RAG

RAG precision tuning can quietly cut retrieval accuracy by 40%, putting agentic pipelines at risk

Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI

We replaced RAG with a virtual filesystem for our AI documentation assistant

Agents need vector search more than RAG ever did

Document poisoning in RAG systems: How attackers corrupt AI's sources

Databricks built a RAG agent it says can handle every kind of enterprise search

Show HN: Rust-powered document chunker for RAG – 40x faster, O(1) memory

'Observational memory' cuts AI agent costs 10x and outscores RAG on long-context benchmarks

Enterprises are measuring the wrong part of RAG

Show HN: ShapedQL – A SQL engine for multi-stage ranking and RAG

MemRL outperforms RAG on complex agent benchmarks without fine-tuning

Databricks' Instructed Retriever beats traditional RAG data retrieval by 70% — enterprise metadata was the missing link

Show HN: Evidex – AI Clinical Search (RAG over PubMed/OpenAlex and SOAP Notes)

With 91% accuracy, open source Hindsight agentic memory provides 20/20 vision for AI agents stuck on failing RAG

Snowflake builds new intelligence that goes beyond RAG to query and aggregate thousands of documents at once

Syllabi – Open-source agentic AI with tools, RAG, and multi-channel deploy

Show HN: Pyversity – Fast Result Diversification for Retrieval and RAG

Gemini Embedding: Powering RAG and context engineering

Don't bother parsing: Just use images for RAG

Show HN: Improving search ranking with chess Elo scores