What’s Cooking

RedisBlog9 Aug

Reciprocal Rank Fusion: How Hybrid Search Really Works

GleanBlog7 Aug

RAG, or Retrieval Augmented Generation: Revolutionizing AI in 2025

GleanBlog7 Aug

Agentic RAG explained: Smarter retrieval with AI agents

NetflixBlog7 Aug

How and Why Netflix Built a Real-Time Distributed Graph: Part 3 — Querying the graph with gRPC…

CloudflareBlog7 Aug

Unveiling good and bad behaviors on the Agentic Internet

CloudflareBlog7 Aug

Introducing Radar Researcher: An AI tool for exploring Internet data in plain language

CloudflareBlog7 Aug

Unifying Workers AI and AI Gateway into a single AI control plane

Hugging FaceBlog7 Aug

Making Knowledge Distillation Cheap Enough to Run at Scale

Hugging FaceBlog7 Aug

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

PlanetScaleBlog7 Aug

Concurrency vs. Throughput: why more parallelism can make databases slower

DatabricksBlog7 Aug

Managing AI Coding Costs at Scale

AtlassianBlog7 Aug

Building a real-time PWA on Atlassian's own stack

QdrantBlog7 Aug

Pre-Filtering vs Post-Filtering (and Why Qdrant Does Neither)

StripeBlog7 Aug

Agentic payments for marketplaces: How a smart fridge can shop safely

AppleBlog7 Aug

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

AppleBlog7 Aug

Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models

AppleBlog7 Aug

Scaling Categorical Flow Maps

MilvusBlog7 Aug

From Retrieval to Structured Results: Aggregation and ORDER BY in Milvus 3.0

QdrantBlog7 Aug

Filtered Vector Search: What ACORN Fixes, and What Fixes ACORN

DatabricksBlog6 Aug

What are Agentic Workflows?

DatabricksBlog6 Aug

What is Tool Calling?

DecagonBlog6 Aug

"Agent, agent, agent": designing conversations to reduce barge

AtlassianBlog6 Aug

How to Speed Up Connect to Forge Migration With AI

HarveyBlog6 Aug

AML AI Software: Detection Systems Plus the Legal Layer