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.
#4834: Why Your AI Bill Keeps Surprising You
How a 37-cent project and a $100 simulation reveal the hidden math of AI API pricing.
#4832: Your AI Memory Should Be Markdown Files
Why your AI project memory should live in Git-tracked Markdown files, not a proprietary platform.
#4827: When Your One-Person Stack Starts Fighting You
Your custom-built system was a perfect fit. Now it's a cast you can't escape.
#4825: Russian Dolls: Skills, MCPs, and Plugins
When to use a skill vs MCP vs plugin in Claude Code — and when to keep it simple.
#4822: Cloud-Local AI Hybrid: Does It Actually Work?
Can you pair Claude's reasoning with a local Qwen 7B for savings? The gap is wider than you think.
#4815: Agent Framework Lock-In: What Actually Breaks
Code-defined vs visual builders. LangGraph vs CrewAI. How portable are agent workflows really?
#4814: The Manager Agent Nobody Sees
How supervisor agents orchestrate AI pipelines without generating content—and the three ways they fail.
#4813: The $70 Mouse That Changed Everything
How a $70 ergonomic mouse purchase reveals the quiet way we learn to trust AI.
#4809: Can a Podcast Train Itself?
Can a podcast become a self-developing project? We explore RAG vs. fine-tuning for lore memory.
#4799: How to Build Your Own TTS Audiobooks
From M4B containers to chapter timing drift — the technical pipeline for creating audiobooks with synthetic voice.
#4795: Workwear as Anti-Label: Ditching Inherited Fashion
Why a DIY project triggered one man's break from Banana Republic and Ralph Lauren — and what he's wearing instead.
#4791: When AI Critiques Our Terminology
Can AI spot conceptual sloppiness in how we describe it? A podcast moment reveals something unexpected.
#4789: How LLMs Actually Know When to Stop
Three layers of stop signals, from EOS tokens to context limits — and why none of them really "know" when to stop.
#4788: How Weather Prediction Became a Science
From hand calculations to chaos theory to machine learning — the full arc of forecasting.
#4786: Markdown vs Vectors for Agent Memory
Why coding agents need two kinds of memory — and why mixing them creates a sync nightmare.
#4778: SSH MCP and Tailscale: Docker Migration Guide
How to configure Tailscale for Docker containers when migrating from public IPs to tailnet addresses.
#4775: The Evaluator Role No One's Building For
Benchmarks like MMLU are broken. A new role is emerging: the domain-specific AI evaluator.
#4774: When a Token Isn't a Word Anymore
Images, audio, and code all use "tokens" — but they're completely different things. Here's how tokenization actually works across modalities.
#4760: Context Window Management: Cutoff vs. Compaction
Trailing cutoff or auto-compaction? How to manage Claude Code's context window without losing critical information.
#4759: API Keys vs OAuth: When Simplicity Becomes a Security Trap
API keys are simple but leak identity, scope, and auditability. Here's when they work and when they don't.