Our blog

Sequential Probability Ratio Test for AI Products

Modeling Statistical Risk in AI Products

Introducing BLUR: A Benchmark for Tip-of-the-Tongue Search and Reasoning

Introducing the Patronus MCP Server

Announcing the Industry-First Multimodal LLM-as-a-Judge

GLIDER: State-of-the-Art SLM Judge

Llama Guard is Off Duty 😲

Introducing the Patronus + Portkey Integration

Lynx: State-of-the-Art Open Source Hallucination Detection Model

“Within our lifetimes, we will be able to push out enough computational power to simulate reality”

- Tim Sweeney