Pinecone
Managed vector database service
Episodes
-
#4832: Your AI Memory Should Be Markdown FilesWhy your AI project memory should live in Git-tracked Markdown files, not a proprietary platform. -
#4786: Markdown vs Vectors for Agent MemoryWhy coding agents need two kinds of memory — and why mixing them creates a sync nightmare. -
#4316: How to Build Memory That Survives AI SessionsWhy AI agents forget between sessions — and how to fix it with markdown files instead of black-box memory. -
#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"? -
#4092: How AI Remembers What You Never Told ItHow ChatGPT connected "wall anchors" to a power tool you bought days ago — without being asked. -
#3874: How to Tag 4000 Episodes Without Losing Your MindWhy tagging breaks at scale, and how a two-stage AI pipeline fixes it for good. -
#3673: Knowledge Graphs vs SQL: How Custom Relationships Change RetrievalWhy naming relationships (not just connecting data) transforms how you retrieve information. -
#3553: Can AI Review Your Lease in Israel?Can AI actually understand Israeli tenant law? We explore the tools, the gaps, and how to build your own. -
#2755: How to Build AI Memory That Actually WorksStop jumping to conflict resolution. The real challenge is getting data in and out cleanly. -
#2677: Memory Layers for AI Agents: SaaS vs Self-HostedZep, mem0, Letta, Graphiti, Cognee — which memory layer should you commit to for your AI agent? -
#2676: Vector Database Schema Design for AI Memory LayersStop dumping vectors blindly. Design metadata schemas and namespaces for retrieval that actually works at scale. -
#2673: The Embedding Coupling Problem: Editing Vector StoresCan you edit or delete individual chunks in Pinecone? And can you actually back up a vector index? Yes—but with critical caveats. -
#2639: The Hidden Layer That Makes Search WorkWhy your search results miss the mark — and how cross-encoders fix it. -
#2466: The Hidden Trap of Embedding Model Lock-InWhat happens when your vector database works great — until your embedding model gets deprecated and your vectors become useless. -
#2271: Vector Search in a Single FileWhat if you could do vector search with just SQLite? We explore sqlite-vec, the extension that adds embeddings to the world's simplest database, an... -
#2181: When RAG Becomes an AgentRAG in chatbots is simple retrieval. RAG in agents is a multi-step decision loop. Here's what actually changes. -
#1792: Google's Native Multimodal Embedding Kills the Fusion LayerGoogle’s new embedding model maps text, images, audio, and video into a single vector space—cutting latency by 70%. -
#1778: Audio Is the New "Read Later" GraveyardWhy listening to AI conversations beats reading dense PDFs, and how serverless GPUs make it cheap. -
#1483: The Recall-Per-Dollar Era: Mastering Vector Database TuningStop burning money on unoptimized vector searches. We dive into HNSW tuning, distance metrics, and the vital "recall-per-dollar" metric. -
#1215: The Vector DB Hangover: Scaling Without Going BrokeStop overpaying for your AI's memory. We break down the math of self-hosting vectors and the rise of serverless search. -
#1212: The Postgres Vector Revolution: Killing the SprawlIs your tech stack a sprawling suburb of microservices? Discover why a 40-year-old database is winning the AI infrastructure war. -
#1124: The Database Explosion: Why One Size No Longer Fits AllFrom vector stores to edge computing, discover why the world now has over 1,000 databases and why Postgres isn't always the answer. -
#1113: The Ghost Company: The High Cost of AI Agent BureaucracyCan a company run entirely on AI? Explore the hidden costs and "agentic bureaucracy" of building autonomous agent hierarchies. -
#371: Beyond the Etch A Sketch: Building Persistent AI MemoryWhy treat AI chats like disposable tissues? Discover how to turn years of prompts into a self-healing, evolving digital brain. -
#263: Why AI Needs a New Kind of MemoryHerman and Corn explore why SQL is losing ground to graph and vector databases. Discover why the "edge" is the new gold standard for AI accuracy. -
#155: Building an Ideation Factory: Beyond Generic AI IdeasLearn how to overcome AI repetition and build a multi-agent "ideation factory" to solve complex local economic challenges. -
#30: Which AI Tools Will You Still Use Next Year?RAG vs. Memory: Are you building resilient AI? Discover the crucial difference between these two foundational pillars.