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.
#2178: How to Actually Evaluate AI Agents
Frontier models score 80% on one agent benchmark and 45% on another. The difference isn't the model—it's contamination, scaffolding, and how the te...
#2177: Skip Fine-Tuning: Shape LLMs With Alignment Alone
Can you build a personalized LLM by skipping traditional fine-tuning and using only post-training alignment methods like DPO and GRPO? We break dow...
#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: Role-Playing as Orchestration
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...
#2173: Inside MiroFish's Agent Simulation Architecture
MiroFish generates thousands of AI agents with distinct personalities to predict social dynamics. But research reveals a critical flaw: LLM agents ...
#2172: Council of Models: How Karpathy Built AI Peer Review
Andrej Karpathy's llm-council uses anonymized peer review to make language models evaluate each other fairly—but can it really suppress model bias?
#2171: How IQT Labs Built a Wargaming LLM (Then Archived It)
A deep code review of Snowglobe, IQT Labs' open-source LLM wargaming system that ran real national security simulations before being archived. What...
#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...
#2169: How Enterprises Are Rethinking Agent Frameworks
Twelve major agentic AI frameworks exist—yet many serious developers avoid them entirely. What patterns emerge in real enterprise adoption?
#2168: What Serious Agentic AI Developers Actually Need to Know
Python, TypeScript, LangGraph, and the frameworks reshaping how agents work. A technical map of the skills and concepts that separate prototypes fr...
#2167: Sync vs. Async: Architecting Agents for Scale
Why most enterprise AI agents fail in production has less to do with models and more to do with whether they're built synchronously or asynchronously.
#2166: Code vs. Canvas: How Developers Pick Their Tools
LangGraph or Flowise? The honest answer isn't obvious. Developers gain speed and integrations with visual builders—but lose version control, testin...
#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...
#2164: Why Bigger Context Windows Don't Fix Attention
Frontier models have million-token context windows, but attention degrades well before you hit the limit. New research reveals why bigger isn't bet...
#2163: Designing Autonomy Boundaries for AI Agents
Production data reveals a surprising truth: fully autonomous AI agents waste 98% of their context window on tool descriptions. Here's why the indus...
#2160: Claude's Latency Profile and SLA Guarantees
Claude is measurably slower than competitors—and Anthropic's SLA promises are even thinner than the latency numbers suggest. What enterprises actua...
#2158: Claude Managed Agents: Brain Versus Hands
Anthropic's new Managed Agents service runs your agent loop on their infrastructure. Here's what you gain, what you lose, and who it's actually for.
#2150: Debugging Your Brain’s Source Code
Learn the five-step CTFAR sequence that turns emotional chaos into a logical, debuggable system for a managed mind.
#2146: The AI Wargame's Flat Hierarchy Problem
AI wargames treat NGOs and nuclear powers as equals. That's a dangerous flaw for real-world policy planning.
#2144: AI Wargaming: One Model or Many?
Should geopolitical AI simulations use one model or many? We debate the pros and cons of a single-model approach.