Context and Memory
299 episodes · Page 10 of 13
#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.
#1538: The Cold Monetization Era: Why AI Limits are Here to Stay
Why is your $200 AI plan hitting limits? Discover the hidden costs of reasoning tokens and the physical bottlenecks of the 2026 AI energy crisis.
#1504: Pragmatic Insincerity: Why AI Still Doesn’t Get the Joke
From Oscar monologues to the "Pun Gap," we explore why even the smartest AI still struggles to understand sarcasm and social nuance.
#1498: The Multi-Player Shift: Sharing One AI Brain
Stop copy-pasting prompts. Explore how shared "multi-player" AI is turning solitary chatbots into collaborative team members.
#1484: The Illusion of Learning: From AI Brain Fry to Mastery
Why do podcasts make us feel smart but leave us with zero retention? Discover the science of AI Brain Fry and the power of active debate.
#1483: The Recall-Per-Dollar Era: Mastering Vector Database Tuning
Stop burning money on unoptimized vector searches. We dive into HNSW tuning, distance metrics, and the vital "recall-per-dollar" metric.
#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.
#1481: The End of the AI Chat Sidebar
Discover how tools like Cursor and Claude Code use Merkle trees and knowledge graphs to master massive codebases with surgical precision.
#1464: When AI Agents Author 4% of All Code
Explore how agentic harnesses transform AI from a passive chatbot into an active developer capable of full-cycle software engineering.
#1406: Giving AI a Brain: The Power of Knowledge Graphs
Move beyond "stochastic parrots" with Knowledge Graphs. Discover how structured data is giving AI the logical backbone it needs to reason.
#1283: Is Your AI Thinking Too Much?
Stop building Rube Goldberg machines. Learn why autonomous AI agents might be the highest-interest technical debt in your stack.
#1235: Beyond "No Training": Securing the New Agentic AI Stack
Think your data is safe because of a "no training" clause? We deconstruct the hidden security risks within the modern agentic AI stack.
#1218: The Architectural Divide Between Batch and Live Speech
Why does voice typing feel so clunky compared to recording a memo? We explore the technical hurdles of real-time AI transcription.
#1212: The Postgres Vector Revolution: Killing the Sprawl
Is your tech stack a sprawling suburb of microservices? Discover why a 40-year-old database is winning the AI infrastructure war.
#1123: When One Database Isn't Enough
Can Postgres 18 finally replace the data warehouse? We dive into data gravity, columnar storage, and the physics of scaling in the AI age.
#1120: The AI Handoff: From Manual Hacks to Standard Protocols
Stop the "context rot." Learn how new protocols like MCP and typed state channels are revolutionizing how AI agents collaborate.
#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.
#1111: Surviving the arXiv Deluge: Finding Signal in AI's Paper Firehose
Discover the unsung research papers that built the AI era and learn how to navigate the relentless flood of new machine learning breakthroughs.
#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.
#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 Hidden Vendor Prompt: Why Enterprise AI Agents Stay Siloed
Stop building AI silos. Discover the 14-layer framework that turns isolated models into a cohesive, connected enterprise ecosystem.
#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.
#1087: Inside My Weird Prompts: A Meta-Analysis of the Hosts
Go behind the scenes of My Weird Prompts as Corn and Herman discuss their unique biology, neural implants, and life in Jerusalem.