Transformer Architecture
215 episodes · Page 7 of 9
#1556: The War Against Latency: Engineering Real-Time AI
From KV cache monsters to sub-100ms response times, explore the hardware and software innovations making real-time AI a reality.
#1547: Why AI Stopped Reading and Started Seeing Everything
From sequential bottlenecks to parallel powerhouses, discover how the Transformer architecture revolutionized how machines process the world.
#1546: The Death of Latency: Three Pillars of Modern Voice AI
Say goodbye to the "digital sandwich." Explore the three architectural pillars closing the latency gap in modern speech recognition.
#1500: The Great AI Divergence: How Models Specialized in 2026
The era of the chatbot is over. Discover how the "agentic substrate" of 2026 is redefining computing through GPT, Gemini, and Claude.
#1482: The Hidden Cost of Choosing an Embedding Model
From Matryoshka models to multimodal search, discover how the fundamental units of AI memory are being optimized for efficiency and scale.
#1479: The Speed of Thought: Inside the New Era of Inference
The war for model size is over. Explore the engineering breakthroughs making massive AI models faster than human thought.
#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.
#1423: Why Can't We Land an Airbus in the Ocean?
Why did we trade the luxury of flying boats for concrete runways? Explore the physics, history, and future of large-scale seaports.
#1322: When AI Stops Seeing and Starts Reasoning
Explore how AI evolved from simple pixel labeling to understanding intent and context through Vision-Language Models and agentic frameworks.
#1282: The Geometry of Thought: The Mathematics Powering AI
Peeking under the hood of AI to discover the beautiful linear algebra and calculus that make machine reasoning possible.
#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.
#1227: Mojo 1.0: Can Chris Lattner Fix the AI Performance Gap?
Explore how Mojo aims to unify Python’s ease of use with C++ performance to solve the "two-language problem" in AI development.
#1162: The Moral Statecraft Paradox: When Principle Costs You Everything
Ireland's "moral crusade" meets economic reality. Is a new trade bill about to sever the nation's vital lifeline to the United States?
#1122: Why AI Agents Are Abandoning Human Language
Why force AI to talk like humans? Explore how agents are ditching English for high-speed "mind-melding" and latent space communication.
#1115: The Rise of the AI Procurement Officer
Discover how AI is evolving from simple chat to autonomous B2B procurement agents capable of negotiating and executing million-dollar deals.
#1112: Inside the Neural Cathedral: Cracking the AI Black Box
Peek inside the "black box" of AI to discover how models use high-dimensional geometry and superposition to organize complex human concepts.
#1103: The Kitchen War: When Theory Meets Messy Reality
Explore the mechanics of LLM context windows and attention, and witness what happens when technical debates collide with household chores.
#1088: Why AI Can Read a Library but Only Write a Postcard
Discover why frontier AI models can process millions of words but struggle to write more than a few pages without losing their logical thread.
#1085: The Tokenization Lie: How AI Actually Processes Media
Think 1,000 tokens equals 750 words? For audio and video, that rule is a lie. Discover the hidden math behind multimodal AI.
#1084: Why AI Models Can’t Read and Your Bill Is Rising
Why does the same prompt cost more on different models? Discover the "invisible wall" of tokenization and how it shapes AI perception.
#1081: The K-V Cache: Solving AI’s Invisible Memory Tax
Why does your AI get slower as you chat? Discover the K-V cache, the invisible bottleneck of generative AI, and how we're fixing it in 2026.
#1080: From Prompt to Intent: The Claude Opus Roadmap
Explore the engineering roadmap from Claude 4.6 to 5.0 as AI evolves from a simple chatbot into a fully autonomous cognitive partner.
#1066: Beyond the Blank Slate: The Evolution of AI Training
Explore the "weight surgery" techniques labs use to expand AI models without losing their core knowledge or starting from zero.
#1056: The Vocabulary Myth: Do More Words Equal Better Thinking?
Does a massive vocabulary lead to deeper thoughts? Explore the hidden mechanics of English, Hebrew, and the famous "Inuit snow" myth.