Hands: A 2,800-Year History
Oct 14, 202619 min
God Bless, Inshallah, Be'ezrat Hashem: Three Ways to Say Maybe
Oct 14, 202625 min
Spy Codenames, Dead Drops, and the Phrases That Fooled Everyone
Oct 14, 202624 min
What North of North Assumes You Know About Inuit
Oct 14, 202639 min
Merging vs Distillation: Can Two Models Become One?
Oct 14, 202624 min
One Model or Two? ASR Cleanup Explained
Oct 14, 202633 min
MCP Security: Tool Poisoning and Agent Identity
Oct 14, 202632 min
AI Meeting Agents Are Becoming Stand-Ins
Oct 14, 202627 min
Personal CRM in 2026: Dex, Mesh, folk, Monica, Twenty
Oct 14, 202627 min
Swapping Your Linux Kernel: What Actually Changes
Oct 14, 202626 min
Ubuntu 26.04 LTS: Is Staying on LTS Still a Trade-Off?
Oct 14, 202630 min
Gentoo in 2026: Still Worth Compiling?
Oct 14, 202625 min
How UEFI, Secure Boot, and the Boot Chain Actually Work
Oct 14, 202632 min
How Much of Your Linux Desktop Is Actually Misconfigured?
Oct 14, 202629 min
Compiling From Source: What You Actually Get
Oct 14, 202627 min
Containers vs VMs for GPU Inference: What You Actually Pay
Oct 14, 202630 min
Running One Model Across Mismatched GPUs
Oct 14, 202631 min
How Word Error Rate Lies to Us
Oct 14, 202626 min