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.
#1731: Why Deep Research Agents Are Being Forgotten
Specialized research agents outperform general orchestrators by 40-60% on verification tasks, yet developer hype is fading. Here's why.
#1730: Are Multi-Agent Coding Frameworks Obsolete?
MetaGPT, SWE-agent, and OpenHands promised a team of AI devs. But in 2026, are they still useful, or has raw model power made them obsolete?
#1729: Why Is AI Code So Hard to Read?
AI writes code faster than ever, but the output is often a cryptic mess. We explore why and how to fix it.
#1728: The AI Carpool: Emergent Collaboration Through Role-Playing
CAMEL AI lets two agents role-play to solve tasks autonomously. No complex code—just emergent teamwork.
#1727: The Great Architectural Heist: LSP as AI's Universal Plumbing
Explore how the Language Server Protocol is being repurposed to integrate AI directly into code editors, unifying development workflows.
#1724: When AI Dubbing Swaps Your Gender
How does YouTube translate a video with one click? We explore the tech behind auto-dubbing, from sandwich models to voice cloning.
#1725: The Death of the Lonely Chatbot
Forget chatbots: AI orchestration is now the key to scaling intelligent agents in the enterprise.
#1723: Why Agentic AI Needs a Hive Mind, Not a Single Brain
The single monolithic AI model is dying. Meet the new native multi-agent architectures that think like a team, not a solo genius.
#1721: AI Doxxing: Why Your Writing Style Is a Liability
AI tools now identify anonymous users by analyzing their unique writing patterns, making traditional privacy measures less effective.
#1719: Why Pattern Matching Fails for PII at Scale
Regex alone is brittle; NER is expensive. See how hybrid frameworks like Presidio balance speed and accuracy to stop data leaks.
#1718: The Ralph Wiggum Technique: AI That Codes Itself
Stop babysitting AI agents. Learn the Ralph Wiggum technique to automate iterative coding loops and let AI finish the job itself.
#1717: The AI Framework Name Game
Why are there thousands of "AI frameworks" on GitHub? We unpack the naming mess and the cost of semantic inflation.
#1716: Seeing the AI Think: Visual Debugging for Agent Workflows
See how a visual, node-based tool lets you build complex AI agent workflows without writing code.
#1715: Why Voice Agents Need Frameworks (Not Just APIs)
Raw APIs handle models, but who manages the audio plumbing? We break down Vapi, LiveKit, and Pipecat.
#1713: Why Native AI Search Grounding Still Fails
Native search grounding is expensive and flaky. Here’s why bolt-on tools still win for accurate, real-time AI answers.
#1712: Five AIs, One Question: A Tiananmen Square Test
We asked five AI models the same question about Tiananmen Square. Their answers reveal a stark divide between Chinese and Western AI.
#1711: Stop Building the Bucket: The Vendor SDK Era
We compare the three major vendor SDKs for building AI agents, weighing speed, safety, and scalability.
#1708: Why Your AI Agent Forgets Everything (And How to Fix It)
Learn how Letta's memory-first architecture solves the AI context bottleneck for long-term agents.
#1706: Hollywood Hacking vs. Real Airgap Sabotage
Why the "lone operative" trope breaks down when you look at the physical reality of nuclear facility security.
#1705: Microsoft's Phi: The Small Model Bet for Agentic AI
Microsoft is pushing small language models like Phi for agentic AI. Here’s why that strategy matters for speed, cost, and edge computing.