OMX Helsinki — S&P 500 — DAX — NASDAQ 100 — STOXX 600 — EUR/USD — EUR/SEK — BTC/USD — ETH/USD — Euribor 3M — Euribor 12M —
AI Engineer

AI Engineer

Technology and AI 652,000 subscribers

Stop Renting Your AI’s Memory — Dylan Couzon, Qdrant

02.10.2026
Published: 02.10.2026 Category: Technology and AI

Episode details

Episode description

Superintelligence is coming. The real question is who it belongs to. Dylan Couzon, developer relations engineer at Qdrant, argues that frontier-class models now run on hardware you can own, but the most valuable part of the stack, the memory that makes an assistant yours, still lives in someone else's cloud. He breaks memory down into write, retrieve and forget, explains why retrieval beats a big folder of markdown, and runs a live, fully offline demo: a drone that builds its own searchable memory with sub-millisecond queries in a 15 MB footprint, using Qdrant Edge. In this talk: • Why owning inference gives you autonomy, and owning memory gives you continuity • The CPU / RAM / disk model for LLMs, context and memory • Why retrieval beats dumping everything into the prompt • A live offline demo of embedded vector memory with Qdrant Edge, plus opt-in shared 'hive mind' memory SPEAKER Dylan Couzon, Developer Relations Engineer, Qdrant LinkedIn: https://www.linkedin.com/in/dcouzon/ X: https://x.com/dylancouzon GitHub: https://github.com/Dylancouzon LINKS Qdrant: https://qdrant.tech Qdrant Edge docs: https://qdrant.tech/documentation/edge/ Qdrant Edge launch post: https://qdrant.tech/blog/qdrant-edge/ On-device memory course (GitHub): https://github.com/Dylancouzon/on-device-memory-course CHAPTERS 0:00 Intro 0:12 Who will superintelligence belong to? 1:12 Geniuses with no long-term memory 1:52 Frontier-class models on your own hardware 2:47 The rented AI stack 3:21 What renting really costs 4:36 Autonomy vs continuity 5:21 What memory actually is 6:01 The infrastructure was ready years ago 6:26 Where your memory lives today 6:41 Model = CPU, context = RAM, memory = disk 7:30 Embedded vector search with Qdrant Edge 8:10 Live demo: a drone that remembers 9:40 Semantic search over memories in under 1 ms 10:25 Hive mind: syncing memory to the cloud 10:50 From drones to agents and code assistants 11:44 Memory for your whole day 13:04 Shared memory, with consent 14:09 Who should own your AI? Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/…

Open the AI assistant chat. The chat loads only when you open it.