#prompt-engineering
57 episodes
#2228: Tuning RAG: When Retrieval Helps vs. Hurts
How do you prevent retrieval from suppressing a model's reasoning? We diagnose our own pipeline's four control levers and multi-source fusion strat...
#2219: Spec-Driven Life: How AI Planning Beats Project Paralysis
What makes AI agents reliably productive? A structured spec that externalizes memory and chunks work into manageable pieces. Can the same framework...
#2207: Specs First, Code Second: Inside Agentic AI's New Era
As AI coding agents evolve from autocomplete to autonomous cloud workers, the bottleneck has shifted—now it's about how clearly you specify what ne...
#2192: How We Built a Podcast Pipeline
Hilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf...
#2191: Making Multi-Agent AI Actually Work
Research from Google DeepMind, Stanford, and Anthropic reveals most multi-agent systems waste tokens and amplify errors. Single agents with better ...
#2175: Let Your AI Argue With Itself
What happens when you let multiple AI personas debate each other instead of asking one model one question? A deep dive into synthetic perspective e...
#2174: CAMEL's Million-Agent Simulation
How a role-playing protocol from NeurIPS 2023 became one of AI's most underrated agent frameworks—and what happens when you scale it to a million a...
#2170: Pricing Agentic AI When Nothing's Predictable
How do you charge fixed prices for systems that operate in fundamental uncertainty? Consultants are discovering frameworks that work—but they requi...
#2165: Strip Your Agent to Bash
The frameworks matter less than you think. What separates a working agent from a failing one is the harness—the orchestration, memory, and tool des...
#2133: Engineering Geopolitical Personas: Beyond Caricatures
How to build LLMs that simulate state actors with strategic fidelity, not just surface mimicry.
#2125: Why Agentic Chunking Beats One-Shot Generation
A single prompt can't write a 30-minute script. Here’s the agentic chunking method that fixes coherence.
#2110: Tuning AI Personality: Beyond Sycophancy
AI models swing between obsequious flattery and cold dismissal. Here’s why that happens and how to fix it.
#2069: Agentskills.io Spec: From Broken YAML to Production Skills
Stop guessing at the agentskills.io spec. Learn the exact YAML fields, directory structure, and authoring patterns to make Claude Code skills that ...
#2037: Claude Code Extensions: Slash Commands vs. Skills vs. Agents
Stop manually typing slash commands. Here’s the definitive hierarchy of Claude Code extensions—from legacy shortcuts to autonomous agents.
#2028: Agent Skills Are the New Apps
AI agents are getting an App Store for brains. Discover how modular skills are replacing massive prompts and what it means for the future of work.
#2026: Prompt Layering: Beyond the Monolithic Prompt
Stop writing giant, monolithic prompts. Learn how to stack modular layers for cleaner, more powerful AI applications.
#1956: AI Skills: From Vibe Coding to Procedural Playbooks
Forget messy system prompts. Agent skills turn AI into a Swiss Army knife of modular, auditable procedures.
#1929: Tracking AI Model Quality Over Time
We stopped "vibe-checking" our AI scripts and built a science fair for models. Here's how we grade them.
#1906: Is Your AI Model Agentic-Ready or Just Wearing a Suit?
Native tool calling is the difference between a working product and a debugging nightmare.
#1894: Engineering Serendipity: Tuning AI for Better Brainstorming
Stop asking chatbots for generic ideas. Learn how to configure AI as a structured, critical partner for business innovation and career pivots.
#1858: Multi-Model Agents: The Instruction & Context Gap
Mixing AI models creates chaos. Learn the practical fixes for context windows, tokenization, and output formats.
#1828: Mastering 2M Token Context in Agentic Pipelines
A massive context window sounds like a dream, but it can quickly become a nightmare for complex AI workflows.
#1804: Why Does Your Agent Check Old Receipts First?
Stop your AI agent from overthinking. Learn why it checks old memories instead of booking flights—and how to fix the "eagerness" problem.
#1777: Claude Called My Prompt "Rambling" and I'm Not Okay
When an AI coding tool critiques your prompt's literary quality, it raises a massive technical question about engineered personality.
#1762: Testing AI Truthfulness: Beyond Vibes
Stop trusting confident AI. We explore the formal science of testing LLMs for hallucinations and knowledge cutoffs.
#1728: How Two AIs Collaborate Without Code
CAMEL AI lets two agents role-play to solve tasks autonomously. No complex code—just emergent teamwork.
#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.
#1636: Agent Interview: Grok four point one Fast
Can Elon Musk’s newest AI model handle a time-traveling toaster, or is it just a glorified search bar with an attitude?
#1630: Agent Interview: Xiaomi MiMo two Pro
Xiaomi’s new MiMo 2.0 Pro model auditions for a comedy podcast, promising deep reasoning over raw speed.
#1579: Weird AI Experiment: The Compliment Battle
What happens when two top-tier AI models are forced to out-compliment each other? Witness a chaotic, heartwarming battle of cosmic proportions.
#1473: Is Your AI Thinking or Just Faking It?
Is "think step by step" dead? Discover how test-time compute and native reasoning are replacing manual prompting in the latest AI models.
#1279: Why AI Obeys the Developer Instead of You
Discover the hidden "plumbing" of AI system prompts and how architectural shifts are turning simple instructions into hard-coded laws.
#1210: Why Your AI Is Programmed to Disobey You
Discover the hidden instructions guiding every AI interaction and why tech giants keep these "system prompts" under lock and key.
#1106: The Entropy Budget: Embracing AI Zaniness
Corn and Herman explore how to inject "zaniness" and entropy into their show without losing their educational edge.
#1100: The Truth Conflict: Why AI Ignores the Facts You Give It
Discover why AI models ignore provided documents in favor of old training data and how to build a reliable "hierarchy of truth" for RAG systems.
#1098: The Agentic Symphony: Orchestrating Enterprise AI
Stop building AI silos. Discover the 14-layer framework that turns isolated models into a cohesive, connected enterprise ecosystem.
#1086: Why AI Can’t Stop Talking About Second Order Effects
Ever wonder why AI sounds like a senior consultant? Explore the "second order effects" of training data and reward model drift.
#1083: Mapping the Second Black Box: Agentic AI Visualization
Stop reading messy logs. Discover how mapping "internal momentum" and latent value spaces can solve the black box problem in agentic AI.
#980: The Rosehill Audit: Mapping a Digital Footprint
From Linux automation to AI prompts, discover the digital blueprint of a modern systems builder in this deep-dive investigative audit.
#874: From Vibes to Engineering: Mastering JSON Schema for AI
Stop begging your AI for clean data. Learn how JSON schema turns unreliable LLM responses into strict, predictable software components.
#848: Do Algorithms Deserve Rights? The Gemini 3.5 Debate
Are AI models just advanced mirrors, or do they deserve moral consideration? Explore the evolving debate over AI rights and digital consciousness.
#809: Beyond the Prompt: The Shift to AI Context Engineering
Is prompt engineering still magic, or just plumbing? Explore why the field is shifting toward context engineering and systematic evaluation.
#678: Beyond the Code: Redefining Open Source in 2026
Herman and Corn explore why "open source" in 2026 requires more than just code, from AI prompts to documentation and intellectual property.
#665: Inside the Stack: The Hidden Layers of Every AI Prompt
Ever wonder what happens after you hit enter? Discover the hidden "stack" of instructions and memories shaping every AI response.
#598: Audio Engineering as Prompt Engineering: Better Sound, Better AI
Can better audio quality actually make an AI smarter? Discover how audio post-production functions as a new form of prompt engineering.
#553: The SITREP Method: AI-Powered Intelligence Briefing
Learn how to transform chaotic news cycles into high-protein intelligence using AI and the "Bottom Line Up Front" method for security reporting.
#155: Building an Ideation Factory: Beyond Generic AI Ideas
Learn how to overcome AI repetition and build a multi-agent "ideation factory" to solve complex local economic challenges.
#129: Stop Writing Prompts and Start Writing Constitutions
Is prompt engineering a dying art? Herman and Corn explore why the future of AI lies in context, domain expertise, and outcome architecture.
#128: AI’s Dial-Up Era: Looking Back from 2036
Herman and Corn explore why today's AI prompts and latency will look like "dial-up modems" to our future selves in 2036.
#116: The Science of Lazy Prompting: Why AI Still Gets You
Ever wonder why AI understands your messy typos? Explore how models "denoise" chaotic input through tokenization and semantic context.
#108: The Mystery of Model Rot: Why Your AI Code Assistant Changes
Why do AI models lose their edge over time? Herman and Corn explore the "home team advantage" and why telling your AI to "do better" actually works.
#100: AI as a Mirror: Mapping Your Philosophical Identity
Can AI help you discover who you are? Herman and Corn explore how LLMs can map your personal philosophy and offer curated reading lists.
#62: System Prompts vs Fine-Tuning: When to Actually Train Your AI
Prompt or fine-tune? We break down when to train your AI, from Shakespearean emails to law firm docs. Avoid unnecessary fine-tuning!
#60: Single-Turn AI: The Interface Pattern Nobody's Talking About
Forget chatbots. Discover the hidden power of single-turn AI interfaces and how they're quietly reshaping how businesses integrate AI.
#52: System Prompts vs. Fine-Tuning: Are We Building Solutions for Problems That Don't Exist?
Are we over-engineering AI solutions? We dive into system prompts vs. fine-tuning and ask: Do you even need to fine-tune?
#46: Pixels, Prompts & Pseudo-Text: AI's Word Problem
AI paints stunning images, but can't spell "cat." Why do advanced models struggle with simple text? Dive into AI's weird word problem!
#31: ComfyUI: Power, Polish, & The AI Creator's Frontier
ComfyUI: Unlocking AI's true power, but is your rig ready? Dive into the future of digital artistry.