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.
#2755: How to Build AI Memory That Actually Works
Stop jumping to conflict resolution. The real challenge is getting data in and out cleanly.
#2754: Why Your Dictation Setup Might Be Wrong
Modern ASR is shockingly robust. The biggest predictor of accuracy? How well your audio matches its training data.
#2750: The Politics of Lighting Protocols
DMX, sACN, Eos vs. grandMA3—how the booth actually controls the lights.
#2749: The 16-Hour Day Behind an 8-Show Week
What a Broadway actor's day actually looks like: silent mornings, straw phonation, and two-show days.
#2747: Can Method Acting Really Rewrite Your Memory?
What happens when an actor's brain starts misfiling a character's memories as their own? The surprising answer.
#2741: What Theoretical Physicists Actually Do All Day
Chalkboards, arXiv firehoses, and 2 hours of real work. What the daily life of a theoretical physicist actually looks like.
#2736: Why AI Flagged Your Em Dash
Punctuation isn't a fixed system handed down by grammarians. It's a two-thousand-year story of contraction, invention, and now AI suspicion.
#2726: Radio Listening vs Podcast Guilt
Why does podcast listening feel different from radio? A deep dive into attention, multitasking, and the psychology of audio.
#2713: The PT Cruiser: Icon or Punchline?
Was the PT Cruiser a design triumph or a cultural joke? We break down its rise, fall, and strange legacy.
#2693: When AI Ignores Your Style Guide
Why your AI ignores formatting instructions and how to fix it with pipeline architecture, not model swaps.
#2691: The Usability Tax of Least Privilege
Is it time to let AI agents handle your API key creation and rotation? We explore the real security tradeoffs.
#2690: Where Agent Builders Actually Gather
The MCP community, A2A protocol, and Linux Foundation are building the professional identity of agentic AI right now.
#2689: Why CLI Beats MCP for AI Agents Sometimes
Why a plain command-line tool can outperform a purpose-built MCP server for AI agents — and what that means for the protocol's future.
#2688: Intelligent Frame Extraction for Multimodal AI
Use multimodal AI and smart frame extraction to turn a walk-through video into an actionable decluttering plan.
#2687: When Pre-Flight Checks Help (or Hurt) Agentic AI Plugins
How to decide when a pre-flight check is worth the latency cost — and how to write good ones.
#2685: Plugin Data Storage for AI Agents
How to separate user data from plugin code across Linux, macOS, and Windows in agentic AI environments.
#2684: When Agent Skills Collide: Context Windows & Plugin Design
How to handle overlapping agent skills and whether context windows will ever make the problem go away.
#2683: MCP vs Agent Skills: Context Wars
When 12M token windows arrive, do MCP servers or agent skills win? Plus: federated access for agent teams.
#2682: Live Retrieval vs. RAG: What an Agent Actually Does
Does every AI conversation create a tiny vector store? We unpack the real tradeoffs between live document fetching and pre-indexed RAG.
#2677: Memory Layers for AI Agents: SaaS vs Self-Hosted
Zep, mem0, Letta, Graphiti, Cognee — which memory layer should you commit to for your AI agent?