Show HN: Improving RAG with chess Elo scores

Hello HN,

I'm Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents.

We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0.

We trained those models using a novel Elo score inspired pipeline which we describe in detail in the blog attached. In a nutshell, here is an outline of the training steps: * Collect soft preferences between pairs of documents using

12d | Hacker news
Show HN: I gave Claude a sundial and it built a calendar

This is an open‑source Model Context Protocol (MCP) server that gives any LLM a sense of the passage of time.

Most MCP demos wire LLMs to external data stores. That’s useful, but MCP is also a chance to give models perception — extra senses beyond the prompt text.

Six functions (`current_datetime`, `time_difference`, `timestamp_context`, etc.) give Claude/GPT real temporal awareness: It can spot pauses, reason about rhythms, and even label a chat’s “three‑act structure”. Runs loca

12d | Hacker news

Search