#large-language-models
167 episodes
#5056: How AI Writes a 30-Minute Podcast in One Pass
What does it take for a model to write a full episode without edits? The answer involves context windows, repetition, and a surprising architecture...
#5041: GPT-6 Astra, 100K GPUs, and the AGI Question
OpenAI's GPT-6 Astra arrives with an AGI claim and a 100K-GPU training run. We break down what Stargate LLC actually is and whether the scale justi...
#4994: How AI Characters Can Actually Grow
Moving beyond static lore books to build characters with real history and evolution.
#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.
#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.
#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.
#4723: Are Model Families Actually Different Models?
Claude Opus, Sonnet, and Haiku aren't trim levels — they're different models sharing a brand name.
#4701: Why Claude Code Re-Introduces Itself to Your Repo
Claude Code remembers your preferences but not your codebase. We explore why that's by design and how to work around it.
#4696: Why AI Over-Explains Simple Tasks
Why does AI turn a simple request into a 24-page document? We explore the training biases and architectural limits behind AI's tendency to over-del...
#4670: Why AI Weights Are Indecipherable
Can you actually read an AI model's weights like a book? We explore why the answer is mostly no — and what researchers are doing about it.
#4669: What "Distribution" Really Means in AI Models
Unpacking what "distribution" actually means under the hood — and why training data variety shapes model behavior.
#4658: Will AI Coding Kill Programming Languages?
Machines now write code better than humans. What happens to Python, TypeScript, and COBOL when no human reads the code?
#4657: From Plugboards to JIT: Who Controls the Hardware?
How the relationship between programming languages and hardware shifted from total programmer control to runtime autonomy.
#4656: Books That Outlive Frameworks: A Dev's Guide
Skip the API docs. Learn the data model, type system, and patterns that survive framework churn.
#4589: The Answer Reflex: Why AI Models Can't Follow Instructions
DeepSeek passes a simple test that stumps GPT and Claude. Why can't Western models stay in character?
#4588: The Hidden Cost of Conversational AI: Why Stateless LLM Calls Matter
Why conversational AI tools are making batch document processing slower, costlier, and less reliable — and what to do about it.
#4581: Text In, Text Out: Designing Single-Purpose AI Utilities
Why small, narrowly scoped AI tools need system prompts that say "shut up and return the output" — and how to write them.
#4570: One Negative Prompt Beat a Dozen Positives — Here's Why
Why one blunt "don't" outperformed a dozen careful "do's" — and how to structure your system prompts for maximum compliance.
#4523: Can You Trust an AI's Summary?
Dedicated text compressors exist but aren't in production. The real problem? Nobody can verify the summary didn't drop what mattered.
#4505: What DeepSeek's Training Data Reveals About Model Voice
Why Chinese AI models trained on 60% English still produce dialogue that feels distinctively different.
#4467: How Zoxide's Decay Algorithm Works
The math behind how zoxide remembers and forgets your directory habits with exponential precision.
#4106: Embedding Models vs LLMs: What Actually Connects?
Can you mix any embedding model with any LLM? And why are new embedding models still dropping if they're "solved"?
#4104: Why 20% of AI Scripts Loop on Themselves
Debugging the mysterious repetition bug affecting one in five podcast episodes.