Transformer Architecture
215 episodes · Page 8 of 9
#974: The Digital Gardener: Why We Don't Understand Our Own AI
We build digital cathedrals but lack the blueprints. Explore the "black box" of AI, emergent abilities, and the mystery of double descent.
#861: Modeling a Nation's Rewiring with AI Digital Twins
What if Israel lost the support of the US and EU? Explore the economic shocks and AI tools used to model a massive geopolitical shift.
#832: How AI Rebuilt the Curb Cut
From Whisper to smart prosthetics, discover how AI is transforming accessibility and granting independence to millions.
#699: Can AI Get the Joke? Sarcasm, Irony, and LLM Nuance
Discover how AI learns to spot sarcasm and avoid being a "Clippy" through the power of latent space and human feedback.
#650: When AI Thinks Longer, Not Bigger
Explore how Gemini 3.0’s Deep Think mode shifts AI from "fast" reflexes to "deliberate" reasoning to solve complex quantum physics problems.
#628: GPT-5.2: 12 Hours of Reason and the Future of AGI
GPT-5.2 spent 12 hours reasoning to solve a novel quantum physics proof. Is this the dawn of AGI or just a very sophisticated calculator?
#574: When Friction Creates Meaning: Travel as a Perspective Shift
Forget vacations. Herman and Corn explore five destinations where a month-long stay will fundamentally shift your perspective on how to live.
#336: The World Model Revolution: Beyond LLM Token Prediction
Herman and Corn explore why LLMs struggle with logic and how the shift to world models is giving AI a sense of physics and spatial reality.
#267: Decoding the Transformer: From Attention to Inference
Herman and Corn dive into the mechanics of transformer inference, exploring how models turn massive matrices into meaningful conversation.
#261: The 70-Year Overnight Success: How AI Finally Arrived
Think AI was an overnight success? Join Herman and Corn as they trace the 70-year journey from rigid logic rules to modern deep learning.
#260: Digital Archeology: The Primitive Power of GPT-1
Revisit the 2018 model that started it all. Herman and Corn dive into GPT-1's romance-novel roots and its 117-million-parameter legacy.
#210: Predictive Motion: How Transformers Are Learning to Walk
Explore how the same transformer architecture behind chatbots is now enabling robots to navigate the physical world using action tokens.
#199: When AI Outruns Physics: The New Weather Forecaster
Exploring the shift from physics-based models to AI-driven meteorology. Can algorithms predict the next big storm better than humans?
#196: Why Your Irish Accent Sounds American
Herman and Corn dive into the mechanics of neural text-to-speech, exploring how AI masters human prosody and the "average voice" accent problem.
#182: The Quadratic Bottleneck: Why AI Needs New Architectures
Is the transformer’s reign ending? Herman and Corn explore Mamba, x-LSTM, and the architectures solving AI's massive memory problem.
#181: Why Your AI Is Finally Stopping to Think
Discover how AI shifted from instant reflexes to deep reflection through inference-time compute and hidden reasoning steps.
#176: What Are AI Weights, Really?
What actually happens inside an AI model? Corn and Herman break down the numerical "valves" and "knobs" that power modern intelligence.
#170: How PyTorch Beat TensorFlow and Became AI's Backbone
Discover why PyTorch is the "oxygen" of AI. Herman and Corn explore its history, the magic of Autograd, and the move to the PyTorch Foundation.
#135: Is OCR Dead? How Vision AI Is Redefining Text Extraction
Are specialized OCR tools obsolete? Herman and Corn explore how Vision Language Models are revolutionizing the way we turn images into data.
#133: When Quantum Computing Becomes Accessible
Discover how quantum computing is transforming AI from brute-force scaling to surgical precision in this deep dive into the 2026 tech landscape.
#132: How AI Learns to See Time as a Dimension
Discover how spatial-temporal tokenization and 3D world modeling are revolutionizing real-time video-to-video AI interaction.
#126: The Cocktail Party Problem: Why AI Forgets
Why do AI models "lose the plot" after a few thousand words? Discover the mechanics of attention and the innovations solving context window limits.
#122: The Comeback of RNNs: Why Old Tech Still Matters
Herman and Corn pull back the curtain on AI to explain the mathematical "plumbing" of neural networks and the future of machine learning.
#117: From Keywords to Vectors: How AI Decodes Meaning
Why can AI write poetry but struggle to find a file? Explore the history and math of semantic understanding with Herman and Corn.