From B-trees to vector DBs back to grep: a viral joke skewers RAG's full circle
burny_tech · x · 2026-09-20
A viral joke tracing three decades of search technology:
- 1990s: B+ trees and inverted indexes — nothing takes more than seconds to find.
- 2010s: distributed full-text search hits billions of logs in milliseconds.
- 2025: chop documents into tiny chunks, burn massive compute on embeddings, stuff retrieved text into a model, and pray it doesn't hallucinate.
- 2026: the LLM itself concludes — this find and grep tool is really nice.
The punchline mocks today's RAG pipelines: huge spend on vector retrieval, only for classic text-search tools to become the model's favorite instruments again.
More from coding & agent
- Hindsight ships 0.8B model for agent memory decisions: 2.5x cheaper, 1.9x faster — victor_explore · 2026-11-04
- Human Oversight Is 70-75% of AI Agent Costs in Banking, McKinsey Finds — mikeflache · 2026-11-04
- Over 80% of Major Financial Institutions Now Run Agentic AI in Production — mikeflache · 2026-11-04
- Mnemos MCP nears launch after shared memory layer fix — RileyRalmuto · 2026-11-04
- Moving mobile dev to remote machines makes it multiplayer across product, design, engineering — rudrank · 2026-11-04
- Kuaishou's EvoRec: self-evolving agentic recommender lifts ad revenue 4.6% — _reachsumit · 2026-11-04